Anatomical Prior-Based Automatic Segmentation for Cardiac Substructures from Computed Tomography Images.

A Cascaded Deep Learning-Based Cardiac Substructures Segmentation Frame and on Non-Gated Non-Enhanced Planning CT Scans in Breast Cancer Patients

Evaluation of a delineation software for cardiac atlas-based autosegmentation: An example of the use of artificial intelligence in modern radiotherapy

Head and neck (H &N) cancer is one of the most prevalent cancers [1]. In its treatment and prognosis analysis, tumors and metastatic lymph nodes may play an important role but their manual segmentations are time-consuming and laborious. In this paper, we propose a coarse-to-fine ensembling framework to segment the H &N tumor and metastatic lymph nodes automatically from Positron Emission Tomography (PET) and Computed Tomography (CT) images. The framework consists of three steps. The first step is to locate the head region in CT images. The second step is a coarse segmentation, to locate the tumor and lymph region of interest (ROI) from the head region. The last step is a fine segmentation, to get the final precise predictions of tumors and metastatic lymph nodes, where we proposed a ensembling refinement model. This framework is evaluated quantitatively with aggregated Dice Similarity Coefficient (DSC) of 0.77782 in the task 1 of the HECKTOR 2022 challenge[2, 3] as team SJTU426.

The shape of pancreas in different patients is very different and the boundary is fuzzy, so the reliable automatic segmentation of pancreas is an important and difficult task. In this paper, we propose a multi-scale hybrid attention cascade network for challenging pancreas segmentation. First, the original CT images are coarsely segmented through the first-level network, then, the coarse segmentation results are clipped and sent to the second-level network for further training to obtain the fine segmentation results. The network adopts full convolutional network (FCN) integrating multi-scale mixed attention. The cut CT image eliminates the irrelevant background interference and reduces the input size of the secondary network, thus improving the segmentation accuracy. An extensive evaluation of 82 open data sets was performed by quadruple cross validation. The experimental results showed that the Dice coefficient was 84.62±4.20% compared with several advanced methods. In addition, this method has excellent performance in three measurement indexes of precision, Jaccard and recall.

Manual segmentation in lumbar paraspinal muscle studies is time-consuming, subject to variability, and limits comprehensive evaluation. To solve the problems, we aim to develop a deep learning algorithm for the automatic segmentation and multi-parameter quantification of eight paraspinal muscles in lumbar CT. We collected CT images covering the range from the superior endplate of the L1 vertebra to the inferior endplate of the S1 vertebra. The dataset was partitioned into training, validation, and test sets in a ratio of 7:1:2. Six convolutional neural networks were employed to automatically segment the bilateral psoas major, quadratus lumborum, erector spinae, and multifidus across all slices. Model performance was evaluated using the Dice Similarity Coefficient (DSC), Hausdorff Distance (HD), and mean Intersection over Union (mIoU). Muscle parameters including cross-sectional area, muscle volume, fat infiltration, CT density, and paraspinal muscle index were calculated. The Intraclass Correlation Coefficient [ICC(3,1)] was used to assess agreement between model's segmentations and manual ground truth. 100 lumbar CT scans (age, 55.02 ± 16.2; 62 female) were used for model development. The mean DSC across all six models ranged from 0.754 to 0.903. TransUNet demonstrated the best overall (DSC, 0.903; 95% CI: 0.902, 0.913) (HD, 9.934mm; 95% CI: 9.815, 11.902) (mIoU, 0.841; 95% CI: 0.839, 0.850). For individual muscles segmented by TransUNet, the highest DSC was 0.936 (95% CI: 0.934-0.938) for the right multifidus. The mean ICC for all parameters was 0.931. The highest ICC value was 0.999 (p < 0.001). The deep learning tool enables automatic and accurate segmentation of eight lumbar paraspinal muscles. Muscle parameter measurements derived from model's segmentations and manual ground truth exhibit high agreement. Accurate segmentation and quantification of paraspinal muscle parameters facilitates large-scale epidemiological studies of paraspinal muscles and spine-related diseases, overcoming the limitations in manual methods.

