Tianye Niu

Abstract Purpose: To evaluate multiparametric MRI features in predicting pathologic response after preoperative chemoradiation therapy (CRT) for locally advanced rectal cancer (LARC). Experimental Design: Forty-eight consecutive patients (January 2012–November 2014) receiving neoadjuvant CRT were enrolled. All underwent anatomical T1/T2, diffusion-weighted MRI (DWI) and dynamic contrast-enhanced (DCE) MRI before CRT. A total of 103 imaging features, analyzed using both volume-averaged and voxelized methods, were extracted for each patient. Univariate analyses were performed to evaluate the capability of each individual parameter in predicting pathologic complete response (pCR) or good response (GR) evaluated based on tumor regression grade. Artificial neural network with 4-fold validation technique was further utilized to select the best predictor sets to classify different response groups and the predictive performance was calculated using receiver operating characteristic (ROC) curves. Results: The conventional volume-averaged analysis could provide an area under ROC curve (AUC) ranging from 0.54 to 0.73 in predicting pCR. While if the models were replaced by voxelized heterogeneity analysis, the prediction accuracy measured by AUC could be improved to 0.71–0.79. Similar results were found for GR prediction. In addition, each subcategory images could generate moderate power in predicting the response, which if combining all information together, the AUC could be further improved to 0.84 for pCR and 0.89 for GR prediction, respectively. Conclusions: Through a systematic analysis of multiparametric MR imaging features, we are able to build models with improved predictive value over conventional imaging metrics. The results are encouraging, suggesting the wealth of imaging radiomics should be further explored to help tailoring the treatment into the era of personalized medicine. Clin Cancer Res; 22(21); 5256–64. ©2016 AACR.

Abstract Purpose: The purpose of this study is to develop and validate a nomogram model combing radiomics features and clinical characteristics to preoperatively differentiate grade 1 and grade 2/3 tumors in patients with pancreatic neuroendocrine tumors (pNET). Experimental Design: A total of 137 patients who underwent contrast-enhanced CT from two hospitals were included in this study. The patients from the second hospital (n = 51) were selected as an independent validation set. The arterial phase in contrast-enhanced CT was selected for radiomics feature extraction. The Mann–Whitney U test and least absolute shrinkage and selection operator regression were applied for feature selection and radiomics signature construction. A combined nomogram model was developed by incorporating the radiomics signature with clinical factors. The association between the nomogram model and the Ki-67 index and rate of nuclear mitosis were also investigated respectively. The utility of the proposed model was evaluated using the ROC, area under ROC curve (AUC), calibration curve, and decision curve analysis (DCA). The Kaplan–Meier (KM) analysis was used for survival analysis. Results: An eight-feature–combined radiomics signature was constructed as a tumor grade predictor. The nomogram model combining the radiomics signature with clinical stage showed the best performance (training set: AUC = 0.907; validation set: AUC = 0.891). The calibration curve and DCA demonstrated the clinical usefulness of the proposed nomogram. A significant correlation was observed between the developed nomogram and Ki-67 index and rate of nuclear mitosis, respectively. The KM analysis showed a significant difference between the survival of predicted grade 1 and grade 2/3 groups (P = 0.002). Conclusions: The combined nomogram model developed could be useful in differentiating grade 1 and grade 2/3 tumor in patients with pNETs.

Purpose: Applications of cone‐beam CT (CBCT) to image‐guided radiation therapy (IGRT) are hampered by shading artifacts in the reconstructed images. These artifacts are mainly due to scatter contamination in the projections but also can result from uncorrected beam hardening effects as well as nonlinearities in responses of the amorphous silicon flat panel detectors. While currently, CBCT is mainly used to provide patient geometry information for treatment setup, more demanding applications requiring high‐quality CBCT images are under investigation. To tackle these challenges, many CBCT correction algorithms have been proposed; yet, a standard approach still remains unclear. In this work, we propose a shading correction method for CBCT that addresses artifacts from low‐frequency projection errors. The method is consistent with the current workflow of radiation therapy. Methods: With much smaller inherent scatter signals and more accurate detectors, diagnostic multidetector CT (MDCT) provides high quality CT images that are routinely used for radiation treatment planning. Using the MDCT image as “free” prior information, we first estimate the primary projections in the CBCT scan via forward projection of the spatially registered MDCT data. Since most of the CBCT shading artifacts stem from low‐frequency errors in the projections such as scatter, these errors can be accurately estimated by low‐pass filtering the difference between the estimated and raw CBCT projections. The error estimates are then subtracted from the raw CBCT projections. Our method is distinct from other published correction methods that use the MDCT image as a prior because it is projection‐based and uses limited patient anatomical information from the MDCT image. The merit of CBCT‐based treatment monitoring is therefore retained. Results: The proposed method is evaluated using two phantom studies on tabletop systems. On the Catphan©600 phantom, our approach reduces the reconstruction error from 348 Hounsfield unit (HU) without correction to 4 HU around the object center after correction, and from 375 HU to 17 HU in the high‐contrast regions. In the selected regions of interest (ROIs), the average image contrast is increased by a factor of 3.3. When noise suppression is implemented, the proposed correction substantially improves the contrast‐to‐noise ratio (CNR) and therefore the visibility of low‐contrast objects, as seen in a more challenging pelvis phantom study. Besides a significant improvement in image uniformity, a low‐contrast object of , which is otherwise buried in the shading artifacts, can be clearly identified after the proposed correction due to a CNR increase of 3.1. Compared to a kernel‐based scatter correction method coupled with an analytical beam hardening correction, our approach also shows an overall improved performance with some residual artifacts. Conclusions: By providing effective shading correction, our approach has the potential to improve the accuracy of more advanced CBCT‐based clinical applications for IGRT, such as tumor delineation and dose calculation.

Dual energy CT (DECT) imaging plays an important role in advanced imaging applications due to its capability of material decomposition. Direct decomposition via matrix inversion suffers from significant degradation of image signal-to-noise ratios, which reduces clinical values of DECT. Existing denoising algorithms achieve suboptimal performance since they suppress image noise either before or after the decomposition and do not fully explore the noise statistical properties of the decomposition process. In this work, the authors propose an iterative image-domain decomposition method for noise suppression in DECT, using the full variance-covariance matrix of the decomposed images.The proposed algorithm is formulated in the form of least-square estimation with smoothness regularization. Based on the design principles of a best linear unbiased estimator, the authors include the inverse of the estimated variance-covariance matrix of the decomposed images as the penalty weight in the least-square term. The regularization term enforces the image smoothness by calculating the square sum of neighboring pixel value differences. To retain the boundary sharpness of the decomposed images, the authors detect the edges in the CT images before decomposition. These edge pixels have small weights in the calculation of the regularization term. Distinct from the existing denoising algorithms applied on the images before or after decomposition, the method has an iterative process for noise suppression, with decomposition performed in each iteration. The authors implement the proposed algorithm using a standard conjugate gradient algorithm. The method performance is evaluated using an evaluation phantom (Catphan©600) and an anthropomorphic head phantom. The results are compared with those generated using direct matrix inversion with no noise suppression, a denoising method applied on the decomposed images, and an existing algorithm with similar formulation as the proposed method but with an edge-preserving regularization term.On the Catphan phantom, the method maintains the same spatial resolution on the decomposed images as that of the CT images before decomposition (8 pairs/cm) while significantly reducing their noise standard deviation. Compared to that obtained by the direct matrix inversion, the noise standard deviation in the images decomposed by the proposed algorithm is reduced by over 98%. Without considering the noise correlation properties in the formulation, the denoising scheme degrades the spatial resolution to 6 pairs/cm for the same level of noise suppression. Compared to the edge-preserving algorithm, the method achieves better low-contrast detectability. A quantitative study is performed on the contrast-rod slice of Catphan phantom. The proposed method achieves lower electron density measurement error as compared to that by the direct matrix inversion, and significantly reduces the error variation by over 97%. On the head phantom, the method reduces the noise standard deviation of decomposed images by over 97% without blurring the sinus structures.The authors propose an iterative image-domain decomposition method for DECT. The method combines noise suppression and material decomposition into an iterative process and achieves both goals simultaneously. By exploring the full variance-covariance properties of the decomposed images and utilizing the edge predetection, the proposed algorithm shows superior performance on noise suppression with high image spatial resolution and low-contrast detectability.

Purpose: Accurate lymph node (LN) status evaluation for intrahepatic cholangiocarcinoma (ICC) patients is essential for surgical planning. This study aimed to develop and validate a prediction model for preoperative LN status evaluation in ICC patients. Methods and Materials: A group of 106 ICC patients, who were diagnosed between April 2011 and February 2016, was used for prediction model training. Image features were extracted from T1-weighted contrast-enhanced MR images. A support vector machine (SVM) model was built by using the most LN status-related features, which were selected using the maximum relevance minimum redundancy (mRMR) algorithm. The mRMR method ranked each feature according to its relevance to the LN status and redundancy with other features. An SVM score was calculated for each patient to reflect the LN metastasis (LNM) probability from the SVM model. Finally, a combination nomogram was constructed by incorporating the SVM score and clinical features. An independent group of 42 patients who were diagnosed from March 2016 to November 2017 was used to validate the prediction models. The model performances were evaluated on discrimination, calibration, and clinical utility. Results: The SVM model was constructed based on five selected image features. Significant differences were found between patients with LNM and non-LNM in SVM scores in both groups (the training group: 0.5466 (interquartile range (IQR), 0.4059-0.6985) vs. 0.3226 (IQR, 0.0527-0.4659), P<0.0001; the validation group: 0.5831 (IQR, 0.3641-0.8162) vs. 0.3101 (IQR, 0.1029-0.4661), P=0.0015). The combination nomogram based on the SVM score, the CA 19-9 level, and the MR-reported LNM factor showed better discrimination in separating patients with LNM and non-LNM, comparing to the SVM model alone (AUC: the training group: 0.842 vs. 0.788; the validation group: 0.870 vs. 0.787). Favorable clinical utility was observed using the decision curve analysis for the nomogram. Conclusion: The nomogram, incorporating the SVM score, CA 19-9 level and the MR-reported LNM factor, provided an individualized LN status evaluation and helped clinicians guide the surgical decisions.

Introduction: The emerging field of “radiomics” has considerable potential in disease diagnosis, pathologic grading, prognosis evaluation, and prediction of treatment response. We aimed to develop a novel radiomics nomogram based on radiomics features and clinical characteristics that could preoperatively predict early recurrence (ER) of intrahepatic cholangiocarcinoma (ICC) after partial hepatectomy. Methods: A predictive model was developed from a training cohort comprising 139 ICC patients diagnosed between January 2010 and June 2014. Radiomics features were extracted from arterial-phase image of contrast-enhanced magnetic resonance imaging. Feature selection and construction of a “radiomics signature” were through Spearman’s rank correlation and least absolute shrinkage and selection operator (LASSO) logistic regression. Combined with clinical characteristics, a radiomics nomogram was developed with multivariable logistic regression. Performance of the nomogram was evaluated with regard to discrimination, calibration, and clinical utility. An independent validation cohort involving 70 patients recruited from July 2014 to March 2016 was used to evaluate the utility of the nomogram developed. Results: The radiomics signature, consisting of nine features, differed significantly between ER patients and non-ER patients in training and validation cohorts. The area under the curve (AUC) of the radiomics signature in training and validation cohorts was 0.82 (confidence interval [CI], 0.74–0.88) and 0.77 (95% CI, 0.65–0.86), respectively. The AUC of the radiomics nomogram combining the radiomics signature and clinical stage in the two cohorts was 0.90 (95%CI, 0.83–0.94) and 0.86 (95% CI, 0.76–0.93), respectively. Decision curve analysis confirmed the clinical usefulness of the radiomics nomogram. Conclusion: The non-invasive radiomics nomogram developed using the radiomics signature and clinical stage could be used to predict ER of ICC after partial hepatectomy.

The poor 5-year survival rate in high-grade osteosarcoma (HOS) has not been increased significantly over the past 30 years. This work aimed to develop a radiomics nomogram for survival prediction at the time of diagnosis in HOS.In this retrospective study, an initial cohort of 102 HOS patients, diagnosed from January 2008 to March 2011, was used as the training cohort. Radiomics features were extracted from the pretreatment diagnostic computed tomography images. A radiomics signature was constructed with the lasso algorithm; then, a radiomics score was calculated to reflect survival probability by using the radiomics signature for each patient. A radiomics nomogram was developed by incorporating the radiomics score and clinical factors. A clinical model was constructed by using clinical factors only. The models were validated in an independent cohort comprising 48 patients diagnosed from April 2011 to April 2012. The performance of the nomogram was assessed with respect to its calibration, discrimination, and clinical usefulness. Kaplan–Meier survival analysis was performed.The radiomics nomogram showed better calibration and classification capacity than the clinical model with AUC 0.86 vs. 0.79 for the training cohort, and 0.84 vs. 0.73 for the validation cohort. Decision curve analysis demonstrated the clinical usefulness of the radiomics nomogram. A significant difference (p-value <.05; log-rank test) was observed between the survival curves of the nomogram-predicted survival and non-survival groups. The radiomics nomogram may assist clinicians in tailoring appropriate therapy.

To predict the neoadjuvant chemoradiation therapy (CRT) response in patients with locally advanced rectal cancer (LARC) using radiomics and deep learning based on pre-treatment MRI and a mid-radiation follow-up MRI taken 3–4 weeks after the start of CRT. A total of 51 patients were included, 45 with pre-treatment, 41 with mid-radiation therapy (RT), and 35 with both MRI sets. The multi-parametric MRI protocol included T2, diffusion weighted imaging (DWI) with b-values of 0 and 800 s/mm2, and dynamic-contrast-enhanced (DCE) MRI. After completing CRT and surgery, the specimen was examined to determine the pathological response based on the tumor regression grade. The tumor ROI was manually drawn on the post-contrast image and mapped to other sequences. The total tumor volume and mean apparent diffusion coefficient (ADC) were measured. Radiomics using GLCM texture and histogram parameters, and deep learning using a convolutional neural network (CNN), were performed to differentiate pathologic complete response (pCR) vs. non-pCR, and good response (GR) vs. non-GR. Tumor volume decreased and ADC increased significantly in the mid-RT MRI compared to the pre-treatment MRI. For predicting pCR vs. non-pCR, combining ROI and radiomics features achieved an AUC of 0.80 for pre-treatment, 0.82 for mid-RT, and 0.86 for both MRI together. For predicting GR vs. non-GR, the AUC was 0.91 for pre-treatment, 0.92 for mid-RT, and 0.93 for both MRI together. In deep learning using CNN, combining pre-treatment and mid-RT MRI achieved a higher accuracy compared to using either dataset alone, with AUC of 0.83 for predicting pCR vs. non-pCR. Radiomics based on pre-treatment and early follow-up multi-parametric MRI in LARC patients receiving CRT could extract comprehensive quantitative information to predict final pathologic response.

The difficulty of assessment of neoadjuvant chemotherapeutic response preoperatively may hinder personalized-medicine strategies that depend on the results from pathological examination.A total of 191 patients with high-grade osteosarcoma (HOS) were enrolled retrospectively from November 2013 to November 2017 and received neoadjuvant chemotherapy (NCT). A cutoff time of November 2016 was used to divide the training set and validation set. All patients underwent diagnostic CTs before and after chemotherapy. By quantifying the tumor regions on the CT images before and after NCT, 540 delta-radiomic features were calculated. The interclass correlation coefficients for segmentations of inter/intra-observers and feature pair-wise correlation coefficients (Pearson) were used for robust feature selection. A delta-radiomics signature was constructed using the lasso algorithm based on the training set. Radiomics signatures built from single-phase CT were constructed for comparison purpose. A radiomics nomogram was then developed from the multivariate logistic regression model by combining independent clinical factors and the delta-radiomics signature. The prediction performance was assessed using area under the ROC curve (AUC), calibration curves and decision curve analysis (DCA).The delta-radiomics signature showed higher AUC than single-CT based radiomics signatures in both training and validation cohorts. The delta-radiomics signature, consisting of 8 selected features, showed significant differences between the pathologic good response (pGR) (necrosis fraction ≥90%) group and the non-pGR (necrosis fraction < 90%) group (P < 0.0001, in both training and validation sets). The delta-radiomics nomogram, which consisted of the delta-radiomics signature and new pulmonary metastasis during chemotherapy showed good calibration and great discrimination capacity with AUC 0.871 (95% CI, 0.804 to 0.923) in the training cohort, and 0.843 (95% CI, 0.718 to 0.927) in the validation cohort. The DCA confirmed the clinical utility of the radiomics model.The delta-radiomics nomogram incorporating the radiomics signature and clinical factors in this study could be used for individualized pathologic response evaluation after chemotherapy preoperatively and help tailor appropriate chemotherapy and further treatment plans.

We aimed to develop and validate a nomogram combining bi-regional radiomics features from multimodal magnetic resonance imaging (MRI) and clinicoradiological characteristics to preoperatively predict microvascular invasion (MVI) of hepatocellular carcinoma (HCC).A total of 267 HCC patients were divided into training (n=194) and validation (n=73) cohorts according to MRI data. Bi-regional features were extracted from whole tumors and peritumoral regions in multimodal MRI. The minimum redundancy maximum relevance (mRMR) algorithm was applied to select features and build signatures. The predictive performance of the optimal radiomics signature was further evaluated within subgroups defined by tumor size and alpha fetoprotein (AFP) level. Then, a radiomics nomogram including the optimal radiomics signature, radiographic descriptors, and clinical variables was developed using multivariable regression. The nomogram performance was evaluated based on its discrimination, calibration, and clinical utility.The fusion radiomics signature derived from triphasic dynamic contrast-enhanced (DCE) MR images can effectively classify MVI and non-MVI HCC patients, with an AUC of 0.784 (95% CI: 0.719-0.840) in the training cohort and 0.820 (95% CI: 0.713-0.900) in the validation cohort. The fusion radiomics signature also performed well in the subgroups defined by the two risk factors, respectively. The nomogram, consisting of the fusion radiomics signature, arterial peritumoral enhancement, and AFP level, outperformed the clinicoradiological prediction model in the validation cohort (AUCs: 0.858 vs. 0.729; P=0.022), fitting well in the calibration curves (P>0.05). Decision curves confirmed the clinical utility of the nomogram.The radiomics nomogram can serve as a visual predictive tool for MVI in HCCs, and thus assist clinicians in selecting optimal treatment strategies to improve clinical outcomes.

