CT male pelvic organ segmentation using fully convolutional networks with boundary sensitive representation

Evaluating the dosimetric impact of deep-learning-based auto-segmentation in prostate cancer radiotherapy: Insights into real-world clinical implementation and inter-observer variability

PURPOSE

This study aimed to investigate the dosimetric impact of deep-learning-based auto-contouring for clinical target volume (CTV) and organs at risk (OARs) delineation in prostate cancer radiotherapy planning. Additionally, we compared the geometric accuracy of auto-contouring system to the variability observed between human experts.

METHODS

We evaluated 28 planning CT volumes, each with three contour sets: reference original contours (OC), auto-segmented contours (AC), and expert-defined manual contours (EC). We generated 3D-CRT and intensity-modulated radiation therapy (IMRT) plans for each contour set and compared their dosimetric characteristics using dose-volume histograms (DVHs), homogeneity index (HI), conformity index (CI), and gamma pass rate (3%/3 mm).

RESULTS

The geometric differences between automated contours and both their original manual reference contours and a second set of manually generated contours are smaller than the differences between two manually contoured sets for bladder, right femoral head (RFH), and left femoral head (LFH) structures. Furthermore, dose distribution accuracy using planning target volumes (PTVs) derived from automatically contoured CTVs and auto-contoured OARs demonstrated consistency with plans based on reference contours across all evaluated cases for both 3D-CRT and IMRT plans. For example, in IMRT plans, the average D95 for PTVs was 77.71 ± 0.53 Gy for EC plans, 77.58 ± 0.69 Gy for OC plans, and 77.62 ± 0.38 Gy for AC plans. Automated contouring significantly reduced contouring time, averaging 0.53 ± 0.08 min compared to 24.9 ± 4.5 min for manual delineation.

CONCLUSION

Our automated contouring system can reduce inter-expert variability and achieve dosimetric accuracy comparable to gold standard reference contours, highlighting its potential for streamlining clinical workflows. The quantitative analysis revealed no consistent trend of increasing or decreasing PTVs derived from automatically contoured CTVs and OAR doses due to automated contours, indicating minimal impact on treatment outcomes. These findings support the clinical feasibility of utilizing our deep-learning-based auto-contouring model for prostate cancer radiotherapy planning.

OSAIRIS: Lessons Learned From the Hospital-Based Implementation and Evaluation of an Open-Source Deep-Learning Model for Radiotherapy Image Segmentation

Several studies report the benefits and accuracy of using autosegmentation for organ at risk (OAR) outlining in radiotherapy treatment planning. Typically, evaluations focus on accuracy metrics, and other parameters such as perceived utility and safety are routinely ignored. Here, we report our finding from the implementation and clinical evaluation of OSAIRIS, an open-source AI model for radiotherapy image segmentation that was carried out as part of its development into a medical device. The device contours OARs in the head and neck and male pelvis (referred to as the prostate model), and is designed to be used as a time-saving workflow device, alongside a clinician. Unlike standard evaluation processes, which heavily rely on accuracy metrics alone, our evaluation sought to demonstrate the tangible benefits, quantify utility and assess risk within a specific clinical workflow. We evaluated the time-saving benefit this device affords to clinicians, and how this time-saving might be linked to accuracy metrics, as well as the clinicians' assessment of the usability of the OSAIRIS contours in comparison to their colleagues' contours and those from other commercial AI contouring devices. Our safety evaluation focused on whether clinicians can notice and correct any errors should they be included in the output of the device. We found that OSAIRIS affords a significant time-saving of 36% (5.4 ± 2.1 minutes) when used for prostate contouring and 67% (30.3 ± 8.7 minutes) for head and neck contouring. Combining editing time data with accuracy metrics, we found the Hausdorff distance best correlated with editing-time, outperforming dice, the industry-standard, with a Spearman correlation coefficient of 0.70, and a Kendall coefficient of 0.52. Our safety and risk-mitigation exercise showed that anchoring bias is present when clinicians edit AI-generated contours, with the effect seemingly more pronounced for some structures over others. Most errors, however, were corrected by clinicians, with 72% of the head and neck errors 81% of the prostate errors removed in the editing step. Notably, our blinded clinician contour rating exercise showed that gold standard clinician contours are not rated more highly than the AI-generated contours. We conclude that evaluations of AI in a clinical setting must consider the clinical workflow in which the device will be used, and not rely on accuracy metrics alone, in order to reliably assess the benefits, utility and safety of the device. The effects of human-AI inter-operation must be evaluated to accurately assess the practical usability and potential uptake of the technology, as demonstrated in our blinded clinical utility review. The clinical risks posed by the use of the device must be studied and mitigated as far as possible, and our 'Mystery Shopping' experiment provides a template for future such assessments.