Background and PurposeStereotactic ablative body radiotherapy (SABR) is increasingly used for early-stage lung cancer, however the impact of dose to the heart and cardiac substructures remains largely unknown. The study investigated doses received by cardiac substructures in SABR patients and impact on survival. Materials and MethodsSSBROC is an Australian multi-centre phase II prospective study of SABR for stage I non-small cell lung cancer. Patients were treated between 2013 and 2019 across 9 centres. In this secondary analysis of the dataset, a previously published and locally developed open-source hybrid deep learning cardiac substructure automatic segmentation tool was deployed on the planning CTs of 117 trial patients. Physical doses to 18 cardiac structures and EQD2 converted doses (α/β = 3) were calculated. Endpoints evaluated include pericardial effusion and overall survival. Associations between cardiac doses and survival were analysed with the Kaplan–Meier method and Cox proportional hazards models. ResultsCardiac structures that received the highest physical mean doses were superior vena cava (22.5 Gy) and sinoatrial node (18.3 Gy). The highest physical maximum dose was received by the heart (51.7 Gy) and right atrium (45.3 Gy). Three patients developed grade 2, and one grade 3 pericardial effusion. The cohort receiving higher than median mean heart dose (MHD) had poorer survival compared to those who received below median MHD (p = 0.00004). On multivariable Cox analysis, male gender and maximum dose to ascending aorta were significant for worse survival. ConclusionsPatients treated with lung SABR may receive high doses to cardiac substructures. Dichotomising the patients according to median mean heart dose showed a clear difference in survival. On multivariable analyses gender and dose to ascending aorta were significant for survival, however cardiac substructure dosimetry and outcomes should be further explored in larger studies.

BackgroundNasopharyngeal carcinoma (NPC), an endemic malignancy in Southeast Asia and southern China, necessitates precise delineation of the gross tumor volume (GTV) for radiotherapy to optimize patient prognosis. Positron emission tomography (PET) imaging offers valuable metabolic insights to guide radiotherapy planning but is hampered by manual GTV segmentation, which is labor-intensive and prone to inter- and intra-observer variability. Conventional segmentation methods are inherently limited, and comparative evaluations of deep learning (DL) frameworks for PET-based primary NPC lesion segmentation remain scarce. Thus, this study aimed to optimize the delineation of primary NPC radiotherapy target volumes by leveraging PET-image-based DL segmentation technology, with the goal of enhancing both the precision and efficiency of lesion delineation.MethodsResearchers retrospectively collected PET imaging data from 212 NPC patients at the Affiliated Hospital of Guangdong Medical University. The patients were randomly divided into training (170 patients) and testing (42 patients) datasets. A radiation oncologist and a nuclear medicine physician collaboratively delineated the cancer lesion boundaries through consensus. After data preprocessing, three DL models (Res-Unet, Nn-Unet, and Nn-Former) were used to automatically segment the lesions. Training was based on the training dataset. During evaluation, the models’ segmentation performance was comprehensively assessed using Dice similarity coefficient (DSC) and Hausdorff distance (HD). A visual analysis of the results was also conducted to intuitively understand the models’ segmentation capabilities.ResultsIn the training set, Nn-Unet achieved the highest DSC of 0.869, whereas in the testing set, its DSC was 0.833. The DSC for Nn-Former hovered around 0.8 in both the training and testing sets. In contrast, Res-Unet demonstrated the lowest DSC values among the three models, particularly in the testing set (DSC =0.794). Statistical analysis revealed that the DSC of Nn-Unet was significantly higher than that of both Res-Unet and Nn-Former in the training set (P<0.01 for both comparisons). Regarding the 95% HD and average surface distance (ASD) values, Nn-Unet outperformed the other two models in both the training and testing sets. However, Res-Unet exhibited a much higher HD value in the testing set compared to the training set. The Loss curves for all models gradually decreased as training progressed, indicating that the models were learning relevant features of NPC lesions. The final Loss value for Res-Unet was approximately 0.7, whereas Nn-Unet and Nn-Former had final Loss values below 0.8.ConclusionsThe PET-image-based automatic segmentation model for the primary tumor of NPC established in this study demonstrates the clinical potential of Nn-Unet in primary lesion of NPC segmentation tasks.