Purpose: Applications of volumetric CT (VCT) are hampered by shading and streaking artifacts in the reconstructed images. These artifacts are mainly due to strong x‐ray scatter signals accompanied with the large illumination area within one projection, which lead to CT number inaccuracy, image contrast loss and spatial nonuniformity. Although different scatter correction algorithms have been proposed in literature, a standard solution still remains unclear. Measurement‐based methods use a beam blocker to acquire scatter samples. These techniques have unrivaled advantages over other existing algorithms in that they are simple and efficient, and achieve high scatter estimation accuracy without prior knowledge of the imaged object. Nevertheless, primary signal loss is inevitable in the scatter measurement, and multiple scans or moving the beam blocker during data acquisition are typically employed to compensate for the missing primary data. In this paper, we propose a new measurement‐based scatter correction algorithm without primary compensation for full‐fan VCT. An accurate reconstruction is obtained with one single‐scan and a stationary x‐ray beam blocker, two seemingly incompatible features which enable simple and efficient scatter correction without increase of scan time or patient dose. Methods: Based on the CT reconstruction theory, we distribute the blocked data over the projection area where primary signals are considered approximately redundant in a full scan, such that the CT image quality is not degraded even with primary loss. Scatter is then accurately estimated by interpolation and scatter‐corrected CT images are obtained using an FDK‐based reconstruction algorithm. Results: The proposed method is evaluated using two phantom studies on a tabletop CBCT system. On the Catphan©600 phantom, our approach reduces the reconstruction error from 207 Hounsfield unit (HU) to 9 HU in the selected region of interest, and improves the image contrast by a factor of 2.0 in the high‐contrast regions. On an anthropomorphic head phantom, the reconstruction error is reduced from 97 HU to 6 HU in the soft tissue region and image spatial nonuniformity decreases from 27% to 5% after correction. Conclusions: Our method inherits the main advantages of measurement‐based methods while avoiding their shortcomings. It has the potential to become a practical scatter correction solution widely implementable on different VCT systems.

Recent advances in compressed sensing (CS) enable accurate CT image reconstruction from highly undersampled and noisy projection measurements, due to the sparsifiable feature of most CT images using total variation (TV). These novel reconstruction methods have demonstrated advantages in clinical applications where radiation dose reduction is critical, such as onboard cone-beam CT (CBCT) imaging in radiation therapy. The image reconstruction using CS is formulated as either a constrained problem to minimize the TV objective within a small and fixed data fidelity error, or an unconstrained problem to minimize the data fidelity error with TV regularization. However, the conventional solutions to the above two formulations are either computationally inefficient or involved with inconsistent regularization parameter tuning, which significantly limit the clinical use of CS-based iterative reconstruction. In this paper, we propose an optimization algorithm for CS reconstruction which overcomes the above two drawbacks.The data fidelity tolerance of CS reconstruction can be well estimated based on the measured data, as most of the projection errors are from Poisson noise after effective data correction for scatter and beam-hardening effects. We therefore adopt the TV optimization framework with a data fidelity constraint. To accelerate the convergence, we first convert such a constrained optimization using a logarithmic barrier method into a form similar to that of the conventional TV regularization based reconstruction but with an automatically adjusted penalty weight. The problem is then solved efficiently by gradient projection with an adaptive Barzilai-Borwein step-size selection scheme. The proposed algorithm is referred to as accelerated barrier optimization for CS (ABOCS), and evaluated using both digital and physical phantom studies.ABOCS directly estimates the data fidelity tolerance from the raw projection data. Therefore, as demonstrated in both digital Shepp-Logan and physical head phantom studies, consistent reconstruction performances are achieved using the same algorithm parameters on scans with different noise levels and∕or on different objects. On the contrary, the penalty weight in a TV regularization based method needs to be fine-tuned in a large range (up to seven times) to maintain the reconstructed image quality. The improvement of ABOCS on computational efficiency is demonstrated in the comparisons with adaptive-steepest-descent-projection-onto-convex-sets (ASD-POCS), an existing CS reconstruction algorithm also using constrained optimization. ASD-POCS alternatively minimizes the TV objective using adaptive steepest descent (ASD) and the data fidelity error using projection onto convex sets (POCS). For similar image qualities of the Shepp-Logan phantom, ABOCS requires less computation time than ASD-POCS in MATLAB by more than one order of magnitude.We propose ABOCS for CBCT reconstruction. As compared to other published CS-based algorithms, our method has attractive features of fast convergence and consistent parameter settings for different datasets. These advantages have been demonstrated on phantom studies.

Purpose : Quantitative cone‐beam CT (CBCT) imaging is on increasing demand for high‐performance image guided radiation therapy (IGRT). However, the current CBCT has poor image qualities mainly due to scatter contamination. Its current clinical application is therefore limited to patient setup based on only bony structures. To improve CBCT imaging for quantitative use, we recently proposed a correction method using planning CT (pCT) as the prior knowledge. Promising phantom results have been obtained on a tabletop CBCT system, using a correction scheme with rigid registration and without iterations. More challenges arise in clinical implementations of our method, especially because patients have large organ deformation in different scans. In this paper, we propose an improved framework to extend our method from bench to bedside by including several new components. Methods : The basic principle of our correction algorithm is to estimate the primary signals of CBCT projections via forward projection on the pCT image, and then to obtain the low‐frequency errors in CBCT raw projections by subtracting the estimated primary signals and low‐pass filtering. We improve the algorithm by using deformable registration to minimize the geometry difference between the pCT and the CBCT images. Since the registration performance relies on the accuracy of the CBCT image, we design an optional iterative scheme to update the CBCT image used in the registration. Large correction errors result from the mismatched objects in the pCT and the CBCT scans. Another optional step of gas pocket and couch matching is added into the framework to reduce these effects. Results : The proposed method is evaluated on four prostate patients, of which two cases are presented in detail to investigate the method performance for a large variety of patient geometry in clinical practice. The first patient has small anatomical changes from the planning to the treatment room. Our algorithm works well even without the optional iterations and the gas pocket and couch matching. The image correction on the second patient is more challenging due to the effects of gas pockets and attenuating couch. The improved framework with all new components is used to fully evaluate the correction performance. The enhanced image quality has been evaluated using mean CT number and spatial nonuniformity (SNU) error as well as contrast improvement factor. If the pCT image is considered as the ground truth, on the four patients, the overall mean CT number error is reduced from over 300 HU to below 16 HU in the selected regions of interest (ROIs), and the SNU error is suppressed from over 18% to below 2%. The average soft‐tissue contrast is improved by an average factor of 2.6. Conclusions : We further improve our pCT‐based CBCT correction algorithm for clinical use. Superior correction performance has been demonstrated on four patient studies. By providing quantitative CBCT images, our approach significantly increases the accuracy of advanced CBCT‐based clinical applications for IGRT.

Purpose: Dual-energy CT (DECT) is being increasingly used for its capability of material decomposition and energy-selective imaging. A generic problem of DECT, however, is that the decomposition process is unstable in the sense that the relative magnitude of decomposed signals is reduced due to signal cancellation while the image noise is accumulating from the two CT images of independent scans. Direct image decomposition, therefore, leads to severe degradation of signal-to-noise ratio on the resultant images. Existing noise suppression techniques are typically implemented in DECT with the procedures of reconstruction and decomposition performed independently, which do not explore the statistical properties of decomposed images during the reconstruction for noise reduction. In this work, the authors propose an iterative approach that combines the reconstruction and the signal decomposition procedures to minimize the DECT image noise without noticeable loss of resolution. Methods: The proposed algorithm is formulated as an optimization problem, which balances the data fidelity and total variation of decomposed images in one framework, and the decomposition step is carried out iteratively together with reconstruction. The noise in the CT images from the proposed algorithm becomes well correlated even though the noise of the raw projections is independent on the two CT scans. Due to this feature, the proposed algorithm avoids noise accumulation during the decomposition process. The authors evaluate the method performance on noise suppression and spatial resolution using phantom studies and compare the algorithm with conventional denoising approaches as well as combined iterative reconstruction methods with different forms of regularization. Results: On the Catphan©600 phantom, the proposed method outperforms the existing denoising methods on preserving spatial resolution at the same level of noise suppression, i.e., a reduction of noise standard deviation by one order of magnitude. This improvement is mainly attributed to the high noise correlation in the CT images reconstructed by the proposed algorithm. Iterative reconstruction using different regularization, including quadratic orq-generalized Gaussian Markov random field regularization, achieves similar noise suppression from high noise correlation. However, the proposed TV regularization obtains a better edge preserving performance. Studies of electron density measurement also show that our method reduces the average estimation error from 9.5% to 7.1%. On the anthropomorphic head phantom, the proposed method suppresses the noise standard deviation of the decomposed images by a factor of ∼14 without blurring the fine structures in the sinus area. Conclusions: The authors propose a practical method for DECT imaging reconstruction, which combines the image reconstruction and material decomposition into one optimization framework. Compared to the existing approaches, our method achieves a superior performance on DECT imaging with respect to decomposition accuracy, noise reduction, and spatial resolution.

BackgroundEvaluating clinical outcome prior to concurrent chemoradiotherapy remains challenging for oesophageal squamous cell carcinoma (OSCC) as traditional prognostic markers are assessed at the completion of treatment. Herein, we investigated the potential of using sub-region radiomics as a novel tumour biomarker in predicting overall survival of OSCC patients treated by concurrent chemoradiotherapy.MethodsIndependent patient cohorts from two hospitals were included for training (n = 87) and validation (n = 46). Radiomics features were extracted from sub-regions clustered from patients' tumour regions using K-means method. The LASSO regression for ‘Cox’ method was used for feature selection. The survival prediction model was constructed based on the sub-region radiomics features using the Cox proportional hazards model. The clinical and biological significance of radiomics features were assessed by correlation analysis of clinical characteristics and copy number alterations(CNAs) in the validation dataset.FindingsThe overall survival prediction model combining with seven sub-regional radiomics features was constructed. The C-indexes of the proposed model were 0.729 (0.656–0.801, 95% CI) and 0.705 (0.628–0.782, 95%CI) in the training and validation cohorts, respectively. The 3-year survival receiver operating characteristic (ROC) curve showed an area under the ROC curve of 0.811 (0.670–0.952, 95%CI) in training and 0.805 (0.638–0.973, 95%CI) in validation. The correlation analysis showed a significant correlation between radiomics features and CNAs.InterpretationThe proposed sub-regional radiomics model could predict the overall survival risk for patients with OSCC treated by definitive concurrent chemoradiotherapy.FundThis work was supported by the Zhejiang Provincial Foundation for Natural Sciences, National Natural Science Foundation of China.

Purpose Dual‐energy CT ( DECT ) has been increasingly used in imaging applications because of its capability for material differentiation. However, material decomposition suffers from magnified noise from two CT images of independent scans, leading to severe degradation of image quality. Existing algorithms exhibit suboptimal decomposition performance because they fail to fully depict the mapping relationship between DECT images and basis materials under noisy conditions. Convolutional neural network exhibits great promise in the modeling of data coupling and has recently become an important technique in medical imaging application. Inspired by its impressive potential, we developed a new Butterfly network to perform the image domain dual material decomposition. Methods The Butterfly network is derived from the model of image domain DECT decomposition by exploring the geometric relationship between the mapping functions of the data model and network components. The network is designed as the double‐entry double‐out crossover architecture based on the decomposition formulation. It enters a pair of dual‐energy images as inputs and defines the ground true decomposed images as each label. The crossover architecture, which plays an important role in material decomposition, is designed to implement the information exchange between the two material generation pathways in the network. The proposed network is further applied on the digital phantom and clinical data to evaluate its performance. Results The qualitative and quantitative evaluations of the material decomposition of digital phantoms and clinical data indicate that the proposed network outperforms its counterparts. For the digital phantom, the proposed network reduces the standard deviation ( SD ) of noise in tissue, bone, and mixture regions by an average of 95.75% and 86.58% compared with the direct matrix inversion and the conventional iterative method, respectively. The line profiles and image biases of the decomposition results of digital phantom indicate that the proposed network provides the decomposition results closest to the ground truth. The proposed network reduces the SD of the noise in decomposed images of clinical head data by over 90% and 80% compared with the direct matrix inversion and conventional iterative method, respectively. As the modulation transfer function decreases to 50%, the proposed network increases the spatial resolution by average factors of 1.34 and 1.17 compared with the direct matrix inversion and conventional iterative methods, respectively. The proposed network is further applied to the clinical abdomen data. Among the three methods, the proposed method received the highest score from six radiologists in the visual inspection of noise suppression in the clinical data. Conclusions We develop a model‐based Butterfly network to perform image domain material decomposition for DECT . The decomposition results of digital phantom validate its capability of decomposing two basis materials from DECT images. The proposed approach also leads to higher decomposition quality in noise suppression on clinical datasets as compared with those using conventional schemes.

Dual-energy CT (DECT) enhances tissue characterization because of its basis material decomposition capability. In addition to conventional two-material decomposition from DECT measurements, multimaterial decomposition (MMD) is required in many clinical applications. To solve the ill-posed problem of reconstructing multi-material images from dual-energy measurements, additional constraints are incorporated into the formulation, including volume and mass conservation and the assumptions that there are at most three materials in each pixel and various material types among pixels. The recently proposed flexible image-domain MMD method decomposes pixels sequentially into multiple basis materials using a direct inversion scheme which leads to magnified noise in the material images. In this paper, we propose a statistical image-domain MMD method for DECT to suppress the noise.The proposed method applies penalized weighted least-square (PWLS) reconstruction with a negative log-likelihood term and edge-preserving regularization for each material. The statistical weight is determined by a data-based method accounting for the noise variance of high- and low-energy CT images. We apply the optimization transfer principles to design a serial of pixel-wise separable quadratic surrogates (PWSQS) functions which monotonically decrease the cost function. The separability in each pixel enables the simultaneous update of all pixels.The proposed method is evaluated on a digital phantom, Catphan©600 phantom and three patients (pelvis, head, and thigh). We also implement the direct inversion and low-pass filtration methods for a comparison purpose. Compared with the direct inversion method, the proposed method reduces noise standard deviation (STD) in soft tissue by 95.35% in the digital phantom study, by 88.01% in the Catphan©600 phantom study, by 92.45% in the pelvis patient study, by 60.21% in the head patient study, and by 81.22% in the thigh patient study, respectively. The overall volume fraction accuracy is improved by around 6.85%. Compared with the low-pass filtration method, the root-mean-square percentage error (RMSE(%)) of electron densities in the Catphan©600 phantom is decreased by 20.89%. As modulation transfer function (MTF) magnitude decreased to 50%, the proposed method increases the spatial resolution by an overall factor of 1.64 on the digital phantom, and 2.16 on the Catphan©600 phantom. The overall volume fraction accuracy is increased by 6.15%.We proposed a statistical image-domain MMD method using DECT measurements. The method successfully suppresses the magnified noise while faithfully retaining the quantification accuracy and anatomical structure in the decomposed material images. The proposed method is practical and promising for advanced clinical applications using DECT imaging.

In computed tomography, automated detection of pulmonary nodules with a broad spectrum of appearance is still a challenge, especially, in the detection of small nodules.An automated detection system usually contains two major steps: candidate detection and false positive (FP) reduction.We propose a novel strategy for fast candidate detection from volumetric chest CT scans, which can minimize false negatives (FNs) and false positives (FPs).The core of the strategy is a nodule-size-adaptive deep model that can detect nodules of various types, locations, and sizes from 3D images.After candidate detection, each result is located with a bounding cube, which can provide rough size information of the detected objects.Furthermore, we propose a simple yet effective CNNs-based classifier for FP reduction, which benefits from the candidate detection.The performance of the proposed nodule detection was evaluated on both independent and publicly available datasets.Our detection could reach high sensitivity with few FPs and it was comparable with the state-of-the-art systems and manual screenings.The study demonstrated that excellent candidate detection plays an important role in the nodule detection and can simplify the design of the FP reduction.The proposed candidate detection is an independent module, so it can be incorporated with any other FP reduction methods.Besides, it can be used as a potential solution for other similar clinical applications.

Current lung cancer diagnosis methods encounter delayed visual confirmation of tumor foci and low-resolution metrics in imaging findings, which delays the early treatment of tumors. Here, we developed a potent lung cancer imaging and treatment strategy centered around a nanotransformational concept of tumor iron mineralization in situ, which employs Prussian blue/calcium peroxide nanocomposites as a precursor. The resultant iron mineralization in tumor cells greatly facilitates the early and differential diagnosis of lung carcinoma from benign nodules via medical imaging, meanwhile introducing oxidative stress to activate the cellular apoptosis and ferroptosis pathways, resulting in inhibition of the malignant behavior of tumor cells. Tumor-microenvironment-triggered iron mineralization enables integration of the detection and prevention of tumor metastasis at its early stages with no assistance of toxic drugs, which offers a potential solution for the precise management of lung cancer with ideal outcomes.