Toward high-quality pseudo masks from noisy or weak annotations for robust medical image segmentation

Deep learning networks excel in image segmentation with abundant accurately annotated training samples. However, in medical applications, acquiring large quantities of high-quality labeled images is prohibitively expensive. Thus, learning from imperfect annotations (e.g. noisy or weak annotations) has emerged as a prominent research area in medical image segmentation. This work aims to extract high-quality pseudo masks from imperfect annotations with the assistance of a small number of clean labels. Our core motivation is based on the understanding that different types of flawed imperfect annotations inherently exhibit unique noise patterns. Comparing clean annotations with corresponding imperfectly annotated labels can effectively identify potential noise patterns at minimal additional cost. To this end, we propose a two-phase framework including a noise identification network and a noise-robust segmentation network. The former network implicitly learns noise patterns and revises labels accordingly. It includes a three-branch network to identify different types of noises. The latter one further mitigates the negative influence of residual annotation noises based on parallel segmentation networks with different initializations and a label softening strategy. Extensive experimental results on two public datasets demonstrate that our method can effectively refine annotation flaws and achieve superior segmentation performance to the state-of-the-art methods.

Deep learning-based segmentation for high-dose-rate brachytherapy in cervical cancer using 3D Prompt-ResUNet

Objective.To develop and evaluate a 3D Prompt-ResUNet module that utilized the prompt-based model combined with 3D nnUNet for rapid and consistent autosegmentation of high-risk clinical target volume (HRCTV) and organ at risk (OAR) in high-dose-rate brachytherapy for cervical cancer patients.Approach.We used 73 computed tomography scans and 62 magnetic resonance imaging scans from 135 (103 for training, 16 for validation, and 16 for testing) cervical cancer patients across two hospitals for HRCTV and OAR segmentation. A novel comparison of the deep learning neural networks 3D Prompt-ResUNet, nnUNet, and segment anything model-Med3D was applied for the segmentation. Evaluation was conducted in two parts: geometric and clinical assessments. Quantitative metrics included the Dice similarity coefficient (DSC), 95th percentile Hausdorff distance (HD95%), Jaccard index (JI), and Matthews correlation coefficient (MCC). Clinical evaluation involved interobserver comparison, 4-grade expert scoring, and a double-blinded Turing test.Main results.The Prompt-ResUNet model performed most similarly to experienced radiation oncologists, outperforming less experienced ones. During testing, the DSC, HD95% (mm), JI, and MCC value (mean ± SD) for HRCTV were 0.92 ± 0.03, 2.91 ± 0.69, 0.85 ± 0.04, and 0.92 ± 0.02, respectively. For the bladder, these values were 0.93 ± 0.05, 3.07 ± 1.05, 0.87 ± 0.08, and 0.93 ± 0.05, respectively. For the rectum, they were 0.87 ± 0.03, 3.54 ± 1.46, 0.78 ± 0.05, and 0.87 ± 0.03, respectively. For the sigmoid, they were 0.76 ± 0.11, 7.54 ± 5.54, 0.63 ± 0.14, and 0.78 ± 0.09, respectively. The Prompt-ResUNet achieved a clinical viability score of at least 2 in all evaluation cases (100%) for both HRCTV and bladder and exceeded the 30% positive rate benchmark for all evaluated structures in the Turing test.Significance.The Prompt-ResUNet architecture demonstrated high consistency with ground truth in autosegmentation of HRCTV and OARs, reducing interobserver variability and shortening treatment times.

An efficient segment anything model for the segmentation of medical images

This paper introduces the efficient medical-images-aimed segment anything model (EMedSAM), addressing the high computational demands and limited adaptability of using SAM for medical image segmentation tasks. We present a novel, compact image encoder, DD-TinyViT, designed to enhance segmentation efficiency through an innovative parameter tuning method called med-adapter. The lightweight DD-TinyViT encoder is derived from the well-known ViT-H using a decoupled distillation approach.The segmentation and recognition capabilities of EMedSAM for specific structures are improved by med-adapter, which dynamically adjusts the model parameters specifically for medical imaging. We conducted extensive testing on EMedSAM using the public FLARE 2022 dataset and datasets from the First Hospital of Zhejiang University School of Medicine. The results demonstrate that our model outperforms existing state-of-the-art models in both multi-organ and lung segmentation tasks.