For autosegmentation models, the data used to train the model (e.g., public datasets and/or vendor-collected data) and the data on which the model is deployed in the clinic are typically not the same, potentially impacting the performance of these models by a process called domain shift. Tools to routinely monitor and predict segmentation performance are needed for quality assurance. Here, we develop an approach to perform such monitoring and performance prediction for cardiac substructure segmentation. To develop a quality assurance (QA) framework for routine or continuous monitoring of domain shift and the performance of cardiac substructure autosegmentation algorithms. A benchmark dataset consisting of computed tomography (CT) images along with manual cardiac substructure delineations of 241 breast cancer radiotherapy patients were collected, including one "normal" image domain of clean images and five "abnormal" domains containing images with artifact (metal, contrast), pathology, or quality variations due to scanner protocol differences (field of view, noise, reconstruction kernel, and slice thickness). The QA framework consisted of an image domain shift detector which operated on the input CT images and a shape quality detector on the output of an autosegmentation model, and a regression model for predicting autosegmentation model performance. The image domain shift detector was composed of a trained denoising autoencoder (DAE) and two hand-engineered image quality features to detect normal versus abnormal domains in the input CT images. The shape quality detector was a variational autoencoder (VAE) trained to estimate the shape quality of the auto-segmentation results. The output from the image domain shift and shape quality detectors was used to train a regression model to predict the per-patient segmentation accuracy, measured by Dice coefficient similarity (DSC) to physician contours. Different regression techniques were investigated including linear regression, Bagging, Gaussian process regression, random forest, and gradient boost regression. Of the 241 patients, 60 were used to train the autosegmentation models, 120 for training the QA framework, and the remaining 61 for testing the QA framework. A total of 19 autosegmentation models were used to evaluate QA framework performance, including 18 convolutional neural network (CNN)-based and one transformer-based model. When tested on the benchmark dataset, all abnormal domains resulted in a significant DSC decrease relative to the normal domain for CNN models ( ), but only for some domains for the transformer model. No significant relationship was found between the performance of an autosegmentation model and scanner protocol parameters ( ) except noise ( ). CNN-based autosegmentation models demonstrated a decreased DSC ranging from 0.07 to 0.41 with added noise, while the transformer-based model was not significantly affected (ANOVA, ). For the QA framework, linear regression models with bootstrap aggregation resulted in the highest mean absolute error (MAE) of , in predicted DSC (relative to true DSC between autosegmentation and physician). MAE was lowest when combining both input (image) detectors and output (shape) detectors compared to output detectors alone. A QA framework was able to predict cardiac substructure autosegmentation model performance for clinically anticipated "abnormal" domain shifts.