To investigate the feasibility of integrating radiomics and morphological features based on computed tomography enterography (CTE) for developing a noninvasive grading model for mucosal activity and surgery risk of Crohn's disease (CD) patients.A total of 167 patients from three centers were enrolled. Radiomics and image morphological features were extracted to quantify segmental and global simple endoscopic score for Crohn's disease (SES-CD). An image-fusion-based support vector machine (SVM) classifier was used for grading SES-CD and identifying moderate-to-severe SES-CD. The performance of the predictive model was assessed using the area under the receiver operating characteristic curve (AUC). A multiparametric model was developed to predict surgical progression in CD patients by combining sum-image scores and clinical data.The AUC values of the multicategorical segmental SES-CD fusion radiomic model based on a combination of luminal and mesenteric radiomics were 0.828 and 0.709 in training and validation cohorts. The image fusion model integrating the fusion radiomics and morphological features could accurately distinguish bowel segments with moderate-to-severe SES-CD in both the training cohort (AUC = 0.847, 95% confidence interval (CI): 0.784-0.902) and the validation cohort (AUC = 0.896, 95% CI: 0.812-0.960). A predictive nomogram for interval surgery was developed based on multivariable cox analysis.This study demonstrated the feasibility of integrating lumen and mesentery radiomic features to develop a promising noninvasive grading model for mucosal activity of CD. In combination with clinical data, the fusion-image score may yield an accurate prognostic model for time to surgery.

PurposeThe 4π static noncoplanar radiation therapy delivery technique has demonstrated better normal tissue sparing and dose conformity than the clinically used volumetric modulated arc therapy (VMAT). It is unclear whether this is a fundamental limitation of VMAT delivery or the coplanar nature of its typical clinical plans. The dosimetry and the limits of normal tissue toxicity constrained dose escalation of coplanar VMAT, noncoplanar VMAT and 4π radiation therapy are quantified in this study.Methods and materialsClinical stereotactic body radiation therapy plans for 20 liver patients receiving 30 to 60 Gy using coplanar VMAT (cVMAT) were replanned using 3 to 4 partial noncoplanar arcs (nVMAT) and 4π with 20 intensity modulated noncoplanar fields. The conformity number, homogeneity index, 50% dose spillage volume, normal liver volume receiving >15 Gy, dose to organs at risk (OARs), and tumor control probability were compared for all 3 treatment plans. The maximum tolerable dose yielding a normal liver normal tissue control probability <1%, 5%, and 10% was calculated with the Lyman-Kutcher-Burman model for each plan as well as the resulting survival fractions at 1, 2, 3, and 4 years.ResultsCompared with cVMAT, the nVMAT and 4π plans reduced liver volume receiving >15 Gy by an average of 5 cm3 and 80 cm3, respectively. 4π reduced the 50% dose spillage volume by ∼23% compared with both VMAT plans, and either significantly decreased or maintained OAR doses. The 4π maximum tolerable doses and survival fractions were significantly higher than both cVMAT and nVMAT (P < .05) for all normal liver normal tissue control probability limits used in this study.ConclusionsThe 4π technique provides significantly better OAR sparing than both cVMAT and nVMAT and enables more clinically relevant dose escalation for tumor local control. Therefore, despite the current accessibility of nVMAT, it is not a viable alternative to 4π for liver SBRT.

Dual-energy CT (DECT) expands applications of CT imaging in its capability to decompose CT images into material images. However, decomposition via direct matrix inversion leads to large noise amplification and limits quantitative use of DECT. Their group has previously developed a noise suppression algorithm via penalized weighted least-square optimization with edge-preservation regularization (PWLS-EPR). In this paper, the authors improve method performance using the same framework of penalized weighted least-square optimization but with similarity-based regularization (PWLS-SBR), which substantially enhances the quality of decomposed images by retaining a more uniform noise power spectrum (NPS).The design of PWLS-SBR is based on the fact that averaging pixels of similar materials gives a low-noise image. For each pixel, the authors calculate the similarity to other pixels in its neighborhood by comparing CT values. Using an empirical Gaussian model, the authors assign high/low similarity value to one neighboring pixel if its CT value is close/far to the CT value of the pixel of interest. These similarity values are organized in matrix form, such that multiplication of the similarity matrix to the image vector reduces image noise. The similarity matrices are calculated on both high- and low-energy CT images and averaged. In PWLS-SBR, the authors include a regularization term to minimize the L-2 norm of the difference between the images without and with noise suppression via similarity matrix multiplication. By using all pixel information of the initial CT images rather than just those lying on or near edges, PWLS-SBR is superior to the previously developed PWLS-EPR, as supported by comparison studies on phantoms and a head-and-neck patient.On the line-pair slice of the Catphan(©)600 phantom, PWLS-SBR outperforms PWLS-EPR and retains spatial resolution of 8 lp/cm, comparable to the original CT images, even at 90% reduction in noise standard deviation (STD). Similar performance on spatial resolution is observed on an anthropomorphic head phantom. In addition, results of PWLS-SBR show substantially improved image quality due to preservation of image NPS. On the Catphan(©)600 phantom, NPS using PWLS-SBR has a correlation of 93% with that via direct matrix inversion, while the correlation drops to -52% for PWLS-EPR. Electron density measurement studies indicate high accuracy of PWLS-SBR. On seven different materials, the measured electron densities calculated from the decomposed material images using PWLS-SBR have a root-mean-square error (RMSE) of 1.20%, while the results of PWLS-EPR have a RMSE of 2.21%. In the study on a head-and-neck patient, PWLS-SBR is shown to reduce noise STD by a factor of 3 on material images with image qualities comparable to CT images, whereas fine structures are lost in the PWLS-EPR result. Additionally, PWLS-SBR better preserves low contrast on the tissue image.The authors propose improvements to the regularization term of an optimization framework which performs iterative image-domain decomposition for DECT with noise suppression. The regularization term avoids calculation of image gradient and is based on pixel similarity. The proposed method not only achieves a high decomposition accuracy, but also improves over the previous algorithm on NPS as well as spatial resolution.

Ring artifacts in cone beam computed tomography (CBCT) images are caused by pixel gain variations using flat-panel detectors, and may lead to structured non-uniformities and deterioration of image quality. The purpose of this study is to propose a method of general ring artifact removal in CBCT images. This method is based on the polar coordinate system, where the ring artifacts manifest as stripe artifacts. Using relative total variation, the CBCT images are first smoothed to generate template images with fewer image details and ring artifacts. By subtracting the template images from the CBCT images, residual images with image details and ring artifacts are generated. As the ring artifact manifests as a stripe artifact in a polar coordinate system, the artifact image can be extracted by mean value from the residual image; the image details are generated by subtracting the artifact image from the residual image. Finally, the image details are compensated to the template image to generate the corrected images. The proposed framework is iterated until the differences in the extracted ring artifacts are minimized. We use a 3D Shepp–Logan phantom, Catphan©504 phantom, uniform acrylic cylinder, and images from a head patient to evaluate the proposed method. In the experiments using simulated data, the spatial uniformity is increased by 1.68 times and the structural similarity index is increased from 87.12% to 95.50% using the proposed method. In the experiment using clinical data, our method shows high efficiency in ring artifact removal while preserving the image structure and detail. The iterative approach we propose for ring artifact removal in cone-beam CT is practical and attractive for CBCT guided radiation therapy.

Scatter correction is an essential technique to improve the image quality of cone-beam CT (CBCT). Although different scatter correction methods have been proposed in the literature, a standard solution is still being studied due to the limitations including accuracy, computation efficiency and generalization. In this paper, we propose a novel scatter correction scheme for CBCT using a deep residual convolution neural network (DRCNN) to overcome the limitations. The proposed method combines the deep convolution neural network (CNN) and the residual learning framework (RLF) to train the mapping function from the uncorrected image to the corrected image. Two residual network modules (RNMs) are built based on the RLF to improve the accuracy of the mapping function by strengthening the propagation of the gradient. The dropout operations are applied as the regularizer of the network to avoid the overfitting problem. The RMSE of the corrected images reconstructed using the DRCNN is reduced from over 200 HU to be about 20 HU. The structural similarity (SSIM) is slightly increased from 0.95 to 0.99, indicating that the proposed scheme maintains the anatomical structure. The proposed DRCNN has a higher accuracy of scatter correction than the networks without the RLF or the dropout operations. The proposed network is effective, efficient and robust as a solution to the CBCT scatter correction.

The purpose of this study was to investigate the predictive performance of 2D and 3D image features across multi-organ cancers using multi-modality images in radiomics studies.

Background To develop and validate a radiomics method via integrating tumor and lymph node radiomics for the preoperative prediction of lymph node (LN) status in gastric cancer (GC). Materials and methods We retrospectively collected 170 contrast-enhanced abdominal CT images from GC patients. Five times repeated random hold-out experiment was employed. Tumor and nodal radiomics features were extracted from each individual tumor and LN respectively, and then multi-step feature selection was performed. The optimal tumor and nodal features were selected using Pearson correlation analysis and sequential forward floating selection (SFFS) algorithm. After feature fusion, the SFFS algorithm was used to develop radiomics signatures. The performance of the radiomics signatures developed based on logistic regression classifier was further analyzed and compared using the area under the receiver operating characteristic curve (AUC). Results The AUC values, reported as mean ± standard deviation, were 0.9319 ± 0.0129 and 0.8546 ± 0.0261 for the training and validation cohorts respectively. The radiomic signatures could predict LN status, especially in T2-stage, diffuse-type and moderately/well differentiated GC. After integrating clinicopathologic information, the radiomic-clinicopathologic model (training cohort, 0.9432 ± 0.0129; validation cohort, 0.8764 ± 0.0322) showed a better discrimination capability than other radiomics models and clinicopathologic model. The radiomic-clinicopathologic model also showed superior performance to the gastroenterologist’ decision in all experiments, and outperformed the radiologist in some experiments. Conclusion Our proposed method presented good predictive performance and great potential for predicting LNM in GC. As a noninvasive preoperative prediction tool, it can be helpful for guiding the prognosis and treatment decision-making in GC patients.

A novel method is proposed to obtain four-dimensional (4D) cone-beam computed tomography (CBCT) images from a routine scan in patients with upper abdominal cancer. The projections are sorted according to the location of the lung diaphragm before being reconstructed to phase-sorted data. A multiscale-discriminator generative adversarial network (MSD-GAN) is proposed to alleviate the severe streaking artifacts in the original images. The MSD-GAN is trained using simulated CBCT datasets from patient planning CT images. The enhanced images are further used to estimate the deformable vector field (DVF) among breathing phases using a deformable image registration method. The estimated DVF is then applied in the motion-compensated ordered-subset simultaneous algebraic reconstruction approach to generate 4D CBCT images. The proposed MSD-GAN is compared with U-Net on the performance of image enhancement. Results show that the proposed method significantly outperforms the total variation regularization-based iterative reconstruction approach and the method using only MSD-GAN to enhance original phase-sorted images in simulation and patient studies on 4D reconstruction quality. The MSD-GAN also shows higher accuracy than the U-Net. The proposed method enables a practical way for 4D-CBCT imaging from a single routine scan in upper abdominal cancer treatment including liver and pancreatic tumors.

Increased noise is a general concern for dual-energy material decomposition. Here, we develop an image-domain material decomposition algorithm for dual-energy CT (DECT) by incorporating an edge-preserving filter into the Local HighlY constrained backPRojection Reconstruction (HYPR-LR) framework. With effective use of the non-local mean, the proposed algorithm, which is referred to as HYPR-NLM, reduces the noise in dual energy decomposition while preserving the accuracy of quantitative measurement and spatial resolution of the material-specific dual energy images. We demonstrate the noise reduction and resolution preservation of the algorithm with iodine concentrate numerical phantom by comparing the HYPR-NLM algorithm to the direct matrix inversion, HYPR-LR and iterative image-domain material decomposition (Iter-DECT). We also show the superior performance of the HYPR-NLM over the existing methods by using two sets of cardiac perfusing imaging data. The reference drawn from the comparison study includes: (1) HYPR-NLM significantly reduces the DECT material decomposition noise while preserving quantitative measurements and high-frequency edge information, and (2) HYPR-NLM is robust with respect to parameter selection.

Background: Serous cystadenoma (SCA), mucinous cystadenoma (MCN), and intraductal papillary mucinous neoplasm (IPMN) are three subtypes of pancreatic cystic neoplasm (PCN). Due to the potential of malignant-transforming, patients with MCN and IPMN require radical surgery while patients with SCA need periodic surveillance. However, accurate pre-surgery diagnosis between SCA, MCN, and IPMN remains challenging in the clinic. Methods: This study enrolled 164 patients including 76 with SCA, 40 with MCN and 48 with IPMN. Patients were randomly split into a training cohort (n = 115) and validation cohort (n = 41). We performed statistical analysis and Boruta method to screen significantly distinct clinical factors and radiomics features extracted on pre-surgery contrast-enhanced computed tomography (CECT) images among three subtypes. Three reliable machine-learning algorithms, support vector machine (SVM), random forest (RF) and artificial neural network (ANN), were utilized to construct classifiers based on important radiomics features and clinical parameters. Precision, recall, and F1-score were calculated to assess the performance of the constructed classifiers. Results: Nine of 547 radiomics features and eight clinical factors showed a significant difference among SCA, MCN, and IPMN. Five radiomics features (Histogram_Entropy, Histogram_Skeweness, LLL_GLSZM_GLV, Histogram_Uniformity, HHL_Histogram_Kurtosis), and four clinical factors, including serum carbohydrate antigen 19-9, sex, age, and serum carcinoembryonic antigen, were identified important by Boruta method. The SVM classifier achieved an overall accuracy of 73.04% in training cohort and 71.43% in validation cohort, respectively. The RF classifier achieved overall accuracy of 84.35 and 79.59%, respectively. The constructed ANN model showed an overall accuracy of 77.39% in the training dataset and 71.43% in the validation dataset. All the three classifiers showed high F1 score for differentiation among the three subtypes. Conclusion: Our study proved the feasibility and translational value of CECT-based radiomics classifiers for differentiation among SCA, MCN, and IPMN.

Abstract Background: Colorectal cancer is harmful to the patient's life. The treatment of patients is determined by accurate preoperative staging. Magnetic resonance imaging (MRI) played an important role in the preoperative examination of patients with rectal cancer, and artificial intelligence (AI) in the learning of images made significant achievements in recent years. Introducing AI into MRI recognition, a stable platform for image recognition and judgment can be established in a short period. This study aimed to establish an automatic diagnostic platform for predicting preoperative T staging of rectal cancer through a deep neural network. Methods: A total of 183 rectal cancer patients’ data were collected retrospectively as research objects. Faster region-based convolutional neural networks (Faster R-CNN) were used to build the platform. And the platform was evaluated according to the receiver operating characteristic (ROC) curve. Results: An automatic diagnosis platform for T staging of rectal cancer was established through the study of MRI. The areas under the ROC curve (AUC) were 0.99 in the horizontal plane, 0.97 in the sagittal plane, and 0.98 in the coronal plane. In the horizontal plane, the AUC of T1 stage was 1, AUC of T2 stage was 1, AUC of T3 stage was 1, AUC of T4 stage was 1. In the coronal plane, AUC of T1 stage was 0.96, AUC of T2 stage was 0.97, AUC of T3 stage was 0.97, AUC of T4 stage was 0.97. In the sagittal plane, AUC of T1 stage was 0.95, AUC of T2 stage was 0.99, AUC of T3 stage was 0.96, and AUC of T4 stage was 1.00. Conclusion: Faster R-CNN AI might be an effective and objective method to build the platform for predicting rectal cancer T-staging. Trial registration: chictr.org.cn: ChiCTR1900023575; http://www.chictr.org.cn/showproj.aspx?proj=39665.

Hepatocellular carcinoma (HCC) is the most common type of primary liver cancer and has poor prognosis. Cytokeratin (CK)19-positive (CK19+) HCC is especially aggressive; early identification of this subtype and timely intervention can potentially improve clinical outcomes. In the present study, we developed a preoperative gadoxetic acid-enhanced magnetic resonance imaging (MRI)-based radiomics model for noninvasive and accurate classification of CK19+ HCC. A multicenter and time-independent cohort of 257 patients were retrospectively enrolled (training cohort, n = 143; validation cohort A, n = 75; validation cohort B, n = 39). A total of 968 radiomics features were extracted from preoperative multisequence MR images. The maximum relevance minimum redundancy algorithm was applied for feature selection. Multiple logistic regression, support vector machine, random forest, and artificial neural network (ANN) algorithms were used to construct the radiomics model, and the area under the receiver operating characteristic (AUROC) curve was used to evaluate the diagnostic performance of corresponding classifiers. The incidence of CK19+ HCC was significantly higher in male patients. The ANN-derived combined classifier comprising 12 optimal radiomics features showed the best diagnostic performance, with AUROCs of 0.857, 0.726, and 0.790 in the training cohort and validation cohorts A and B, respectively. The combined model based on multisequence MRI radiomics features can be used for preoperative noninvasive and accurate classification of CK19+ HCC, so that personalized management strategies can be developed.