Automated contouring of CTV and OARs in planning CT scans using novel hybrid convolution-transformer networks for prostate cancer radiotherapy

PURPOSE OBJECTIVE(S)

Manual contouring of the prostate region in planning computed tomography (CT) images is a challenging task due to factors such as low contrast in soft tissues, inter- and intra-observer variability, and variations in organ size and shape. Consequently, the use of automated contouring methods can offer significant advantages. In this study, we aimed to investigate automated male pelvic multi-organ contouring in multi-center planning CT images using a hybrid convolutional neural network-vision transformer (CNN-ViT) that combines convolutional and ViT techniques.

MATERIALS/METHODS

We used retrospective data from 104 localized prostate cancer patients, with delineations of the clinical target volume (CTV) and critical organs at risk (OAR) for external beam radiotherapy. We introduced a novel attention-based fusion module that merges detailed features extracted through convolution with the global features obtained through the ViT.

RESULTS

The average dice similarity coefficients (DSCs) achieved by VGG16-UNet-ViT for the prostate, bladder, rectum, right femoral head (RFH), and left femoral head (LFH) were 91.75%, 95.32%, 87.00%, 96.30%, and 96.34%, respectively. Experiments conducted on multi-center planning CT images indicate that combining the ViT structure with the CNN network resulted in superior performance for all organs compared to pure CNN and transformer architectures. Furthermore, the proposed method achieves more precise contours compared to state-of-the-art techniques.

CONCLUSION

Results demonstrate that integrating ViT into CNN architectures significantly improves segmentation performance. These results show promise as a reliable and efficient tool to facilitate prostate radiotherapy treatment planning.

An AS-OCT image dataset for deep learning-enabled segmentation and 3D reconstruction for keratitis

Infectious keratitis is among the major causes of global blindness. Anterior segment optical coherence tomography (AS-OCT) images allow the characterizing of cross-sectional structures in the cornea with keratitis thus revealing the severity of inflammation, and can also provide 360-degree information on anterior chambers. The development of image analysis methods for such cases, particularly deep learning methods, requires a large number of annotated images, but to date, there is no such open-access AS-OCT image repository. For this reason, this work provides a dataset containing a total of 1168 AS-OCT images of patients with keratitis, including 768 full-frame images (6 patients). Each image has associated segmentation labels for lesions and cornea, and also labels of iris for full-frame images. This study provides a great opportunity to advance the field of image analysis on AS-OCT images in both two-dimensional (2D) and three-dimensional (3D) and would aid in the development of artificial intelligence-based keratitis management.

Novel dosimetric validation of a commercial CT scanner based deep learning automated contour solution for prostate radiotherapy

PURPOSE

OAR delineation accuracy influences: (i) a patient's optimised dose distribution (PD), (ii) the reported doses (RD) presented at approval, which represent plan quality. This study utilised a novel dosimetric validation methodology, comprehensively evaluating a new CT-scanner-based AI contouring solution in terms of PD and RD within an automated planning workflow.

METHODS

20 prostate patients were selected to evaluate AI contouring for rectum, bladder, and proximal femurs. Five planning 'pipelines' were considered; three using AI contours with differing levels of manual editing (nominally none (AIStd), minor editing in specific regions (AIMinEd), and fully corrected (AIFullEd)). Remaining pipelines were manual delineations from two observers (MDOb1, MDOb2). Automated radiotherapy plans were generated for each pipeline. Geometric and dosimetric agreement of contour sets AIStd, AIMinEd, AIFullEd and MDOb2 were evaluated against the reference set MDOb1. Non-inferiority of AI pipelines was assessed, hypothesising that compared to MDOb1, absolute deviations in metrics for AI contouring were no greater than that from MDOb2.

RESULTS

Compared to MDOb1, organ delineation time was reduced by 24.9 min (96 %), 21.4 min (79 %) and 12.2 min (45 %) for AIStd, AIMinEd and AIFullEd respectively. All pipelines exhibited generally good dosimetric agreement with MDOb1. For RD, median deviations were within ± 1.8 cm3, ± 1.7 % and ± 0.6 Gy for absolute volume, relative volume and mean dose metrics respectively. For PD, respective values were within ± 0.4 cm3, ± 0.5 % and ± 0.2 Gy. Statistically (p < 0.05), AIMinEd and AIFullEd were dosimetrically non-inferior to MDOb2.