BackgroundThe evaluation of automatic segmentation algorithms is commonly performed using geometric metrics. An analysis based on dosimetric parameters might be more relevant in clinical practice but is often lacking in the literature. The aim of this study was to investigate the impact of state-of-the-art 3D U-Net-generated organ delineations on dose optimization in radiation therapy (RT) for prostate cancer patients.MethodsA database of 69 computed tomography images with prostate, bladder, and rectum delineations was used for single-label 3D U-Net training with dice similarity coefficient (DSC)-based loss. Volumetric modulated arc therapy (VMAT) plans have been generated for both manual and automatic segmentations with the same optimization settings. These were chosen to give consistent plans when applying perturbations to the manual segmentations. Contours were evaluated in terms of DSC, average and 95% Hausdorff distance (HD). Dose distributions were evaluated with the manual segmentation as reference using dose volume histogram (DVH) parameters and a 3%/3 mm gamma-criterion with 10% dose cut-off. A Pearson correlation coefficient between DSC and dosimetric metrics, i.e. gamma index and DVH parameters, has been calculated.Results3D U-Net-based segmentation achieved a DSC of 0.87 (0.03) for prostate, 0.97 (0.01) for bladder and 0.89 (0.04) for rectum. The mean and 95% HD were below 1.6 (0.4) and below 5 (4) mm, respectively. The DVH parameters, V_{60/65/70,{mathrm{Gy}}} for the bladder and V_{50/65/70,{mathrm{Gy}}} for the rectum, showed agreement between dose distributions within pm , 5% and pm ,2%, respectively. The D_{98/2%} and V_{95%}, for prostate and its 3 mm expansion (surrogate clinical target volume) showed agreement with the reference dose distribution within 2% and 3 Gy with the exception of one case. The average gamma pass-rate was 85%. The comparison between geometric and dosimetric metrics showed no strong statistically significant correlation.ConclusionsThe 3D U-Net developed for this work achieved state-of-the-art geometrical performance. Analysis based on clinically relevant DVH parameters of VMAT plans demonstrated neither excessive dose increase to OARs nor substantial under/over-dosage of the target in all but one case. Yet the gamma analysis indicated several cases with low pass rates. The study highlighted the importance of adding dosimetric analysis to the standard geometric evaluation.

Accurate and robust auto-segmentation of highly deformable organs (HDOs), for example, stomach or bowel, remains an outstanding problem due to these organs' frequent and large anatomical variations. Yet, time-consuming manual segmentation of these organs presents a particular challenge to time-limited modern radiotherapy techniques such as on-line adaptive radiotherapy and high-dose-rate brachytherapy. We propose a machine-assisted interpolation (MAI) that uses prior information in the form of sparse manual delineations to facilitate rapid, accurate segmentation of the stomach from low field magnetic resonance images (MRI) and the bowel from computed tomography (CT) images. Stomach MR images from 116 patients undergoing 0.35T MRI-guided abdominal radiotherapy and bowel CT images from 120 patients undergoing high dose rate pelvic brachytherapy treatment were collected. For each patient volume, the manual delineation of the HDO was extracted from every 8th slice. These manually drawn contours were first interpolated to obtain an initial estimate of the HDO contour. A two-channel 64×64pixel patch-based convolutional neural network (CNN) was trained to localize the position of the organ's boundary on each slice within a five-pixel wide road using the image and interpolated contour estimate. This boundary prediction was then input, in conjunction with the image, to an organ closing CNN which output the final organ segmentation. A Dense-UNet architecture was used for both networks. The MAI algorithm was separately trained for the stomach segmentation and the bowel segmentation. Algorithm performance was compared against linear interpolation (LI) alone and against fully automated segmentation (FAS) using a Dense-UNet trained on the same datasets. The Dice Similarity Coefficient (DSC) and mean surface distance (MSD) metrics were used to compare the predictions from the three methods. Statistically significance was tested using Student's t test. For the stomach segmentation, the mean DSC from MAI (0.91 ± 0.02) was 5.0% and 10.0% higher as compared to LI and FAS, respectively. The average MSD from MAI (0.77 ± 0.25mm) was 0.54 and 3.19mm lower compared to the two other methods. Only 7% of MAI stomach predictions resulted in a DSC<0.8, as compared to 30% and 28% for LI and FAS, respectively. For the bowel segmentation, the mean DSC of MAI (0.90 ± 0.04) was 6% and 18% higher, and the average MSD of MAI (0.93 ± 0.48mm) was 0.42 and 4.9mm lower as compared to LI and FAS. Sixteen percent of the predicted contour from MAI resulted in a DSC<0.8, as compared to 46% and 60% for FAS and LI, respectively. All comparisons between MAI and the baseline methods were found to be statistically significant (p-value<0.001). The proposed MAI algorithm significantly outperformed LI in terms of accuracy and robustness for both stomach segmentation from low-field MRIs and bowel segmentation from CT images. At this time, FAS methods for HDOs still require significant manual editing. Therefore, we believe that the MAI algorithm has the potential to expedite the process of HDO delineation within the radiation therapy workflow.