BackgroundThe high recurrence rate after radical resection of pancreatic ductal adenocarcinoma (PDAC) leads to its poor prognosis. We aimed to develop a model to preoperatively predict the risk of recurrence based on computed tomography (CT) radiomics and multiple clinical parameters.MethodsDatasets were retrospectively collected and analysed of 220 PDAC patients who underwent contrast-enhanced computed tomography (CE-CT) and received radical resection at 3 institutions in China between 2013 and 2017, with 153 from one institution as a training set, the remaining 67 as a validation set. For each patient, CT radiomics features were extracted from intratumoral and peritumoral regions to establish intratumoral, peritumoral and combined radiomics models using artificial neural network (ANN) algorithm. By incorporating clinical factors, radiomics-clinical nomograms were finally built by multivariable logistic regression analysis to predict 1- and 2-year recurrence risk.FindingsThe developed radiomics model integrating intratumoral and peritumoral radiomics features was superior to the conventionally constructed model merely using intratumoral radiomics features. Further, radiomics-clinical nomograms outperformed other models in predicting 1-year recurrence with an area under the receiver operating characteristic curve (AUROC) of 0.916 (95%CI, 0.860-0.955) in the training set and 0.764 (95%CI, 0.644-0.859) in the validation set, and 2-year recurrence with an AUROC of 0.872 (95%CI: 0.809-0.921) in the training set and 0.773 (95%CI, 0.654-0.866) in the validation set.InterpretationThis study has developed and externally validated a radiomics-clinical nomogram integrating intra- and peritumoral CT radiomics signature as well as clinical factors to predict the recurrence risk of PDAC after radical resection, which will facilitate optimized and individualized treatment strategies.FundingThis work was supported by the National Key R&D Program of China [grant number: 2018YFE0114800], the General Program of National Natural Science Foundation of China [grant number: 81772562, 2017; 81871351, 2018], the Fundamental Research Funds for the Central Universities [grant number: 2021FZZX005-08], and Zhejiang Provincial Key Projects of Technology Research [grant number: WKJ-ZJ-2033].

Chemodynamic therapy (CDT)-activated apoptosis is a potential anticancer strategy. However, CDT encounters a bottleneck in clinical translation due to its serious side effects and low efficacy. Here, we first reveal that surface engineering of ginsenoside Rg3 dramatically alters the organ distribution and tumor enrichment of systematically administered nanocatalysts using the orthotopic pancreatic tumor model while avoiding toxicity and increasing efficacy in vivo to address the key and universal toxicity problems encountered in nanomedicine. Compared with nanocatalysts alone, Rg3-sheltered dynamic nanocatalysts form hydrophilic nanoclusters, prolonging their circulation lifespan in the blood, protecting the internal nanocatalysts from leakage while allowing their specific release at the tumor site. Moreover, the nanoclusters provide a drug-loading platform for Rg3 so that more Rg3 reaches the tumor site to achieve obvious synergistic effect with nanocatalysts. Rg3-sheltered dynamic nanocatalysts can simultaneously activate ferroptosis and apoptosis to significantly improve anticancer efficacy. Systematic administration of ginsenoside Rg3-sheltered nanocatalysts inhibited 86.6% of tumor growth without toxicity and prolonged the survival time of mice. This study provides a promising approach of nanomedicine with high biosafety and a new outlook for catalytic ferroptosis-apoptosis combined antitumor therapies. STATEMENT OF SIGNIFICANCE: Chemodynamic therapy (CDT) has limited clinical efficacy in cancer. In this study, we developed Rg3-sheltered dynamic nanocatalysts, which could simultaneously activate ferroptosis based on CDT-activated apoptosis, and ultimately form a combined therapy of ferroptosis-apoptosis to kill tumors. Studies have shown that the nanocatalysts after Rg3 surface engineering dramatically alters the pharmacokinetics and organ distribution of the nanocatalysts after being systematically administered, resulting in avoiding the toxicity of the nanocatalysts. Nanocatalysts also act as a drug-loading platform, guiding more Rg3 into the tumor site. This study emphasizes that nanocatalysts after Rg3 surface engineering improve the safety and effectiveness of ferroptosis-apoptosis combined therapy, providing an effective idea for clinical practices.

It is useful to predict planned dosimetry and determine the eligibility of a liver cancer patient for SBRT treatment using knowledge based planning (KBP). We compare the predictive accuracy using the overlap volume histogram (OVH) and statistical voxel dose learning (SVDL) KBP prediction models for coplanar VMAT to non-coplanar 4π radiotherapy plans.In this study, 21 liver SBRT cases were selected, which were initially treated using coplanar VMAT plans. They were then re-planned using 4π IMRT plans with 20 inversely optimized non-coplanar beams. OVH was calculated by expanding the planning target volume (PTV) and then plotting the percent overlap volume v with the liver vs. r v , the expansion distance. SVDL calculated the distance to the PTV for all liver voxels and bins the voxels of the same distance. Their dose information is approximated by either taking the median or using a skew-normal or non-parametric fit, which was then applied to voxels of unknown dose for each patient in a leave-one-out test. The liver volume receiving less than 15 Gy (V<15Gy), DVHs, and 3D dose distributions were predicted and compared between the prediction models and planning methods.On average, V<15Gy was predicted within 5%. SVDL was more accurate than OVH and able to predict DVH and 3D dose distributions. Median SVDL yielded predictive errors similar or lower than the fitting methods and is more computationally efficient. Prediction of the 4π dose was more accurate compared to VMAT for all prediction methods, with significant (p < 0.05) results except for OVH predicting liver V<15Gy (p = 0.063).In addition to evaluating plan quality, KBP is useful to automatically determine the patient eligibility for liver SBRT and quantify the dosimetric gains from non-coplanar 4π plans. The two here analyzed dose prediction methods performed more accurately for the 4π plans than VMAT.

Purpose.This study aims to develop and validate a multi-view learning method by the combination of primary tumor radiomics and lymph node (LN) radiomics for the preoperative prediction of LN status in gastric cancer (GC).Methods.A total of 170 contrast-enhanced abdominal CT images from GC patients were enrolled in this retrospective study. After data preprocessing, two-step feature selection approach including Pearson correlation analysis and supervised feature selection method based on test-time budget (FSBudget) was performed to remove redundance of tumor and LN radiomics features respectively. Two types of discriminative features were then learned by an unsupervised multi-view partial least squares (UMvPLS) for a latent common space on which a logistic regression classifier is trained. Five repeated random hold-out experiments were employed.Results.On 20-dimensional latent common space, area under receiver operating characteristic curve (AUC), precision, accuracy, recall and F1-score are 0.9531 ± 0.0183, 0.9260 ± 0.0184, 0.9136 ± 0.0174, 0.9468 ± 0.0106 and 0.9362 ± 0.0125 for the training cohort respectively, and 0.8984 ± 0.0536, 0.8671 ± 0.0489, 0.8500 ± 0.0599, 0.9118 ± 0.0550 and 0.8882 ± 0.0440 for the validation cohort respectively (reported as mean ± standard deviation). It shows a better discrimination capability than single-view methods, our previous method, and eight baseline methods. When the dimension was reduced to 2, the model not only has effective prediction performance, but also is convenient for data visualization.Conclusions.Our proposed method by integrating radiomics features of primary tumor and LN can be helpful in predicting lymph node metastasis in patients of GC. It shows multi-view learning has great potential for guiding the prognosis and treatment decision-making in GC.

Objective.Four-dimensional cone-beam computed tomography (4D CBCT) has unique advantages in moving target localization, tracking and therapeutic dose accumulation in adaptive radiotherapy. However, the severe fringe artifacts and noise degradation caused by 4D CBCT reconstruction restrict its clinical application. We propose a novel deep unsupervised learning model to generate the high-quality 4D CBCT from the poor-quality 4D CBCT.Approach.The proposed model uses a contrastive loss function to preserve the anatomical structure in the corrected image. To preserve the relationship between the input and output image, we use a multilayer, patch-based method rather than operate on entire images. Furthermore, we draw negatives from within the input 4D CBCT rather than from the rest of the dataset.Main results.The results showed that the streak and motion artifacts were significantly suppressed. The spatial resolution of the pulmonary vessels and microstructure were also improved. To demonstrate the results in the different directions, we make the animation to show the different views of the predicted correction image in the supplementary animation.Significance.The proposed method can be integrated into any 4D CBCT reconstruction method and maybe a practical way to enhance the image quality of the 4D CBCT.

X-ray cone-beam computed tomography (CBCT) is widely used nowadays, mainly for its large volume coverage and hardware compatibility with open-gantry x-ray imaging systems. As the size of x-ray illumination increases, an inevitable and adverse effect is the boost of scatter contamination on the x-ray images, which becomes one of the fundamental limitations of CBCT imaging. The large scatter signals in CBCT cause severe streaking and cupping artifacts in the CT images and greatly hamper the applications of CBCT due to its degraded image quality as compared to that of the conventional x-ray CT scanner. Research on scatter correction has gained heated attention in recent years. In this review, we first analyze the magnitudes of scatter in CBCT and its resultant errors in the reconstructed images. The existing CBCT scatter correction methods are then summarized in several categories: pre-processing methods, and post-processing methods including measurement-based, software-based, hardware-based decomposition and hybrid methods. An important issue related to the post-processing methods, the noise increase in the scatter corrected images, is also discussed. Although numerous scatter correction methods have been proposed in the literature, each approach has its own strengths and drawbacks and an optimal and standard method is still elusive. This review provides a comprehensive summary of the current research on scatter correction, and suggests future directions from the authors perspective. Keywords: Scatter correction, noise suppression, cone-beam computed tomography (CBCT)

This paper details an algorithm to simultaneously perform registration of computed tomography (CT) and cone-beam computed (CBCT) images, and image enhancement of CBCT. The algorithm employs a viscous fluid model which naturally incorporates two components: a similarity measure for registration and an intensity correction term for image enhancement. Incorporating an intensity correction term improves the registration results. Furthermore, applying the image enhancement term to CBCT imagery leads to an intensity corrected CBCT with better image quality. To achieve minimal processing time, the algorithm is implemented on a graphic processing unit (GPU) platform. The advantage of the simultaneous optimization strategy is quantitatively validated and discussed using a synthetic example. The effectiveness of the proposed algorithm is then illustrated using six patient datasets, three head-and-neck datasets and three prostate datasets.

Recently, we proposed a new algorithm of accelerated barrier optimization compressed sensing (ABOCS) for iterative CT reconstruction. The previous implementation of ABOCS uses gradient projection (GP) with a Barzilai-Borwein (BB) step-size selection scheme (GP-BB) to search for the optimal solution. The algorithm does not converge stably due to its non-monotonic behavior. In this paper, we further improve the convergence of ABOCS using the unknown-parameter Nesterov (UPN) method and investigate the ABOCS reconstruction performance on clinical patient data. Comparison studies are carried out on reconstructions of computer simulation, a physical phantom and a head-and-neck patient. In all of these studies, the ABOCS results using UPN show more stable and faster convergence than those of the GP-BB method and a state-of-the-art Bregman-type method. As shown in the simulation study of the Shepp-Logan phantom, UPN achieves the same image quality as those of GP-BB and the Bregman-type methods, but reduces the iteration numbers by up to 50% and 90%, respectively. In the Catphan©600 phantom study, a high-quality image with relative reconstruction error (RRE) less than 3% compared to the full-view result is obtained using UPN with 17% projections (60 views). In the conventional filtered-backprojection reconstruction, the corresponding RRE is more than 15% on the same projection data. The superior performance of ABOCS with the UPN implementation is further demonstrated on the head-and-neck patient. Using 25% projections (91 views), the proposed method reduces the RRE from 21% as in the filtered backprojection (FBP) results to 7.3%. In conclusion, we propose UPN for ABOCS implementation. As compared to GP-BB and the Bregman-type methods, the new method significantly improves the convergence with higher stability and fewer iterations.

Shading artifacts in CT images are caused by scatter contamination, beam-hardening effect and other non-ideal imaging conditions. The purpose of this study is to propose a novel and general correction framework to eliminate low-frequency shading artifacts in CT images (e.g. cone-beam CT, low-kVp CT) without relying on prior information. The method is based on the general knowledge of the relatively uniform CT number distribution in one tissue component. The CT image is first segmented to construct a template image where each structure is filled with the same CT number of a specific tissue type. Then, by subtracting the ideal template from the CT image, the residual image from various error sources are generated. Since forward projection is an integration process, non-continuous shading artifacts in the image become continuous signals in a line integral. Thus, the residual image is forward projected and its line integral is low-pass filtered in order to estimate the error that causes shading artifacts. A compensation map is reconstructed from the filtered line integral error using a standard FDK algorithm and added back to the original image for shading correction. As the segmented image does not accurately depict a shaded CT image, the proposed scheme is iterated until the variation of the residual image is minimized. The proposed method is evaluated using cone-beam CT images of a Catphan©600 phantom and a pelvis patient, and low-kVp CT angiography images for carotid artery assessment. Compared with the CT image without correction, the proposed method reduces the overall CT number error from over 200 HU to be less than 30 HU and increases the spatial uniformity by a factor of 1.5. Low-contrast object is faithfully retained after the proposed correction. An effective iterative algorithm for shading correction in CT imaging is proposed that is only assisted by general anatomical information without relying on prior knowledge. The proposed method is thus practical and attractive as a general solution to CT shading correction.

Dual-Energy Computed Tomography (DECT) is of great interest in medical imaging, security inspection, and nondestructive testing. Most DECT reconstruction methods focus on producing two material images with different linear attenuation coefficients. However, the ability to reconstruct three or more basis materials is clinically and industrially important. Under the assumption that there are at most three materials in each pixel, there are a few methods that estimate multiple material images from DECT measurements by enforcing sum-to-one and a box constraint ([0 1]) derived from both the volume and mass conservation assumption. The recently proposed image-domain multimaterial decomposition (MMD) method introduces edge-preserving regularization for each material image. It enforces the assumption that there are at most three materials in each pixel using a time-consuming loop over all possible material triplets. However, this method neglects relations among material images. We propose a new image-domain MMD model for DECT that considers the prior information that different material images have common or complementary edges and encourages sparsity of material composition in each pixel using regularization.The proposed PWLS-TNV-ℓ0 method uses penalized weighted least-square (PWLS) reconstruction with three regularization terms. The first term is total nuclear variation (TNV) that accounts for the image property that basis material images share common or complementary boundaries and each material image is piecewise constant. The second term is an ℓ0 norm that encourages each pixel containing a small subset of material types out of several possible materials. The third term is a characteristic function based on sum-to-one and a box constraint derived from the volume and mass conservation assumption. We apply the Alternating Direction Method of Multipliers (ADMM) to optimize the cost function of the PWLS-TNV-ℓ0 method.We evaluated the proposed method on a simulated digital phantom, Catphan©600 phantom and patient's pelvis data. We implemented two existing image-domain MMD methods for DECT, the Direct Inversion and the PWLS-EP-LOOP method. We initialized the PWLS-TNV-ℓ0 method and the PWLS-EP-LOOP method with the results of the Direct Inversion method and compared performance of the proposed method with that of the PWLS-EP-LOOP method. The proposed method lowers the bias of decomposed material fractions by 84.47% in the digital phantom study, by 99.50% in the Catphan©600 phantom study, and by 99.64% in the pelvis patient study, respectively, compared to the PWLS-EP-LOOP method. The proposed method reduces noise standard deviation (STD) by 52.21% in the Catphan©600 phantom study, and by 16.74% in the patient's pelvis study, compared to the PWLS-EP-LOOP method. The proposed method increases volume fraction accuracy by 6.04%,20.55%, and 13.46% for the digital phantom, the Catphan©600 phantom, and the patient's pelvis study, respectively, compared to the PWLS-EP-LOOP method. Compared with the PWLS-EP-LOOP method, the root mean square percentage error [RMSE(%)] of electron densities in the Catphan©600 phantom is decreased by about 7.39%.We proposed an image-domain MMD method, PWLS-TNV-ℓ0 , for DECT. The PWLS-TNV-ℓ0 method takes low rank property of material image gradients, sparsity of material composition and mass and volume conservation into consideration. The proposed method suppresses noise, reduces cross contamination, and improves accuracy in the decomposed material images, compared to the PWLS-EP-LOOP method.

Automated multi-organ segmentation on abdominal CT images may replace or complement manual segmentation for clinical applications including image-guided radiation therapy. However, the accuracy of auto-segmentation is challenged by low image contrast, large spatial and inter-patient anatomical variations. In this study, we propose an end-to-end segmentation network, termed self-paced DenseNet, for improved multi-organ segmentation performance, especially for the difficult-to-segment organs. Specifically, a learning-based attention mechanism and dense connection block are seamlessly integrated into the proposed self-paced DenseNet to improve the learning capability and efficiency of the backbone network. To heavily focus on the organs showing low soft-tissue contrast and motion artifacts, a boundary condition is utilized to constrain the network optimization. Additionally, to ease the large learning pace discrepancies of individual organs, a task-wise self-paced-learning strategy is employed to adaptively control the learning paces of individual organs. The proposed self-paced DenseNet was trained and evaluated on a public abdominal CT data set consisting of 90 subjects with manually labeled ground truths of eight organs (including spleen, left kidney, esophagus, gallbladder, stomach, liver, pancreas, and duodenum). For quantitative evaluation, the Dice similarity coefficient (DSC) and average surface distance (ASD) were calculated. An average DSC of 84.46% and ASD of 1.82 mm were achieved on the eight organs, which outperforms the state-of-the-art segmentation methods 2.96% on DSC under the same experimental configuration. Moreover, the proposed segmentation method shows notable improvements on the duodenum and gallbladder, obtaining an average DSC of 69.26% and 80.94% and ASD of 2.14 mm and 2.24 mm, respectively. The results are markedly superior to the average DSC of 63.12% and 76.35% and average ASD of 3.87 mm and 4.33 mm using the vanilla DenseNet, respectively, for the two organs. We demonstrated the effectiveness of the proposed self-paced DenseNet to automatically segment abdominal organs with low boundary conspicuity. The self-paced DenseNet achieved consistently superior segmentation performance on eight abdominal organs with varying segmentation difficulties. The demonstrated computational efficiency (<2 s/CT) makes it well-suited for online applications.