CONCLUSIONS

This novel dosimetric validation demonstrated that following targeted minor editing (AIMinEd), AI contours were dosimetrically non-inferior to manual delineations, reducing delineation time by 79 %.

Artificial Intelligence-Based Organ Delineation for Radiation Treatment Planning of Prostate Cancer on Computed Tomography

Purpose

Meticulous manual delineations of the prostate and the surrounding organs at risk are necessary for prostate cancer radiation therapy to avoid side effects to the latter. This process is time consuming and hampered by inter- and intraobserver variability, all of which could be alleviated by artificial intelligence (AI). This study aimed to evaluate the performance of AI compared with manual organ delineations on computed tomography (CT) scans for radiation treatment planning.

Methods and Materials

Manual delineations of the prostate, urinary bladder, and rectum of 1530 patients with prostate cancer who received curative radiation therapy from 2006 to 2018 were included. Approximately 50% of those CT scans were used as a training set, 25% as a validation set, and 25% as a test set. Patients with hip prostheses were excluded because of metal artifacts. After training and fine-tuning with the validation set, automated delineations of the prostate and organs at risk were obtained for the test set. Sørensen-Dice similarity coefficient, mean surface distance, and Hausdorff distance were used to evaluate the agreement between the manual and automated delineations.

Results

The median Sørensen-Dice similarity coefficient between the manual and AI delineations was 0.82, 0.95, and 0.88 for the prostate, urinary bladder, and rectum, respectively. The median mean surface distance and Hausdorff distance were 1.7 and 9.2 mm for the prostate, 0.7 and 6.7 mm for the urinary bladder, and 1.1 and 13.5 mm for the rectum, respectively.

Conclusions

Automated CT-based organ delineation for prostate cancer radiation treatment planning is feasible and shows good agreement with manually performed contouring.

Cascaded cross-attention transformers and convolutional neural networks for multi-organ segmentation in male pelvic computed tomography

Purpose

Segmentation of the prostate and surrounding organs at risk from computed tomography is required for radiation therapy treatment planning. We propose an automatic two-step deep learning-based segmentation pipeline that consists of an initial multi-organ segmentation network for organ localization followed by organ-specific fine segmentation.

Approach

Initial segmentation of all target organs is performed using a hybrid convolutional-transformer model, axial cross-attention UNet. The output from this model allows for region of interest computation and is used to crop tightly around individual organs for organ-specific fine segmentation. Information from this network is also propagated to the fine segmentation stage through an image enhancement module, highlighting regions of interest in the original image that might be difficult to segment. Organ-specific fine segmentation is performed on these cropped and enhanced images to produce the final output segmentation.

Results

We apply the proposed approach to segment the prostate, bladder, rectum, seminal vesicles, and femoral heads from male pelvic computed tomography (CT). When tested on a held-out test set of 30 images, our two-step pipeline outperformed other deep learning-based multi-organ segmentation algorithms, achieving average dice similarity coefficient (DSC) of 0.836 ± 0.071 (prostate), 0.947 ± 0.038 (bladder), 0.828 ± 0.057 (rectum), 0.724 ± 0.101 (seminal vesicles), and 0.933 ± 0.020 (femoral heads).

Conclusions

Our results demonstrate that a two-step segmentation pipeline with initial multi-organ segmentation and additional fine segmentation can delineate male pelvic CT organs well. The utility of this additional layer of fine segmentation is most noticeable in challenging cases, as our two-step pipeline produces noticeably more accurate and less erroneous results compared to other state-of-the-art methods on such images.

Adaptive Region-Specific Loss for Improved Medical Image Segmentation

Defining the loss function is an important part of neural network design and critically determines the success of deep learning modeling. A significant shortcoming of the conventional loss functions is that they weight all regions in the input image volume equally, despite the fact that the system is known to be heterogeneous (i.e., some regions can achieve high prediction performance more easily than others). Here, we introduce a region-specific loss to lift the implicit assumption of homogeneous weighting for better learning. We divide the entire volume into multiple sub-regions, each with an individualized loss constructed for optimal local performance. Effectively, this scheme imposes higher weightings on the sub-regions that are more difficult to segment, and vice versa. Furthermore, the regional false positive and false negative errors are computed for each input image during a training step and the regional penalty is adjusted accordingly to enhance the overall accuracy of the prediction. Using different public and in-house medical image datasets, we demonstrate that the proposed regionally adaptive loss paradigm outperforms conventional methods in the multi-organ segmentations, without any modification to the neural network architecture or additional data preparation.