There has been a significant increase from 2010 to 2016 in the number of people suffering from spine problems. The automatic image segmentation of the spine obtained from a computed tomography (CT) image is important for diagnosing spine conditions and for performing surgery with computer-assisted surgery systems. The spine has a complex anatomy that consists of 33 vertebrae, 23 intervertebral disks, the spinal cord, and connecting ribs. As a result, the spinal surgeon is faced with the challenge of needing a robust algorithm to segment and create a model of the spine. In this study, we developed a fully automatic segmentation method to segment the spine from CT images, and we compared our segmentation results with reference segmentations obtained by well-known methods. We use a hybrid method. This method combines the convolutional neural network (CNN) and fully convolutional network (FCN), and utilizes class redundancy as a soft constraint to greatly improve the segmentation results. The proposed method was found to significantly enhance the accuracy of the segmentation results and the system processing time. Our comparison was based on 12 measurements: the Dice coefficient (94%), Jaccard index (93%), volumetric similarity (96%), sensitivity (97%), specificity (99%), precision (over segmentation 8.3 and under segmentation 2.6), accuracy (99%), Matthews correlation coefficient (0.93), mean surface distance (0.16 mm), Hausdorff distance (7.4 mm), and global consistency error (0.02). We experimented with CT images from 32 patients, and the experimental results demonstrated the efficiency of the proposed method. Highlights A method to enhance the accuracy of spine segmentation from CT data was proposed. The proposed method uses Convolutional Neural Network via redundant generation of class labels. Experiments show the segmentation accuracy has been enhanced.

Epicardial adipose tissue (EAT) is a visceral fat deposit, that’s known for its association with factors, such as obesity, diabetes mellitus, age, and hypertension. Segmentation of the EAT in a fast and reproducible way is important for the interpretation of its role as an independent risk marker intricate. However, EAT has a variable distribution, and various diseases may affect the volume of the EAT, which can increase the complexity of the already time-consuming manual segmentation work. We propose a 3D deep attention U-Net method to automatically segment the EAT from coronary computed tomography angiography (CCTA). Five-fold cross-validation and hold-out experiments were used to evaluate the proposed method through a retrospective investigation of 200 patients. The automatically segmented EAT volume was compared with physician-approved clinical contours. Quantitative metrics used were the Dice similarity coefficient (DSC), sensitivity, specificity, Jaccard index (JAC), Hausdorff distance (HD), mean surface distance (MSD), residual mean square distance (RMSD), and the center of mass distance (CMD). For cross-validation, the median DSC, sensitivity, and specificity were 92.7%, 91.1%, and 95.1%, respectively, with JAC, HD, CMD, MSD, and RMSD are 82.9% ± 8.8%, 3.77 ± 1.86 mm, 1.98 ± 1.50 mm, 0.37 ± 0.24 mm, and 0.65 ± 0.37 mm, respectively. For the hold-out test, the accuracy of the proposed method remained high. We developed a novel deep learning-based approach for the automated segmentation of the EAT on CCTA images. We demonstrated the high accuracy of the proposed learning-based segmentation method through comparison with ground truth contour of 200 clinical patient cases using 8 quantitative metrics, Pearson correlation, and Bland-Altman analysis. Our automatic EAT segmentation results show the potential of the proposed method to be used in computer-aided diagnosis of coronary artery diseases (CADs) in clinical settings.