Abstract Previous studies have suggested that the intratumoral texture features may reflect the tumor recurrence risk in intrahepatic cholangiocarcinoma (ICC). The peritumoral features may be associated with the distribution of microsatellites. Therefore, integrating the imaging features based on intratumoral and peritumoral areas may provide more accurate predictions in tumor recurrence (both early and late recurrences) than the predictions conducted based on the intratumoral area only. This retrospective study included 209 ICC patients. We divided the patient population into two sub-groups according to the order of diagnosis time: a training cohort (159 patients) and an independent validation cohort (50 patients). The MR imaging features were quantified based on the intratumoral and peritumoral (3 and 5 mm) areas. The radiomics signatures, clinical factor-based models and combined radiomics-clinical models were developed to predict the tumor recurrence. The prediction performance was measured based on the validation cohort using the area under receiver operating characteristic curve (AUC) index. For the prediction of early recurrence, the combined radiomics-clinical model of intratumoral area with 5 mm peritumoral area showed the highest performance (0.852(95% confidence interval (CI), 0.724–0.937)). The AUC for the clinical factor-based model was 0.805(95%CI, 0.668–0.903). For the prediction of late recurrence, the radiomics signature of intratumoral area with 5 mm peritumoral area had the optimal performance with an AUC of 0.735(95%CI, 0.591–0.850). The clinical factor-based showed inferior performance (0.598(95%CI, 0.450–0.735)). For both early and late recurrences prediction, the optimal models were all constructed using imaging features extracted based on intratumoral and peritumoral areas together. These suggested the importance of involving the intratumoral and peritumoral areas in the radiomics studies.

Excessive imaging dose from repeated scans and poor image quality mainly due to scatter contamination are the two bottlenecks of cone-beam CT (CBCT) imaging. Compressed sensing (CS) reconstruction algorithms show promises in recovering faithful signals from low-dose projection data but do not serve well the needs of accurate CBCT imaging if effective scatter correction is not in place. Scatter can be accurately measured and removed using measurement-based methods. However, these approaches are considered unpractical in the conventional FDK reconstruction, due to the inevitable primary loss for scatter measurement. We combine measurement-based scatter correction and CS-based iterative reconstruction to generate scatter-free images from low-dose projections. We distribute blocked areas on the detector where primary signals are considered redundant in a full scan. Scatter distribution is estimated by interpolating/extrapolating measured scatter samples inside blocked areas. CS-based iterative reconstruction is finally carried out on the undersampled data to obtain scatter-free and low-dose CBCT images. With only 25% of conventional full-scan dose, our method reduces the average CT number error from 250 HU to 24 HU and increases the contrast by a factor of 2.1 on Catphan 600 phantom. On an anthropomorphic head phantom, the average CT number error is reduced from 224 HU to 10 HU in the central uniform area.

To evaluate the pharmacokinetic parameters of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) in diagnosing and staging liver fibrosis in rabbits.DCE-MRI with gadodiamide (Gd-DTPA-BMA) was performed on a 3.0 Tesla, 60 cm bore MR scanner for rabbits with CCl4 -induced liver fibrosis, and an untreated control group. Fibrosis was staged according to the METAVIR system: control (F0; n = 13), nonadvanced fibrosis (F1-2; n = 15), and advanced fibrosis (F3-4; n = 12). The DCE-MRI parameters K(trans) , kep , Ve , and vp were measured with a dual-input extended Tofts model. Receiver operating characteristic analyses were performed to assess the diagnostic performance of K(trans) , Ve , and vp in staging liver fibrosis.Both K(trans) and Ve decreased with increasing fibrosis stage. K(trans) of the control group was significantly different from that of the overall fibrosis group, nonadvanced group, and advanced group (P < 0.001 for all). Significant differences were found between Ve of the control group and that of the overall fibrosis and advanced groups (P = 0.019 and P = 0.009, respectively). For K(trans) , the areas under the receiver operating characteristic curve (AUROCs) for discriminating the control group from the overall fibrosis and advanced fibrosis groups were 0.909 (95% confidence interval [CI], 0.809-1.000), and 0.936 (95% CI,0.847-1.000), respectively. For discriminating between the control and nonadvanced fibrosis groups, the AUROC of K(trans) was 0.887 (95% CI, 0.762-1.000). The AUROCs of K(trans) were higher than those of Ve and vp for discriminating between the control and overall fibrosis groups, the control and nonadvanced fibrosis groups, and the control and advanced fibrosis groups. Pharmacokinetic parameters were negatively correlated with fibrosis stage (K(trans) , rho = -0.668, P < 0.001; Ve , rho = -0.438, P = 0.005; vp , rho = -0.360, P = 0.023).Among pharmacokinetic parameters of DCE-MRI in our study, K(trans) was an excellent predictor for differentiating fibrotic livers from normal livers, and differentiating normal livers from nonadvanced or advanced fibrosis livers. J. Magn. Reson. Imaging 2016;44:98-104.

An x-ray energy spectrum plays an essential role in computed tomography (CT) imaging and related tasks. Because of the high photon flux of clinical CT scanners, most of the spectrum estimation methods are indirect and usually suffer from various limitations. In this study, we aim to provide a segmentation-free, indirect transmission measurement–based energy spectrum estimation method using dual-energy material decomposition. The general principle of this method is to minimize the quadratic error between the polychromatic forward projection and the raw projection to calibrate a set of unknown weights, which are used to express the unknown spectrum together with a set of model spectra. The polychromatic forward projection is performed using material-specific images, which are obtained using dual-energy material decomposition. The algorithm was evaluated using numerical simulations, experimental phantom data, and realistic patient data. The results show that the estimated spectrum matches the reference spectrum quite well and the method is robust. Extensive studies suggest that the method provides an accurate estimate of the CT spectrum without dedicated physical phantom and prolonged workflow. This paper may be attractive for CT dose calculation, artifacts reduction, polychromatic image reconstruction, and other spectrum-involved CT applications.

Background: The accurate prediction of the tumor infiltration depth in the gastric wall based on enhanced CT images of gastric cancer is crucial for screening gastric cancer diseases and formulating treatment plans. Convolutional neural networks perform well in image segmentation. In this study, a convolutional neural network was used to construct a framework for automatic tumor recognition based on enhanced CT images of gastric cancer for the identification of lesion areas and the analysis and prediction of T staging of gastric cancer. Methods: Enhanced CT venous phase images of 225 patients with advanced gastric cancer from January 2017 to June 2018 were retrospectively collected. Ftable LabelImg software was used to identify the cancerous areas consistent with the postoperative pathological T stage. The training set images were enhanced to train the Faster RCNN detection model. Finally, the accuracy, specificity, recall rate, F1 index, ROC curve, and AUC were used to quantify the classification performance of T staging on this system. Results: The AUC of the Faster RCNN operating system was 0.93, and the recognition accuracies for T2, T3, and T4 were 90, 93, and 95%, respectively. The time required to automatically recognize a single image was 0.2 s, while the interpretation time of an imaging expert was ~10 s. Conclusion: In enhanced CT images of gastric cancer before treatment, the application of Faster RCNN to diagnosis the T stage of gastric cancer has high accuracy and feasibility.

Purpose: X‐ray cone‐beam CT (CBCT) is being increasingly used for various clinical applications, while its performance is still hindered by image artifacts. This work investigates a new source of reconstruction error, which is often overlooked in the current CBCT imaging. The authors find that the x‐ray flat field intensity ( I 0 ) varies significantly as the illumination volume size changes at different collimator settings. A wrong I 0 value leads to inaccurate CT numbers of reconstructed images as well as wrong scatter measurements in the CBCT research. Methods: The authors argue that the finite size of x‐ray focal spot together with the detector glare effect cause the I 0 variation at different illumination sizes. Although the focal spot of commercial x‐ray tubes typically has a nominal size of less than 1 mm, the off‐focal‐spot radiation covers an area of several millimeters on the tungsten target. Due to the large magnification factor from the field collimator to the detector, the penumbra effects of the collimator blades result in different I 0 values for different illumination field sizes. Detector glare further increases the variation, since one pencil beam of incident x‐ray is scattered into an area of several centimeters on the detector. In this paper, the authors study these two effects by measuring the focal spot distribution with a pinhole assembly and the detector point spread function (PSF) with an edge‐spread function method. The authors then derive a formula to estimate the I 0 value for different illumination field sizes, using the measured focal spot distribution and the detector PSF. Phantom studies are carried out to investigate the accuracy of scatter measurements and CT images with and without considering the I 0 variation effects. Results: On our tabletop system with a Varian Paxscan 4030CB flat‐panel detector and a Varian RAD‐94 x‐ray tube as used on a clinical CBCT system, the focal spot distribution has a measured full‐width‐at‐half‐maximum (FWHM) of around 0.4 mm, while non‐negligible off‐focal‐spot radiation is observed at a distance of over 2 mm from the center. The measured detector PSF has an FWHM of 0.510 mm, with a shape close to Gaussian. From these two distributions, the author calculate the estimated I 0 values at different collimator settings. The I 0 variation mainly comes from the focal spot effect. The estimation matches well with the measurements at different collimator widths in both horizontal and vertical directions, with an average error of less than 3%. Our method improves the accuracy of conventional scatter measurements, where the scatter is measured as the difference between fan‐beam and cone‐beam projections. On a uniform water cylinder phantom, more accurate I 0 suppresses the unfaithful high‐frequency signals at the object boundaries of the measured scatter, and the SPR estimation error is reduced from 0.158 to 0.014. The proposed I 0 estimation also reduces the reconstruction error from about 20 HU on the Catphan©600 phantom in the selected regions of interest to less than 4 HU. Conclusions: The I 0 variation is identified as one additional error source in x‐ray imaging. By measuring the focal‐spot distribution and detector PSF, the authors propose an accurate method of estimating the I 0 value for different illumination field sizes. The method obtains more accurate scatter measurements and therefore facilitates scatter correction algorithm designs. As correction methods for other CBCT artifacts become more successful, our research is significant in further improving the CBCT imaging accuracy.

DUAL-energy computed tomography (DECT) differentiates materials by exploiting the varying material linear attenuation coefficients (LACs) for different x-ray energy spectra. Multi-material decomposition (MMD) is a particularly attractive DECT clinical application to distinguish the complicated material components within the human body. One prior material assisted (PMA) image domain MMD method was implemented, but has suffered from inaccurate decomposition, magnified noise, and expensive computation. To suppress the noise, we implemented a statistical MMD (SMMD) algorithm, which applied the statistical weight to account for the noise variance in the DECT images. Its decomposition accuracy heavily relies on the initial value. In this paper, we propose a novel method to overcome these challenges. Based on the piecewise constant property of CT images with energy-dependent LAC, we assume that the pixels with high similarity have the same material composition. We cluster pixel patches into groups using the block-matching technique. The material composition in each group is preselected according to the shortest Euclidean distance in the energy map between the center of mass of the similar patch groups and the LAC of the object with known material composition pre-assigned by the clinician. MMD is performed on the central pixel of each patch using the preselected material composition. In a preliminary study, the proposed method is evaluated using the digital and water phantoms. The proposed method increases the volume fraction by 25.2% and decreases the standard deviation by 66.2% compared with the PMA method and increases the volume fraction by 19.6% compared with the SMMD method. The proposed method achieves an overall improvement of the normalized cross-correlation matrix diagonality by 34.8% and 69.4% compared with the PMA and SMMD methods. The phantom results indicate that the proposed method has the potential to be applied to clinical practice due to its increased decomposition accuracy, and suppressed noise and cross contamination.

Although rectal cancer comprises up to one-third of colorectal cancer cases and several prognosis nomograms have been established for colon cancer, statistical tools for predicting long-term survival in rectal cancer are lacking. In addition, previous prognostic studies did not include much imaging findings, qualitatively or quantitatively. Therefore, we include multiparametric MRI information from both radiologists' readings and quantitative radiomics signatures to construct a prognostic model that allows 5-year overall survival (OS) prediction for advance-staged rectal cancer patients. The result suggested that the model combined with quantitative imaging findings might outperform that of conventional TNM staging or other clinical prognostic factors. It was noteworthy that the identified radiomics signature consisted of three from dynamic contrast-enhanced (DCE)-MRI, four from anatomical MRI, and one from functional diffusion-weighted imaging (DWI). This highlighted the importance of multiparametric MRI to address the issue of long-term survival estimation in rectal cancer. Additionally, the constructed radiomics signature demonstrated value to the conventional prognostic factors in predicting 5-year OS for stage II-III rectal cancer. The presented nomogram also provides a practical example of individualized prognosis estimation and may potentially impact treatment strategies.

Achieving accurate and automated tumor segmentation plays an important role in both clinical practice and radiomics research. Segmentation in medicine is now often performed manually by experts, which is a laborious, expensive and error-prone task. Manual annotation relies heavily on the experience and knowledge of these experts. In addition, there is much intra- and interobserver variation. Therefore, it is of great significance to develop a method that can automatically segment tumor target regions.In this paper, we propose a deep learning segmentation method based on multimodal positron emission tomography-computed tomography (PET-CT), which combines the high sensitivity of PET and the precise anatomical information of CT. We design an improved spatial attention network(ISA-Net) to increase the accuracy of PET or CT in detecting tumors, which uses multi-scale convolution operation to extract feature information and can highlight the tumor region location information and suppress the non-tumor region location information. In addition, our network uses dual-channel inputs in the coding stage and fuses them in the decoding stage, which can take advantage of the differences and complementarities between PET and CT.We validated the proposed ISA-Net method on two clinical datasets, a soft tissue sarcoma(STS) and a head and neck tumor(HECKTOR) dataset, and compared with other attention methods for tumor segmentation. The DSC score of 0.8378 on STS dataset and 0.8076 on HECKTOR dataset show that ISA-Net method achieves better segmentation performance and has better generalization.The method proposed in this paper is based on multi-modal medical image tumor segmentation, which can effectively utilize the difference and complementarity of different modes. The method can also be applied to other multi-modal data or single-modal data by proper adjustment.

Chemosensitivity prediction in colorectal cancer patients with liver metastases has remained a research hotspot. Radiomics can extract features from patient imaging, and deep learning or machine learning can be used to build models to predict patient outcomes prior to chemotherapy.In this study, the radiomics features and clinical data of colorectal cancer patients with liver metastases were used to predict their sensitivity to irinotecan-based chemotherapy.A total of 116 patients with unresectable colorectal cancer liver metastases who received first-line irinotecan-based chemotherapy from January 2015 to January 2020 in our institution were retrospectively collected. Overall, 116 liver metastases were randomly divided into training (n = 81) and validation (n = 35) cohorts in a 7:3 ratio. The effect of chemotherapy was determined based on Response Evaluation Criteria in Solid Tumors. The lesions were divided into response and nonresponse groups. Regions of interest (ROIs) were manually segmented, and sample sizes of 1×1×1, 3×3×3, 5×5×5 mm3 were used to extract radiomics features. The relevant features were identified through Pearson correlation analysis and the MRMR algorithm, and the clinical data were merged into the artificial neural network. Finally, the p-model was obtained after repeated learning and testing.The p-model could distinguish responders in the training (area under the curve [AUC] 0.754, 95% CI 0.650-0.858) and validation cohorts (AUC 0.752 95% CI 0.581-0.904). AUC values of the pure image group model are 0.720 (95% CI 0.609-0.827) and 0.684 (95% CI 0.529-0.890) for the training and validation cohorts respectively. As for the clinical data model, AUC values of the training and validation cohorts are 0.638 (95% CI 0.500-0.757) and 0.545 (95% CI 0.360-0.785), respectively. The performances of the latter two are less than that of the former.The p-model has the potential to discriminate colorectal cancer patients sensitive to chemotherapy. This model holds promise as a noninvasive tool to predict the response of colorectal liver metastases to chemotherapy, allowing for personalized treatment planning.

In this study, we aim to develop and validate a radiomics model for pretreatment prediction of RPS6K expression in hepatocellular carcinoma (HCC) patients, thus helping clinical decision-making of mTOR-inhibitor (mTORi) therapy. We retrospectively enrolled 147 HCC patients, who underwent curative hepatic resection at First Affiliated Hospital Zhejiang University School of Medicine. RPS6K expression was determined with immunohistochemistry staining. Patients were randomly split into training or validation cohorts on a 7:3 ratio. Radiomics features were extracted from T2-weighted and diffusion-weighted images. Machine learning algorithms including multiple logistic regression (MLR), supporting vector machine (SVM), random forest (RF), and artificial neural network (ANN) were applied to construct the predictive model. A nomogram was further built to visualize the possibility of RPS6K expression. The area under the receiver operating characteristic (AUC) was used to evaluate the performance of diagnostic models. 174 radiomics features were confirmed correlated with RPS6K expression. Amongst all built models, the ANN-based hybrid model exhibited best predictive ability with AUC of 0.887 and 0.826 in training and validation cohorts. ALB was identified as the key clinical index, and the nomogram displayed further improved ability with AUC of 0.917 and 0.845. In this study, we proved MRI-based radiomics model and nomogram can accurately predict RPS6K expression non-invasively, thus providing help for clinical decision making for mTORi therapy.

Objective. This study proposes and evaluates a new figure of merit (FOMn) for dose optimization of Dual-energy cone-beam CT (DE-CBCT) scanning protocols based on size-dependent modeling of radiation dose and multi-scale image quality.Approach. FOMn was defined using Z-score normalization and was proportional to the dose efficiency providing better multi-scale image quality, including comprehensive contrast-to-noise ratio (CCNR) and electron density (CED) for CatPhan604 inserts of various materials. Acrylic annuluses were combined with CatPhan604 to create four phantom sizes (diameters of the long axis are 200 mm, 270 mm, 350 mm, and 380 mm, respectively). DE-CBCT was decomposed using image-domain iterative methods based on Varian kV-CBCT images acquired using 25 protocols (100 kVp and 140 kVp combined with 5 tube currents).Main results. The accuracy of CED was approximately 1% for all protocols, but degraded monotonically with the increased phantom sizes. Combinations of lower voltage + higher current and higher voltage + lower current were optimal protocols balancing CCNR and dose. The most dose-efficient protocols for CED and CCNR were inconsistent, underlining the necessity of including multi-scale image quality in the evaluation and optimization of DE-CBCT. Pediatric and adult anthropomorphic phantom tests confirmed dose-efficiency of FOMn-recommended protocols.Significance. FOMn is a comprehensive metric that collectively evaluates radiation dose and multi-scale image quality for DE-CBCT. The models and data can also serve as lookup tables, suggesting personalized dose-efficient protocols for specific clinical imaging purposes.