A research on the improved rotational robustness for thoracic organ delineation by using joint learning of segmenting spatially-correlated organs: A U-net based comparison

PURPOSE

To study the improved rotational robustness by using joint learning of spatially-correlated organ segmentation (SCOS) for thoracic organ delineation. The network structure is not our point.

METHODS

The SCOS was implemented in a U-net-like model (abbr. SCOS-net) and evaluated on unseen rotated test sets. Two hundred sixty-seven patients with thoracic tumors (232 without rotation and 35 with rotation) were enrolled. The training and validation images came from 61 randomly chosen unrotated patients. The test data included two sets. One consisted of 3000 slices from the rest 171 unrotated patients. They were rotated by us by -30°∼30°. One was the images from the 35 rotated patients. The lung, heart, and spinal cord were delineated by experienced radiation oncologists and regarded as ground truth. The SCOS-net was compared with its single-task learning counterparts, two published multiple learning task settings, and rotation augmentation. Dice, 3 distance metrics (maximum and 95th percentile of Hausdorff distances and average surface distance (ASD)) and the number of cases where ASD = infinity were adopted. We analyzed the results using visualization techniques.

RESULTS

In terms of no augmentation, the SCOS-net achieves the best lung and spinal cord segmentations and comparable heart delineation. With augmentation, SCOS performs better in some cases.

CONCLUSION

The proposed SCOS can improve rotational robustness, and is promising in clinical applications for its low network capacity and computational cost.

Weakly supervised bilayer convolutional network in segmentation of HER2 related cells to guide HER2 targeted therapies

Overexpression of human epidermal growth factor receptor 2 (HER2/ERBB2) is identified as a prognostic marker in metastatic breast cancer and a predictor to determine the effects of ERBB2-targeted drugs. Accurate ERBB2 testing is essential in determining the optimal treatment for metastatic breast cancer patients. Brightfield dual in situ hybridization (DISH) was recently authorized by the United States Food and Drug Administration for the assessment of ERRB2 overexpression, which however is a challenging task due to a variety of reasons. Firstly, the presence of touching clustered and overlapping cells render it difficult for segmentation of individual HER2 related cells, which must contain both ERBB2 and CEN17 signals. Secondly, the fuzzy cell boundaries make the localization of each HER2 related cell challenging. Thirdly, variation in the appearance of HER2 related cells is large. Fourthly, as manual annotations are usually made on targets with high confidence, causing sparsely labeled data with some unlabeled HER2 related cells defined as background, this will seriously confuse fully supervised AI learning and cause poor model outcomes. To deal with all issues mentioned above, we propose a two-stage weakly supervised deep learning framework for accurate and robust assessment of ERBB2 overexpression. The effectiveness and robustness of the proposed deep learning framework is evaluated on two DISH datasets acquired at two different magnifications. The experimental results demonstrate that the proposed deep learning framework achieves an accuracy of 96.78 ± 1.25, precision of 97.77 ± 3.09, recall of 84.86 ± 5.83 and Dice Index of 90.77 ± 4.1 and an accuracy of 96.43 ± 2.67, precision of 97.82 ± 3.99, recall of 87.14 ± 10.17 and Dice Index of 91.87 ± 6.51 for segmentation of ERBB2 overexpression on the two experimental datasets, respectively. Furthermore, the proposed deep learning framework outperforms 15 state-of-the-art benchmarked methods by a significant margin (P<0.05) with respect to IoU on both datasets.

Deep learning-based segmentation of prostatic urethra on computed tomography scans for treatment planning

Background and purpose

The intraprostatic urethra is an organ at risk in prostate cancer radiotherapy, but its segmentation in computed tomography (CT) is challenging. This work sought to: i) propose an automatic pipeline for intraprostatic urethra segmentation in CT, ii) analyze the dose to the urethra, iii) compare the predictions to magnetic resonance (MR) contours.

Materials and methods

First, we trained Deep Learning networks to segment the rectum, bladder, prostate, and seminal vesicles. Then, the proposed Deep Learning Urethra Segmentation model was trained with the bladder and prostate distance transforms and 44 labeled CT with visible catheters. The evaluation was performed on 11 datasets, calculating centerline distance (CLD) and percentage of centerline within 3.5 and 5 mm. We applied this method to a dataset of 32 patients treated with intensity-modulated radiation therapy (IMRT) to quantify the urethral dose. Finally, we compared predicted intraprostatic urethra contours to manual delineations in MR for 15 patients without catheter.