Automatic segmentation of kidneys in computed tomography images using U-Net

Background and objectiveThe size, shape, and position of the pancreas are affected by the patient characteristics such as age, sex, adiposity. Owing to more complex anatomical structures (size, shape, and position) of the pancreas, specialists have some difficulties in the analysis of pancreatic diseases (diabetes, pancreatic cancer, pancreatitis). Therefore, the treatment of the disease requires enormous time and depends on the experience of specialists. In order to decrease the rate of pancreatic disease deaths and to assist the specialist in the analysis of pancreatic diseases, automatic pancreas segmentation techniques have been actively developed in the research article for many years. MethodsAlthough the rapid growth of deep learning and proving satisfactory performance in many medical image processing and computer vision applications, the maximum Dice Similarity Coefficients (DSC) value of these techniques related to automatic pancreas segmentation is only around 85% due to complex structure of the pancreas and other factors. Contrary to previous techniques which are required significantly higher computational power and memory, this paper suggests a novel two-phase approach for high-accuracy automatic pancreas segmentation in computed tomography (CT) imaging. The proposed approach consists of two phases; (1) Pancreas Localization, where the rough pancreas position is detected on the 2D CT slice by adopting Mask R-CNN model, (2) Pancreas Segmentation, where the segmented pancreas region is produced by refining the candidate pancreas region with 3D U-Net on the 2D sub-CT slices generated in the first phase. Both qualitative and quantitative assessments of the proposed approach are performed on the NIH data set. ResultsIn order to evaluate the achievement of the recommended approach, a total of 16 different automatic pancreas segmentation techniques reported in the literature are compared by utilizing performance assessment procedures which are Dice Similarity Coefficient (DSC), Jaccard Index (JI), Precision (PRE), Recall (REC), Pixel Accuracy (ACC), Specificity (SPE), Receiver Operating Characteristics (ROC) and Area under ROC curve (AUC). The average values of DSC, JI, REC and ACC are computed as 86.15%, 75.93%, 86.27%, 86.27% and 99.95% respectively, which are the best values among well-established studies for automatic pancreas segmentation. ConclusionIt is demonstrated with qualitative and quantitative results that our suggested two-phase approach creates more favorable results than other existing approaches.

Objective To investigate the application of CT image and cone beam computed tomography (CBCT) image registration based on 3D Slicer software in image-guided radiotherapy for uterine cervical neoplasms. Methods Based on 3D Slicer software and Slicer RT toolkit, 10 positioning CT images and 50 CBCT images of 10 patients with uterine cervical neoplasms in Henan Provincial People's Hospital between January 2018 and October 2018 had rigid registration and b-spline deformation registration respectively. The dice similarity coefficient (DSC) and Hausdorff distance (HD) of the bladder, rectum, femoral head, spinal cord, and body of CT-CBCT images were compared by using paired t-test before and after the registration. Results Pre-registration, rigid registration and after b-spline deformation registration of CT images and CBCT images, the DSC in the bladder (0.459±0.177, 0.528±0.184, 0.542±0.187, respectively), the rectum (0.564±0.141, 0.632±0.091, 0.684±0.097, respectively), the femoral head (0.695±0.088, 0.833±0.030, 0.865±0.027, respectively), the spinal cord (0.587±0.119, 0.746±0.085, 0.834±0.032, respectively) and the body surface (0.922±0.013, 0.948±0.011, 0.959±0.009, respectively) showed an increased trend; HD in the bladder (12.8±7.2, 12.2±7.1, 11.7±7.3, respectively), the rectum (5.0±1.8, 4.4±1.2, 3.4±1.2, respectively), the femoral head (3.6±1.2, 1.8±0.5, 1.5±0.5, respectively), the spinal cord (4.0±1.0, 2.7±1.3, 1.8±0.5, respectively) and the body surface (6.3±2.1, 5.2±2.0, 4.3±2.0, respectively) showed a decreased trend. The differences of pairwise comparison in the same parts were statistically significant (all P < 0.05). Conclusions Both rigid registration and b-spline deformation registration of CT-CBCT images based on 3D Slicer software can improve the radiotherapy accuracy of uterine cervical neoplasms, and b-spline deformation registration has more significant advantages. Key words: Uterine cervical neoplasms; Radiotherapy; 3D Slicer software; Cone-beam computed tomography; Image registration; Image-guided radiation therapy