Dual-energy cone-beam computed tomography (DE-CBCT) integrates dual-energy imaging seamlessly into the CBCT system, offering a practical solution for real-time clinical applications in treatment rooms. Traditional DE-CBCT systems often rely on intricate hardware or dual scanning, imposing significant constraints on the broader application of dual-energy CT (DECT) in CBCT machines. In this study, we introduce an innovative GAN-based single-scan dual-energy CBCT reconstruction strategy designed for DE-CBCT systems, effectively reducing acquisition time compared to conventional two-scan DE-CBCT approaches. Our approach leverages a strip-type modulator positioned in front of the detector, enabling the acquisition of spectra-mixed dual-energy projections in a single scan by modulating specific areas on the detector. The obtained incomplete dual-energy projections undergo precise recovery through our designed dual-energy recovery GAN (DER-GAN). DER-GAN adeptly extracts complementary spectra and ensures consistency in anatomical information between high and low-energy projections. Through qualitative and quantitative analyses, DER-GAN demonstrates commendable performance in terms of CT number accuracy and preservation of anatomical details. Furthermore, in the realm of DECT applications, particularly in multi-material decomposition, DER-GAN's reconstructed images exhibit promising potential for clinical CBCT applications. This pioneering approach represents a significant stride toward efficient and practical integration of dual-energy imaging into the CBCT paradigm.

A semi-analytical solution to the unified Boltzmann equation is constructed to exactly describe the scatter distribution on a flat-panel detector for high-quality conebeam CT (CBCT) imaging. The solver consists of three parts, including the phase space distribution estimator, the effective source constructor and the detector signal extractor. Instead of the tedious Monte Carlo solution, the derived Boltzmann equation solver achieves ultrafast computational capability for scatter signal estimation by combining direct analytical derivation and time-efficient one-dimensional numerical integration over the trajectory along each momentum of the photon phase space distribution. The execution of scatter estimation using the proposed ultrafast Boltzmann equation solver (UBES) for a single projection is finalized in around 0.4 seconds. We compare the performance of the proposed method with the state-of-the-art schemes, including a time-expensive Monte Carlo (MC) method and a conventional kernel-based algorithm using the same dataset, which is acquired from the CBCT scans of a head phantom and an abdominal patient. The evaluation results demonstrate that the proposed UBES method achieves comparable correction accuracy compared with the MC method, while exhibits significant improvements in image quality over learning and kernel-based methods. With the advantages of MC equivalent quality and superfast computational efficiency, the UBES method has the potential to become a standard solution to scatter correction in high-quality CBCT reconstruction.

Four-dimensional conebeam computed tomography (4D CBCT) is an efficient technique to overcome motion artifacts caused by organ motion during breathing. 4D CBCT reconstruction in a single scan usually divides projections into different groups of sparsely sampled data based on the respiratory phases. The reconstructed images within each group present poor image quality due to the limited number of projections. To improve the image quality of 4D CBCT in a single scan, we propose a novel reconstruction scheme that combines prior knowledge with motion compensation. We apply the reconstructed images of the full projections within a single routine as prior knowledge, providing structural information for the network to enhance the restoration structure. The prior network (PN-Net) is proposed to extract features of prior knowledge and fuse them with the sparsely sampled data using an attention mechanism. The prior knowledge guides the reconstruction process to restore the approximate organ structure and alleviates severe streaking artifacts. The deformation vector field (DVF) extracted using deformable image registration among different phases is then applied in the motion-compensated ordered-subset simultaneous algebraic reconstruction algorithm to generate 4D CBCT images. Proposed method has been evaluated using simulated and clinical datasets and has shown promising results by comparative experiment. Compared with previous methods, our approach exhibits significant improvements across various evaluation metrics.

Download This Paper Open PDF in Browser Add Paper to My Library Share: Permalink Using these links will ensure access to this page indefinitely Copy URL Copy DOI

Abstract Purpose: To develop a novel method to simultaneously obtain the structural and functional characteristics of the brain extracellular space. Materials and Methods: Design and develop a magnetic tracing imaging analysis method compatible with impedance measurement using Michigan electrodes, synchronously obtaining brain extracellular space structural and electrical characteristic parameters. Twelve adult Sprague-Dawley rats were randomly divided into two groups: the first group was tested using traditional magnetic tracing techniques (n=6), while the second group was tested with a magnetic tracing detection system compatible with impedance measurement applied (n=6). Parameters such as diffusion coefficients, volume fraction and electrical characteristic parameters were calculated and compared. Visualisation of the tissue fluid drainage process was also conducted. Results: The system can synchronously obtain structural and impedance characteristic parameters of extracellular molecular diffusion in the mouse brain. The comparison results show a decrease in the molecular diffusion coefficient in the extracellular gaps (t=4.748, P＜0.01) and a reduction in the diffusion rate and volume fraction of extracellular gaps (t=7.77, P＜0.01). Additionally, electrical parameters of the extracellular gaps were measured, with a conductivity of 2.006 S/m, a dielectric constant of 84.77, a calculated diffusion rate of 3.54*10 -4 mm 2 /s, and a volume fraction of 17.43%, consistent with the data obtained from the magnetic tracing method. Conclusion: This system can simultaneously acquire the structural and functional characteristics of ECS, laying the foundation for a new method of neural regulation through the ECS pathway.

Appearance anxiety and depression have become common and global public health problems worldwide, especially among adolescents. However, few studies have revealed the mechanisms between them. This study aimed to explore the multiple mediating roles of interpersonal sensitivity and social support between appearance anxiety and depression among medical college students.With 13 invalid samples excluded, 724 college students participated in our survey and completed questionnaires. The average age of 724 samples was 19.8 ± 2.02 including freshman to senior year and graduate school and above; 31.9% of the participants were male and 68.1% were female. SPSS 25.0 and Hayes' PROCESS macro were used for statistical description, correlation analysis and built multiple mediation models.Appearance anxiety can not only directly affect depression, but also indirectly affect depression through three significant mediating pathways: (1) IS (B = 0.106, 95% CI [0.082-0.132]), which accounted for 49.77% of the total effect, (2) SS (B = 0.018, 95% CI [0.008-0.031]), which accounted for 8.45% of the total effect, and (3) IS and SS (B = 0.008, 95% CI [0.003-0.014]), which accounted for 3.76% of the total effect. And the total mediating effect was 61.97%.It is a cross-sectional research method and the causal relationship is unclear.This study found that lower interpersonal sensitivity and higher social support can effectively reduce depression caused by appearance anxiety among college students. The schools and relevant departments should take measures to reduce the interpersonal sensitivity of college students and establish reliable social support, so as to reduce the occurrence of depression.

Download This Paper Open PDF in Browser Add Paper to My Library Share: Permalink Using these links will ensure access to this page indefinitely Copy URL Copy DOI

The x-ray radiation dose in computed tomography (CT) examination has been a major concern for patients. Lowing the tube current and exposure time in data acquisition is a straightforward and cost-effective strategy to reduce the x-ray radiation dose. However, this will inevitably increase the noise fluctuations in measured projection data, and the corresponding CT image quality will be severely degraded if noise suppression is not performed during image reconstruction. To reconstruct high-quality low-dose CT image, we present a spatial-radon domain total generalized variation (SRDTGV) regularization for statistical iterative reconstruction (SIR) based on penalized weighted least-squares (PWLS) principle, which is called PWLS-SRDTGV for simplicity. The presented PWLS-SRDTGV model can simultaneously reconstruct high-quality CT image in space domain and its corresponding projection in radon domain. An efficient split Bregman algorithm was applied to minimize the cost function of the proposed reconstruction model. Qualitative and quantitative studies were performed to evaluate the effectiveness of the PWLS-SRDTGV image reconstruction algorithm using a digital 3D XCAT phantom and an anthropomorphic torso phantom. The experimental results demonstrate that PWLS-SRDTGV algorithm achieves notable gains in noise reduction, streak artifact suppression, and edge preservation compared with competing reconstruction approaches.

<title>Abstract</title> Purpose To establish prediction models to predict 2-year overall survival (OS) and stratify patients with different risks based on radiomics features extracted from magnetic resonance imaging (MRI) and computed tomography (CT) before definite chemoradiotherapy (dCRT) in locally advanced esophageal squamous cell carcinoma (ESCC). Methods Patients with locally advanced ESCC were recruited. We extracted 547 radiomics features from MRI and CT images. The least absolute shrinkage and selection operator (LASSO) for COX algorithm was used to obtain features highly correlated with survival outcomes in training cohort. Based on MRI, CT and the hybrid image data, three prediction models were built. The predictive performance of the radiomics models was evaluated in the training cohort and verified in the validation cohort using AUC values. Results A total of 192 patients were included and randomized into the training and validation cohorts. In predicting 2-year OS, the AUCs of the CT-based model were 0.733 and 0.654 for the training and validation sets. The MRI radiomics-based model was observed with similar AUCs of 0.750 and 0.686 in the training and validation sets. The AUC values of hybrid model combining MRI and CT radiomics features in predicting 2-year OS were 0.792 and 0.715 in the training and validation cohorts. It showed significant differences of 2-year OS in the high-risk and low-risk groups divided by the best cutoff value in the hybrid radiomics-based model. Conclusions The hybrid radiomics-based model has the best performance of predicting 2-year OS and can differentiate the high-risk and low-risk patients.

In this work, we aim to propose an accurate and robust spectrum estimation method by synergistically combining X-ray imaging physics with a convolutional neural network (CNN). &#xD;Approach: The approach relies on transmission measurements, and the estimated spectrum is formulated as a convolutional summation of a few model spectra generated using Monte Carlo simulation. The difference between the actual and estimated projections is utilized as the loss function to train the network. We contrasted this approach with the weighted sums of model spectra approach previously proposed. Comprehensive studies were performed to demonstrate the robustness and accuracy of the proposed approach in various scenarios. &#xD;Main results: The results show the desirable accuracy of the CNN-based method for spectrum estimation. The ME and NRMSE were -0.021 keV and 3.04% for 80kVp, and 0.006 keV and 4.44% for 100kVp, superior to the previous approach. The robustness test and experimental study also demonstrated superior performances. The CNN-based approach yielded remarkably consistent results in phantoms with various material combinations, and the CNN-based approach was robust concerning spectrum generators and calibration phantoms. &#xD;Significance: We proposed a method for estimating the real spectrum by integrating a deep learning model with real imaging physics. The results demonstrated that this method was accurate and robust in estimating the spectrum, and it is potentially helpful for broad X-ray imaging tasks.

In this article, four kinds of optical emission spectroscopic methods of determining electron temperature are used to investigate the relationship between electron temperature and pressure in the cylindrical plasmas of dc glow discharges at low pressures in laboratory by measuring the relative intensities of ArI lines at various pressures. These methods are developed respectively on the basis of the Fermi–Dirac model, corona model, and two kinds of electron collision cross section models according to the kinetic analysis. Their theoretical bases and the conditions to which they are applicable are reviewed, and their calculation results and fitting errors are compared with each other. The investigation has indicated that the electron temperatures obtained by the four methods become consistent with each other when the pressure increases in the low pressure argon plasmas.

Recent advances in total variation (TV) technology enable accurate CT image reconstruction from highly under-sampled and noisy projection data. The standard iterative reconstruction algorithms, which work well in conventional CT imaging, fail to perform as expected in cone beam CT (CBCT) applications, wherein the non-ideal physics issues, including scatter and beam hardening, are more severe. These physics issues result in large areas of shading artifacts and cause deterioration to the piecewise constant property assumed in reconstructed images. To overcome this obstacle, we incorporate a shading correction scheme into low-dose CBCT reconstruction and propose a clinically acceptable and stable three-dimensional iterative reconstruction method that is referred to as the shading correction assisted iterative reconstruction. In the proposed method, we modify the TV regularization term by adding a shading compensation image to the reconstructed image to compensate for the shading artifacts while leaving the data fidelity term intact. This compensation image is generated empirically, using image segmentation and low-pass filtering, and updated in the iterative process whenever necessary. When the compensation image is determined, the objective function is minimized using the fast iterative shrinkage-thresholding algorithm accelerated on a graphic processing unit. The proposed method is evaluated using CBCT projection data of the Catphan© 600 phantom and two pelvis patients. Compared with the iterative reconstruction without shading correction, the proposed method reduces the overall CT number error from around 200 HU to be around 25 HU and increases the spatial uniformity by a factor of 20 percent, given the same number of sparsely sampled projections. A clinically acceptable and stable iterative reconstruction algorithm for CBCT is proposed in this paper. Differing from the existing algorithms, this algorithm incorporates a shading correction scheme into the low-dose CBCT reconstruction and achieves more stable optimization path and more clinically acceptable reconstructed image. The method proposed by us does not rely on prior information and thus is practically attractive to the applications of low-dose CBCT imaging in the clinic.

In the era of high‐precision radiotherapy, cone‐beam CT (CBCT) is frequently utilized for on‐board treatment guidance. However, CBCT images usually contain severe shading artifacts due to strong photon scatter from illumination of a large volume and non‐optimized patient‐specific data measurements, limiting the full clinical applications of CBCT. Many algorithms have been proposed to alleviate this problem by data correction on projections. Sophisticated methods have also been designed when prior patient information is available. Nevertheless, a standard, efficient, and effective approach with large applicability remains elusive for current clinical practice. In this work, we develop a novel algorithm for shading correction directly on CBCT images. Distinct from other image‐domain correction methods, our approach does not rely on prior patient information or prior assumption of patient data. In CBCT, projection errors (mostly from scatter and non‐ideal usage of bowtie filter) result in dominant low‐frequency shading artifacts in image domain. In circular scan geometry, these artifacts often show global or local radial patterns. Hence, the raw CBCT images are first preprocessed into the polar coordinate system. Median filtering and polynomial fitting are applied on the transformed image to estimate the low‐frequency shading artifacts (referred to as the bias field) angle‐by‐angle and slice‐by‐slice. The low‐pass filtering process is done firstly along the angular direction and then the radial direction to preserve image contrast. The estimated bias field is then converted back to the Cartesian coordinate system, followed by 3D low‐pass filtering to eliminate possible high‐frequency components. The shading‐corrected image is finally obtained as the uncorrected volume divided by the bias field. The proposed algorithm was evaluated on CBCT images of a pelvis patient and a head patient. Mean CT number values and spatial non‐uniformity on the reconstructed images were used as image quality metrics. Within selected regions of interest, the average CT number error was reduced from around 300 HU to 42 and 38 HU, and the spatial nonuniformity error was reduced from above 17.5% to 2.1% and 1.7% for the pelvis and the head patients, respectively. As our method suppresses only low‐frequency shading artifacts, patient anatomy and contrast were retained in the corrected images for both cases. Our shading correction algorithm on CBCT images offers several advantages. It has a high efficiency, since it is deterministic and directly operates on the reconstructed images. It requires no prior information or assumptions, which not only achieves the merits of CBCT‐based treatment monitoring by retaining the patient anatomy, but also facilitates its clinical use as an efficient image‐correction solution. PACS number(s): 87.57.C‐, 87.57.cp, 87.57.Q‐

Purpose Scatter contamination in the cone‐beam CT (CBCT) leads to CT number inaccuracy, spatial nonuniformity, and loss of image contrast. In our previous work, we proposed a single scan scatter correction approach using a stationary partial beam blocker. Although the previous method works effectively on a tabletop CBCT system, it fails to achieve high image quality on a clinical CBCT system mainly due to the wobble of the LINAC gantry during scan acquisition. Due to the mechanical deformation of CBCT gantry, the wobbling effect is observed in the clinical CBCT scan, and more missing data present using the previous blocker with the uniformly distributed lead strips. Methods An optimal blocker distribution is proposed to minimize the missing data. In the objective function of the missing data, the motion of the beam blocker in each projection is estimated using the segmentation due to its high contrast in the blocked area. The scatter signals from the blocker are also estimated using an air scan with the inserted blocker. The final image is generated using the forward projection to compensate for the missing data. Results On the Catphan©504 phantom, our approach reduces the average CT number error from 86 Hounsfield unit (HU) to 9 HU and improves the image contrast by a factor of 1.45 in the high‐contrast rods. On a head patient, the CT number error is reduced from 97 HU to 6 HU in the soft‐tissue region and the image spatial nonuniformity is decreased from 27% to 5%. Conclusions The results suggest that the proposed method is promising for clinical applications.

Abstract Background Stereotactic body radiotherapy (SBRT) is the standard care for inoperable early stage non‐small cell lung cancer (NSCLC). The purpose of our study was to investigate whether a prediction model based on cone‐beam CT (CBCT) plus pretreatment CT radiomics features could improve the prediction of tumor control and lung toxicity after SBRT in comparison to a model based on pretreatment CT radiomics features alone. Methods A total of 34 cases of stage I NSCLC patients who received SBRT were included in the study. The pretreatment planning CT and serial CBCT radiomics features were analyzed using the imaging biomarker explorer (IBEX) software platform. Multivariate logistic regression was conducted for the association between progression‐free survival (PFS), lung toxicity and features. The predictive capabilities of the models based on CBCT and CT features were compared using receiver operating characteristic (ROC) curves. Results Five CBCT features and two planning CT features were correlated with disease progression. Six CBCT features and two planning CT features were related to lung injury. The ROC curves indicated that the model based on the CBCT plus planning CT features might be better than the model based on the planning CT features in predicting lung injury. The other ROC curves indicated that the model based on the planning CT features was similar to the model based on the CBCT plus planning CT features in predicting disease progression. Conclusions Both pretreatment CT and CBCT radiomics features could predict disease progression and lung injury. A model with CBCT plus pretreatment CT radiomics features might improve the prediction of lung toxicity in comparison with a model with pretreatment CT features alone. Key points Significant findings of the study : A model with cone‐beam CT radiomics features plus pre‐treatment CT radiomics features might improve the prediction of lung toxicity after SBRT in stage I NSCLC patients. What this study adds : In the prediction of PFS and lung toxicity in early‐stage NSCLC patients treated with SBRT, CBCT radiomics could be another effective method.

Objective: Dual-energy CT (DECT) strengthens the material characterization and quantification due to its capability of material discrimination. The image-domain multi-material decomposition (MMD) via matrix inversion suffers from serious degradation of the signal-to-noise ratios (SNRs) of the decomposed images, and thus the clinical application of DECT is limited. In this paper, we propose a noise suppression algorithm based on the noise propagation for image-domain MMD. Methods: The noise in the decomposed images only distributes in two perpendicular directions and is suppressed by estimating the center of mass of the same-material pixel group vertically along the principal axis where the noise disturbance is minimal. The proposed method is evaluated using the line-pair and contrast-rod slices of the Catphan©600 phantom and one patient data set. We compared the proposed method with the direct inversion and the block-matching and three-dimensional (BM3D) filtration methods. Results: The results of Catphan©600 phantom and the patient show that the proposed method successfully suppresses the noise of the basis material images by one order of magnitude and preserves the spatial resolution of the decomposed images. Compared with the BM3D filtration method, the proposed method maintains the texture distribution of the decomposed images at the same SNR and the accuracy of the electron density measurement. Conclusion: The algorithm achieves effective noise suppression compared with the BM3D filtration while maintaining the spatial distribution of the decomposed material images. It is, thus, attractive for advanced clinical applications using DECT.

Dual-energy computed tomography (DECT) has capability to improve material differentiation, but most scanning schemes require two sets of full-scan measurements at different x-ray spectra, limiting its application to imaging system with incomplete scan. In this study, using one half-scan and a second limited-angle scan, we propose a DECT reconstruction method by exploiting the consistent information of gradient images at high- and low-energy spectra, which relaxes the requirement of data acquisition of DECT. Based on the theory of sampling condition analysis, the complementary support set of gradient images plays an important role in image reconstruction because it constitutes the sufficient and necessary condition for accurate CT reconstruction. For DECT, the gradient images of high- and low-energy CT images ideally share the same complementary support set for the same object. Inspired by this idea, we extract the prior knowledge of complementary support set (Pri-CSS) from the gradient image of the first half-scan CT image to promote the second limited-angle CT reconstruction. Pri-CSS will be incorporated into total variation regularization model in the form of constrains. Alternative direction method is applied to iteratively solve the modified optimization model, thereby deriving the proposed algorithm to recover low-energy CT image from limited-angle measurements. The qualitative and quantitative experiments on digital and real data are performed to validate the proposed method. The results show that the proposed method outperforms its counterparts and achieve high reconstruction quality for the designed scanning configuration.

Diabetes mellitus is a serious metabolic condition associated with a multitude of cardiovascular complications. Moreover, the prevalence of diabetes in heart failure populations is higher than that in control populations. However, the role of cardiomyocyte alterations in type 2 diabetes mellitus (T2DM) has not been well characterized and the underlying mechanisms remain elusive. In this study, two patients who were diagnosed as T2DM were recruited and patient-specific induced pluripotent stem cells (iPSCs) were generated from urine epithelial cells using nonintegrated Sendai virus. The iPSC lines derived from five healthy subjects were used as controls. All iPSCs were differentiated into cardiomyocytes (iPSC-CMs) using the monolayer-based differentiation protocol. T2DM iPSC-CMs exhibited various disease phenotypes, including cellular hypertrophy and lipid accumulation. Moreover, T2DM iPSC-CMs exhibited higher susceptibility to high-glucose/high-lipid challenge than control iPSC-CMs, manifesting an increase in apoptosis. RNA-Sequencing analysis revealed a differential transcriptome profile and abnormal activation of TGFβ signaling pathway in T2DM iPSC-CMs. We went on to show that inhibition of TGFβ significantly rescued the hypertrophic phenotype in T2DM iPSC-CMs. In conclusion, we demonstrate that the iPSC-CM model is able to recapitulate cellular phenotype of T2DM. Our results indicate that iPSC-CMs can therefore serve as a suitable model for investigating molecular mechanisms underlying diabetic cardiomyopathies and for screening therapeutic drugs.

Tumor budding is considered a sign of cancer cell activity and the first step of tumor metastasis. This study aimed to establish an automatic diagnostic platform for rectal cancer budding pathology by training a Faster region-based convolutional neural network (F-R-CNN) on the pathological images of rectal cancer budding. Postoperative pathological section images of 236 patients with rectal cancer from the Affiliated Hospital of Qingdao University, China, taken from January 2015 to January 2017 were used in the analysis. The tumor site was labeled in Label image software. The images of the learning set were trained using Faster R-CNN to establish an automatic diagnostic platform for tumor budding pathology analysis. The images of the test set were used to verify the learning outcome. The diagnostic platform was evaluated through the receiver operating characteristic (ROC) curve. Through training on pathological images of tumor budding, an automatic diagnostic platform for rectal cancer budding pathology was preliminarily established. The precision–recall curves were generated for the precision and recall of the nodule category in the training set. The area under the curve = 0.7414, which indicated that the training of Faster R-CNN was effective. The validation in the validation set yielded an area under the ROC curve of 0.88, indicating that the established artificial intelligence platform performed well at the pathological diagnosis of tumor budding. The established Faster R-CNN deep neural network platform for the pathological diagnosis of rectal cancer tumor budding can help pathologists make more efficient and accurate pathological diagnoses.

We have fabricated GaAs-based microelectromechanical systems' (MEMSs) terahertz bolometers on high-resistivity Si substrates by using a wafer-bonding technique. In contrast to polar GaAs, nonpolar Si has very small absorption in the terahertz (THz) frequency range. The wafer-bonded MEMS bolometers show a large responsivity even in the Reststrahlen band of GaAs, where the responsivity vanishes in the conventional MEMS bolometers fabricated on GaAs substrates. Furthermore, we have observed two peaks in the responsivity spectrum near the TO and LO phonon frequencies of GaAs, which originate from an interplay between strong reflection in the Reststrahlen band and strong absorption at the TO phonon frequency in the GaAs MEMS beam. The present result demonstrates that the wafer-bonded MEMS bolometers are a very good candidate for the room-temperature, fast, and sensitive broadband THz detection.

Abstract Purpose To study and investigate the synergistic benefit of incorporating both conventional handcrafted and learning‐based features in disease identification across a wide range of clinical setups. Methods and materials In this retrospective study, we collected 170, 150, 209, and 137 patients with four different disease types associated with identification objectives : Lymph node metastasis status of gastric cancer (GC), 5‐year survival status of patients with high‐grade osteosarcoma (HOS), early recurrence status of intrahepatic cholangiocarcinoma (ICC), and pathological grades of pancreatic neuroendocrine tumors (pNETs). Computed tomography (CT) and magnetic resonance imaging (MRI) were used to derive image features for GC/HOS/pNETs and ICC, respectively. In each study, 67 universal handcrafted features and study‐specific features based on the sparse autoencoder (SAE) method were extracted and fed into the subsequent feature selection and learning model to predict the corresponding disease identification. Models using handcrafted alone, SAE alone, and hybrid features were optimized and their performance was compared. Prominent features were analyzed both qualitatively and quantitatively to generate study‐specific and cross‐study insight. In addition to direct performance gain assessment, correlation analysis was performed to assess the complementarity between handcrafted features and SAE features. Results On the independent hold‐off test, the handcrafted, SAE, and hybrid features based prediction yielded area under the curve of 0.761 versus 0.769 versus 0.829 for GC, 0.629 versus 0.740 versus 0.709 for HOS, 0.717 versus 0.718 versus 0.758 for ICC, and 0.739 versus 0.715 versus 0.771 for pNETs studies, respectively. In three out of the four studies, prediction using the hybrid features yields the best performance, demonstrating the general benefit in using hybrid features. Prediction with SAE features alone had the best performance in the HOS study, which may be explained by the complexity of HOS prognosis and the possibility of a slight overfit due to higher correlation between handcrafted and SAE features. Conclusion This study demonstrated the general benefit of combing handcrafted and learning‐based features in radiomics modeling. It also clearly illustrates the task‐specific and data‐specific dependency on the performance gain and suggests that while the common methodology of feature combination may be applied across various studies and tasks, study‐specific feature selection and model optimization are still necessary to achieve high accuracy and robustness.

Dual-energy computed tomography (CT) can be used for material decomposition, allowing for the precise quantitative mapping of body substances; this has a wide range of clinical applications, including disease diagnosis, treatment response evaluation and prognosis prediction. However, dual-energy CT has not yet become the mainstream technique in most clinical settings due to its limited accessibility. To fully take advantage of material quantification, researchers have attempted to use deep learning to generate material decomposition maps from conventional single-energy CT images, mainly by synthesizing another single-energy CT image from a conventional single-energy CT image to form a dual-energy CT image first and then generate material decomposition maps. This is not a straightforward process, and it potentially introduces many inaccuracies after multiple steps. In this work, we proposed a generative adversarial network (GAN) framework as the base and improved its generator; this approach combines convolutional neural networks (CNNs) and a transformer module to directly generate material decomposition maps from conventional single-energy CT images. Our model pays attention to both local and global information. Then, we compared our method with 6 competitive deep learning methods on water (calcium) and calcium (water) substrate density image datasets. The average PSNR, SSIM, MAE, and RMSE of the generated and ground truth of the water (calcium) substrate density images were 32.7207, 0.9685, 0.0323, and 0.0555, respectively. Furthermore, the average PSNR, SSIM, MAE, and RMSE of the generated and ground truth of the calcium (water) substrate density images were 30.2823, 0.9449, 0.0652, and 0.0715, respectively. Our model achieved better performance and stronger stability than competing approaches.

The aim of this paper is to develop a fast and accurate beam hardening correction method by modeling physical interactions between X-ray photons and materials for computed tomography (CT) imaging. The nonlinear attenuation process of the X-ray projection is modeled by reprojecting a template image with the estimated polychromatic spectrum. By adding the scaled difference of the monochromatic reprojection data and the polychromatic reprojection to the raw projection data, the raw projection data is mapped into the corresponding monochromatic projection data, which is to reconstruct the beam hardening artifacts corrected images. The algorithm can also be implemented in image-domain which takes the uncorrected image volume as input when there is an adequate model of the spectrum. In this case, the scaled difference is reconstructed to yield a set of artifacts images that can be added directly to the uncorrected images. Numerical simulations, experimental phantom data, and animal data which are acquired on a modern diagnostic CT scanner (Discovery CT750 HD, GE Healthcare, WI, USA), and a modern C-Arm CT scanner (Artis Zee, Siemens Healthcare, Forchheim, Germany), respectively, are used to evaluate the proposed method. The results show the proposed method significantly reduced both cupping and streak artifacts, and successfully recovered the Housfield units accuracy. Extensive studies suggest the proposed model-based method successfully corrects the beam hardening artifacts. This paper is practically useful and is promising to be applied to commercial products.

The aim of this pilot study was to explore the integrated positron emission tomography and magnetic resonance imaging scanner (PET/MR) for biological characterization of nasopharyngeal carcinoma (NPC) and potential therapeutic applications of dose painting (DP). Twenty-one NPC patients with PET/MR were included in this study. Overlap of tumor volumes was analyzed on T2-weighted images (volume of interest, VOIT2), diffusion-weighted magnetic resonance imaging (VOIDWI) and 18F-fluorodeoxyglucose positron emission tomography (VOIPET). The overlap percentages of low-metabolic sub-region (cluster 1) and high-metabolic sub-region (cluster 2) in VOIPET and VOIDWI were analyzed by cluster analysis. Both the VOIDWI and VOIPET were encompassed in the VOIT2, respectively 99.6% and 97.5%. The median tumor overlap was 94.4% (VOIDWI within VOIPET). The median overlap of cluster 2 in VOIPET and VOIDWI was 43.61% (27.67–52.66%) and 21.86%(10.47–40.89%), respectively. The median overlap of cluster 1 in VOIPET and VOIDWI was 48.03% (23.91–63.15%) and 24.40% (7.44–51.44%), respectively. Separation between clusters appeared to be defined by a SUV value. For NPC, the VOIs of DWI and FDG PET were not overlapped completely and the volume defined by cluster-analysis might be meaningful for DP.

Background: This study aimed to determine the impact of including radiomics analysis of non-tumorous bone region of interest in improving the performance of pathological response prediction to chemotherapy in high-grade osteosarcomas (HOS), compared to radiomics analysis of tumor region alone. Methods: This retrospective study included 157 patients diagnosed with HOS between November 2013 and November 2017 (age range, 5–44 years; mean age, 16.99 ±7.42 years), in which 69 and 88 patients were diagnosed as pathological good response (pGR) and non-pGR, respectively. Radiomics features were extracted from tumor and non-tumorous bone regions based on diagnostic CT images. Pathological response classifiers were developed and validated via leave-one-out cross validation (LOOCV) and independent validation methods by using the area under the receiver operating characteristic curve (AUC) value as the figure of merit. Results: Using the LOOCV, the classifiers combining features from tumor and non-tumorous regions showed better prediction performance than those from tumor region alone (AUC, 0.8207±0.0043 vs. 0.7799±0.0044). The combined classifier also showed better performance than the tumor feature-based classifier in both training and validation datasets [training dataset: 0.791, 95% confidence interval (CI), 0.706–0.860 vs. 0.766, 95% CI, 0.679–0.840; validation dataset: 0.816, 95% CI, 0.662–0.920 vs. 0.766, 95% CI, 0.606–0.885]. Conclusions: Radiomics analysis of combined tumor and non-tumorous bone features showed improved performance of pathological response prediction to chemotherapy in HOS compared to that of tumor features alone. Moreover, the proposed classifier had the potential to predict pathological response to chemotherapy for HOS patients.

In this paper, we study the reliability of a novel deep learning framework for internal gross target volume (IGTV) delineation from 4-D computed tomography (4DCT), which is applied to patients with lung cancer treated by stereotactic body radiation therapy (SBRT). Seventy seven patients who underwent SBRT followed by 4DCT scans were incorporated in this retrospective study. The IGTV_DL was delineated using a novel deep machine learning algorithm with a linear exhaustive optimal combination framework. For the purpose of comparison, three other IGTVs based on common methods was also delineated. We compared the relative volume difference (RVI), matching index (MI), and encompassment index (EI) for the above IGTVs. Then, multiple parameter regression analysis was performed to assess the tumor volume and motion range as clinical influencing factors in the MI variation. The results demonstrated that the deep learning algorithm with linear exhaustive optimal combination framework has a higher probability of achieving optimal MI compared with other currently widely used methods. For patients after simple breathing training by keeping the respiratory frequency in 10 breath per minute (BPM), the four phase combinations of 0%, 30%, 50% and 90% can be considered as a potential solution for an optimal combination to synthesize IGTV in all respiration amplitudes.

Multi-material decomposition (MMD) decomposes CT images into basis material images, and is a promising technique in clinical diagnostic CT to identify material compositions within the human body. MMD could be implemented on measurements obtained from spectral CT protocol, although spectral CT data acquisition is not readily available in most clinical environments. MMD methods using single energy CT (SECT), broadly applied in radiological departments of most hospitals, have been proposed in the literature while challenged by the inferior decomposition accuracy and the limited number of material bases due to the constrained material information in the SECT measurement. In this paper, we propose an image-domain SECT MMD method using material sparsity as an assistance under the condition that each voxel of the CT image contains at most two different elemental materials. L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">0</sub> norm represents the material sparsity constraint (MSC) and is integrated into the decomposition objective function with a least-square data fidelity term, total variation term, and a sum-to-one constraint of material volume fractions. An accelerated primal-dual (APD) algorithm with line-search scheme is applied to solve the problem. The pixelwise direct inversion method with the two-material assumption (TMA) is applied to estimate the initials. We validate the proposed method on phantom and patient data. Compared with the TMA method, the proposed MSC method increases the volume fraction accuracy (VFA) from 92.0% to 98.5% in the phantom study. In the patient study, the calcification area can be clearly visualized in the virtual non-contrast image generated by the proposed method, and has a similar shape to that in the ground-truth contrast-free CT image. The high decomposition image quality from the proposed method substantially facilitates the SECT-based MMD clinical applications.

The energy transformation from electromagnetic wave to plasmas polaritons in overdense plasma is investigated by using the theory of hydrodynamics in the thin cylinder limit and surface wave resonator. The grating experiment certifies the excitation of the surface wave. Through studying the role of the magnetic field in excitation of the surface wave and analyzing the frequency domain spectrum of the reflected wave, the time series of reflection, transmission and plasma density are diagnosed when the electromagnetic wave transforms into the surface wave. The experimental scheme of Bliokh [Phys. Rev. Lett. 95, 165003 (2005)] is improved. A steady overdense plasma in a cylindrical cavity is obtained by dc high voltage discharging and measurement is taken in series. The diffraction grating is fixed in optimum position after the distance from it to the chamber is adjusted. The reflection ratios of plasma and a piece of tinfoil are compared to avoid the effect of the standing wave. The effect of incident polarization is discussed and a measurement result is obtained with a 70Gauss magnetic field. Further research on scanning measurement reveals that the collision rate is the only determinant element of the half absorption width. Numerical simulation is given, based on the theory of surface plasmons (SPs). The experimental data agree with the numerical simulation well near the resonance frequency f=5GHz, while on the trailing edge, the curve is obviously expanded. The mechanism of these phenomena is very complex and other conceivable factors must exist during the excitation of SPs, which should be studied in the further research.

Megavoltage CT (MVCT) images are noisier than kilovoltage CT (KVCT) due to low detector efficiency to high-energy x rays. Conventional denoising methods compromise edge resolution and low-contrast object visibility. In this work, we incorporated block-matching 3D-transform shrinkage (BM3D) transformation into MVCT iterative reconstruction as nonlocal patch-wise regularization.The iterative reconstruction was achieved by adding to the existing least square data fidelity objective a regularization term, formulated as the L1 norm of the BM3D transformed image. A Fast Iterative Shrinkage-Thresholding Algorithm (FISTA) was adopted to accelerate CT reconstruction. The proposed method was compared against total variation (TV) regularization, BM3D postprocess method, and filtered back projection (FBP).In the Catphan phantom study, BM3D regularization better enhances low-contrast objects compared with TV regularization and BM3D postprocess method at the same noise level. The spatial resolution using BM3D regularization is 2.79 and 2.55 times higher than that using the TV regularization at 50% of the modulation transfer function (MTF) magnitude, for the fully sampled reconstruction and down-sampled reconstruction, respectively. The BM3D regularization images show better bony details and low-contrast soft tissues, on the head and neck (H&N) and prostate patient images.The proposed iterative BM3D regularization CT reconstruction method takes advantage of both the BM3D denoising capability and iterative reconstruction data fidelity consistency. This novel approach is superior to TV regularized iterative reconstruction or BM3D postprocess for improving noisy MVCT image quality.

Iterative reconstruction via total variation (TV) minimization has demonstrated great successes in accurate CT imaging from under-sampled projections. When projections are further reduced, over-smoothing artifacts appear in the current reconstruction especially around the structure boundaries.We propose a practical algorithm to improve TV-minimization based CT reconstruction on very few projection data.Based on the theory of compressed sensing, the L-0 norm approach is more desirable to further reduce the projection views. To overcome the computational difficulty of the non-convex optimization of the L-0 norm, we implement an adaptive weighting scheme to approximate the solution via a series of TV minimizations for practical use in CT reconstruction. The weight on TV is initialized as uniform ones, and is automatically changed based on the gradient of the reconstructed image from the previous iteration. The iteration stops when a small difference between the weighted TV values is observed on two consecutive reconstructed images.We evaluate the proposed algorithm on both a digital phantom and a physical phantom. Using 20 equiangular projections, our method reduces reconstruction errors in the conventional TV minimization by a factor of more than 5, with improved spatial resolution.By adaptively reweighting TV in iterative CT reconstruction, we successfully further reduce the projection number for the same or better image quality.

Objective.The quantitative and routine imaging capabilities of cone-beam CT (CBCT) are hindered from clinical applications due to the severe shading artifacts of scatter contamination. The scatter correction methods proposed in the literature only consider the anatomy of the scanned objects while disregarding the impact of incident x-ray energy spectra. The multiple-spectral model is in urgent need for CBCT scatter estimation.Approach.In this work, we incorporate the multiple spectral diagnostic multidetector CT labels into the pixel-to-pixel (Pix2pix) GAN to estimate accurate scatter distributions from CBCT projections acquired at various imaging volume sizes and x-ray energy spectra. The Pix2pix GAN combines the residual network as the generator and the PatchGAN as the discriminator to construct the correspondence between the scatter-contaminated projection and scatter distribution. The network architectures and loss function of Pix2pix GAN are optimized to achieve the best performance on projection-to-scatter transition.Results.The CBCT data of a head phantom and abdominal patients are applied to test the performance of the proposed method. The error of the corrected CBCT image using the proposed method is reduced from over 200 HU to be around 20 HU in both phantom and patient studies. The mean structural similarity index of the CT image is improved from 0.2 to around 0.9 after scatter correction using the proposed method compared with the MC-simulation method, which indicates a high similarity of the anatomy in the images before and after the proposed correction. The proposed method achieves higher accuracy of scatter estimation than using the Pix2pix GAN with the U-net generator.Significance.The proposed scheme is an effective solution to the multiple spectral CBCT scatter correction. The scatter-correction software using the proposed model will be available at:https://github.com/YangkangJiang/Cone-beam-CT-scatter-correction-tool.

Cone beam computed tomography (CBCT) plays an increasingly important role in image-guided radiation therapy. However, the image quality of CBCT is severely degraded by excessive scatter contamination, especially in the abdominal region, hindering its further applications in radiation therapy.To restore low-quality CBCT images contaminated by scatter signals, a scatter correction algorithm combining the advantages of convolutional neural networks (CNN) and Swin Transformer is proposed.In this paper a scatter correction model for CBCT image, the Flip Swin Transformer U-shape network (FSTUNet) model, is proposed. In this model, the advantages of CNN in texture detail and Swin Transformer in global correlation are used to accurately extract shallow and deep features, respectively. Instead of using the original Swin Transformer tandem structure, we build the Flip Swin Transformer Block to achieve a more powerful inter-window association extraction. The validity and clinical relevance of the method is demonstrated through extensive experiments on a Monte Carlo (MC) simulation dataset and frequency split dataset generated by a validated method, respectively.Experimental results on the MC simulated dataset show that the root mean square error of images corrected by the method is reduced from over 100 HU to about 7 HU. Both the structural similarity index measure (SSIM) and the universal quality index (UQI) are close to 1. Experimental results on the frequency split dataset demonstrate that the method not only corrects shading artifacts but also exhibits a high degree of structural consistency. In addition, comparison experiments show that FSTUNet outperforms UNet, Deep Residual Convolutional Neural Network (DRCNN), DSENet, Pix2pixGAN, and 3DUnet methods in both qualitative and quantitative metrics.Accurately capturing the features at different levels is greatly beneficial for reconstructing high-quality scatter-free images. The proposed FSTUNet method is an effective solution to CBCT scatter correction and has the potential to improve the accuracy of CBCT image-guided radiation therapy.

Weak absorption contrast in biological tissues has hindered x-ray computed tomography from accessing biological structures. Recently, grating-based imaging has emerged as a promising solution to biological low-contrast imaging, providing complementary and previously unavailable structural information of the specimen. Although it has been successfully applied to work with conventional x-ray sources, grating-based imaging is time-consuming and requires a sophisticated experimental setup. In this work, we demonstrate that a deep convolutional neural network trained with a generative adversarial network can directly convert x-ray absorption images into differential phase-contrast and dark-field images that are comparable to those obtained at both a synchrotron beamline and a laboratory facility. By smearing back all of the virtual projections, high-quality tomographic images of biological test specimens deliver the differential phase-contrast- and dark-field-like contrast and quantitative information, broadening the horizon of x-ray image contrast generation.

Nephron sparing nephrectomy may not reduce the prognosis of nephroblastoma in the absence of involvement of the renal capsule, sinus vessels, and lymph nodes, However, there is no accurate preoperative noninvasive evaluation method at present.105 nephroblastoma patients underwent contrast-enhanced CT scan between 2013 and 2020 in our hospital were retrospectively collected, including 59 cases with localized stage and 46 cases with non-localized stage, and then were divided into training cohort (n= 73) and validation cohort (n= 32) according to the order of CT scanning time. After lesion segmentation and data preprocessing, radiomic features were extracted from each volume of interest. The multi-step procedure including Pearson correlation analysis and sequential forward floating selection was performed to produce radiomic signature. Prediction model was constructed using the radiomic signature and Logistic Regression classifier for predicting the localized nephroblastoma in the training cohort. Finally, the model performance was validated in the validation cohort.A total of 1652 radiomic features have been extracted, from which TOP 10 features were selected as the radiomic signature. The area under the receiver operating characteristic curve, accuracy, sensitivity and specificity of the prediction model were 0.796, 0.795, 0.732 and 0.875 for the training cohort respectively, and 0.710, 0.719, 0.611 and 0.857 for the validation cohort respectively. The result comparison with prediction models composed of different machine learning classifiers and different parameters also manifest the effectiveness of our radiomic model.A logistic regression model based on radiomic features extracted from preoperative CT images had good ability to noninvasively predict nephroblastoma without renal capsule, sinus vessel, and lymph node involvement.

Whole slide image (WSI) has been widely used to assist automated diagnosis under the deep learning fields. However, most previous works only discuss the SINGLE task setting which is not aligned with real clinical setting, where pathologists often conduct multiple diagnosis tasks simultaneously. Also, it is commonly recognized that the multi-task learning paradigm can improve learning efficiency by exploiting commonalities and differences across multiple tasks. To this end, we present a novel multi-task framework (i.e., MulGT) for WSI analysis by the specially designed Graph-Transformer equipped with Task-aware Knowledge Injection and Domain Knowledge-driven Graph Pooling modules. Basically, with the Graph Neural Network and Transformer as the building commons, our framework is able to learn task-agnostic low-level local information as well as task-specific high-level global representation. Considering that different tasks in WSI analysis depend on different features and properties, we also design a novel Task-aware Knowledge Injection module to transfer the task-shared graph embedding into task-specific feature spaces to learn more accurate representation for different tasks. Further, we elaborately design a novel Domain Knowledge-driven Graph Pooling module for each task to improve both the accuracy and robustness of different tasks by leveraging different diagnosis patterns of multiple tasks. We evaluated our method on two public WSI datasets from TCGA projects, i.e., esophageal carcinoma and kidney carcinoma. Experimental results show that our method outperforms single-task counterparts and the state-of-theart methods on both tumor typing and staging tasks.

Objective.Ultra-high-dose-rate radiotherapy, referred to as FLASH therapy, has been demonstrated to reduce the damage of normal tissue as well as inhibiting tumor growth compared with conventional dose-rate radiotherapy. The transient hypoxia may be a vital explanation for sparing the normal tissue. The heterogeneity of oxygen distribution for different doses and dose rates in the different radiotherapy schemes are analyzed. With these results, the influence of doses and dose rates on cell survival are evaluated in this work.Approach.The two-dimensional reaction-diffusion equations are used to describe the heterogeneity of the oxygen distribution in capillaries and tissue. A modified linear quadratic model is employed to characterize the surviving fraction at different doses and dose rates.Main results.The reduction of the damage to the normal tissue can be observed if the doses exceeds a minimum dose threshold under the ultra-high-dose-rate radiation. Also, the surviving fraction exhibits the 'plateau effect' under the ultra-high dose rates radiation, which signifies that within a specific range of doses, the surviving fraction either exhibits minimal variation or increases with the dose. For a given dose, the surviving fraction increases with the dose rate until tending to a stable value, which means that the protection in normal tissue reaches saturation.Significance.The emergence of the 'plateau effect' allows delivering the higher doses while minimizing damage to normal tissue. It is necessary to develop appropriate program of doses and dose rates for different irradiated tissue to achieve more efficient protection.

Tumor angiogenesis is considered an important prognostic factor. With an increasing emphasis on imaging evaluation of the tumor microenvironment, dynamic contrast enhanced-computed tomography (DCE-CT) has evolved as an important functional technique in this setting. Yet many questions remain as to how and when these functional measurements should be performed for each agent and tumor type, and what quantitative models should be used in the fitting process. In this study, we evaluated the variations of perfusion measurement on DCE-CT for rectal cancer patients from (1) different tracer kinetic models, (2) different scan acquisition lengths, and (3) different scan intervals. A total of seven commonly used models were studied: the adiabatic approximation to the tissue homogeneity (AATH) model, adiabatic approximation to the homogeneity tissue with fixed transit time (AATHFT) model, the Tofts model (TM), the extended Tofts model (ETM), Patlak model, Logan model, and the model-free deconvolution method. Akaike's information criterion was used to identify the best fitting model. The interchangeability of different models was further evaluated using Bland–Altman analysis. All models gave comparable blood volume (BV) measurements except the Patlak method. While for the volume transfer constant (Ktrans) estimation, AATHFT, AATH, and ETM generated reasonable agreement among each other but not for the other models. Regarding the blood flow (BF) measurement, no two models were interchangeable. In addition, the perfusion parameters were compared with four acquisition times (45, 65, 85, and 105 s) and four temporal intervals (1, 2, 3, and 4 s). No significant difference was observed in the volume transfer constant (Ktrans), BV, and BF measurements when comparing data acquired over 65 s with data acquired over 105 s using any of the DCE models in this study. Yet increasing the temporal interval led to a significant overestimation of BF in the deconvolution method. In conclusion, the perfusion measurement is indeed model dependent and the image acquisition/processing technique is dependent. The radiation dose of DCE-CT was an average of 1.5–2 times an abdomen/pelvic CT, which is not insubstantial. To take the DCE-CT forward as a biomarker in oncology, prospective studies should be carefully designed with the optimal image acquisition and analysis technique.

Cone-beam CT (CBCT) imaging is used in the patient setup on the advance image-guided radiation therapy. However, the scatter contamination causes spatial non-uniformity, the error of the CT number, and image contrast loss, which is considered as one of the fundamental limitations for CBCT application. In this paper, we use both scatter correction and noise suppression for improving the quality of CBCT image and comprehensively evaluate our method on patient data. A CBCT software package with parallel computation is designed, which is easily compatible with the existing CBCT system of radiotherapy device with high computing efficiency and CT number accuracy. The primary signals of projections are estimated through the use of the forward projections from the registered planning CT (pCT). The errors of low frequency in the raw projections are obtained through subtracting the forward projections and the low-pass filter implementation. The penalty-weighted-least-square (PWLS) method is applied to reduce the high-frequency noise in the corrected CBCT projections. We use the graphics-processing unit (GPU) NVidia Tesla C2075 card with CUDA C programming to accelerate the time-consuming processes. The CBCT projections of a pelvis phantom and the two pelvis patients are obtained from the Varian TrueBeam system, which is a machine for the radiotherapy. The maximum errors of CT number are reduced over 70 HU on the TrueBeam result to below 15 HU, and the errors of spatial non-uniformity are decreased by a factor of around 7. The computation time is about 25 min on the GPU, which is reduced over 10 h on the CPU. The proposed software shows superior performance over the existing reconstruction. The proposed software demonstrates the reliability of the high-accuracy CBCT-based image-guided radiotherapy (IGRT), providing the high-precise CBCT with less computation time.

For the special characters, remote sensing image has higher requirements not only in the security but also in the management; it requires not only the active encryption during storage and transmission for preventing information leakage but also the marking technology to prevent illegal usage as well as copyright protection or even source tracing. Therefore, this paper proposes to integrate encryption and marking technology by the independence and fusion of orthogonal decomposition for the comprehensive security protection of remote sensing image. Under the proposed scheme, encryption and marking technology can achieve the operation independence and content mergence; moreover, there is no special requirement in selecting encryption and marking algorithms. It makes up the shortage of recent integration of encryption and watermarking based on spatial scrambling in applicability and security. According to the experimental results, integration of encryption and marking technology based on orthogonal decomposition satisfies the common constraints of encryption, and marking technology, furthermore, has little impact on remote sensing image data characters and later applications.

Intensity modulated arc therapy (IMAT) delivers conformal dose distributions through continuous gantry rotation with constant or variable speed while modulating the field aperture shape and weight. The enlarged angular space and machine delivery constraints make inverse planning of IMAT more intractable as compared to its counterpart of fixed gantry IMRT. Currently, IMAT inverse planning is being done using two extreme methods: the first one computes in beamlet domain with a subsequent arc leaf sequencing, and the second proceeds in machine parameter domain with entire emphasis placed on a pre-determined delivery method without exploring potentially better alternative delivery schemes. Towards truly optimizing the IMAT treatment on a patient specific basis, in this work we propose a total-variation based inverse planning framework for IMAT, which takes advantage of the useful features of the above two existing approaches while avoiding their shortcomings. A quadratic optimization algorithm has been implemented to demonstrate the performance and advantage of the proposed approach. Applications of the technique to a prostate case and a head and neck case indicate that the algorithm is capable of generating IMAT plans with patient specific numbers of arcs efficiently. Superior dose distributions and delivery time are achieved with a maximum number of apertures of three for each field. As compared to conventional beamlet-based algorithms, our method regularizes the field modulation complexity during optimization, and permits us to obtain the best possible plan with a pre-set modulation complexity of fluences. As illustrated in both prostate and head-and-neck case studies, the proposed method produces more favorable dose distributions than the segment-based algorithms, by optimally accommodating the clinical need of intensity modulation levels for each individual field. On a more fundamental level, our formulation preserves the convexity of optimization and makes the search of the global optimal solution possible with a deterministic method.

Dual-energy computed tomography (CT) has the potential to decompose tissues into different materials. However, the classic direct inversion (DI) method for multimaterial decomposition (MMD) cannot accurately separate more than two basis materials due to the ill-posed problem and amplified image noise. We propose an integrated MMD method that addresses the piecewise smoothness and intrinsic sparsity property of the decomposition image. The proposed MMD was formulated as an optimization problem including a quadratic data fidelity term, an isotropic total variation term that encourages image smoothness, and a nonconvex penalty function that promotes decomposition image sparseness. The mass and volume conservation rule was formulated as the probability simplex constraint. An accelerated primal-dual splitting approach with line search was applied to solve the optimization problem. The proposed method with different penalty functions was compared against DI on a digital phantom, a Catphan® 600 phantom, a quantitative imaging phantom, and a pelvis patient. The proposed framework distinctly separated the CT image up to 12 basis materials plus air with high decomposition accuracy. The cross talks between two different materials are substantially reduced, as shown by the decreased nondiagonal elements of the normalized cross correlation (NCC) matrix. The mean square error of the measured electron densities was reduced by 72.6%. Across all datasets, the proposed method improved the average volume fraction accuracy from 61.2% to 99.9% and increased the diagonality of the NCC matrix from 0.73 to 0.96. Compared with DI, the proposed MMD framework improved decomposition accuracy and material separation.