Results

A mean CLD of 1.6 ± 0.8 mm for the whole urethra and 1.7 ± 1.4, 1.5 ± 0.9, and 1.7 ± 0.9 mm for the top, middle, and bottom thirds were obtained in CT. On average, 94% and 97% of the segmented centerlines were within a 3.5 mm and 5 mm radius, respectively. In IMRT, the urethra received a higher dose than the overall prostate. We also found a slight deviation between the predicted and manual MR delineations.

Conclusion

A fully-automatic segmentation pipeline was validated to delineate the intraprostatic urethra in CT images.

BowelNet: Joint Semantic-Geometric Ensemble Learning for Bowel Segmentation From Both Partially and Fully Labeled CT Images

Accurate bowel segmentation is essential for diagnosis and treatment of bowel cancers. Unfortunately, segmenting the entire bowel in CT images is quite challenging due to unclear boundary, large shape, size, and appearance variations, as well as diverse filling status within the bowel. In this paper, we present a novel two-stage framework, named BowelNet, to handle the challenging task of bowel segmentation in CT images, with two stages of 1) jointly localizing all types of the bowel, and 2) finely segmenting each type of the bowel. Specifically, in the first stage, we learn a unified localization network from both partially- and fully-labeled CT images to robustly detect all types of the bowel. To better capture unclear bowel boundary and learn complex bowel shapes, in the second stage, we propose to jointly learn semantic information (i.e., bowel segmentation mask) and geometric representations (i.e., bowel boundary and bowel skeleton) for fine bowel segmentation in a multi-task learning scheme. Moreover, we further propose to learn a meta segmentation network via pseudo labels to improve segmentation accuracy. By evaluating on a large abdominal CT dataset, our proposed BowelNet method can achieve Dice scores of 0.764, 0.848, 0.835, 0.774, and 0.824 in segmenting the duodenum, jejunum-ileum, colon, sigmoid, and rectum, respectively. These results demonstrate the effectiveness of our proposed BowelNet framework in segmenting the entire bowel from CT images.

Dynamic Cross-Task Representation Adaptation for Clinical Targets Co-Segmentation in CT Image-Guided Post-Prostatectomy Radiotherapy

Adjuvant and salvage radiotherapy after radical prostatectomy requires precise delineations of prostate bed (PB), i.e., the clinical target volume, and surrounding organs at risk (OARs) to optimize radiotherapy planning. Segmenting PB is particularly challenging even for clinicians, e.g., from the planning computed tomography (CT) images, as it is an invisible/virtual target after the operative removal of the cancerous prostate gland. Very recently, a few deep learning-based methods have been proposed to automatically contour non-contrast PB by leveraging its spatial reliance on adjacent OARs (i.e., the bladder and rectum) with much more clear boundaries, mimicking the clinical workflow of experienced clinicians. Although achieving state-of-the-art results from both the clinical and technical aspects, these existing methods improperly ignore the gap between the hierarchical feature representations needed for segmenting those fundamentally different clinical targets (i.e., PB and OARs), which in turn limits their delineation accuracy. This paper proposes an asymmetric multi-task network integrating dynamic cross-task representation adaptation (i.e., DyAdapt) for accurate and efficient co-segmentation of PB and OARs in one-pass from CT images. In the learning-to-learn framework, the DyAdapt modules adaptively transfer the hierarchical feature representations from the source task of OARs segmentation to match up with the target (and more challenging) task of PB segmentation, conditioned on the dynamic inter-task associations learned from the learning states of the feed-forward path. On a real-patient dataset, our method led to state-of-the-art results of PB and OARs co-segmentation. Code is available at https://github.com/ladderlab-xjtu/DyAdapt.

A skeleton context-aware 3D fully convolutional network for abdominal artery segmentation

PURPOSE

This paper aims to propose a deep learning-based method for abdominal artery segmentation. Blood vessel structure information is essential to diagnosis and treatment. Accurate blood vessel segmentation is critical to preoperative planning. Although deep learning-based methods perform well on large organs, segmenting small organs such as blood vessels is challenging due to complicated branching structures and positions. We propose a 3D deep learning network from a skeleton context-aware perspective to improve segmentation accuracy. In addition, we propose a novel 3D patch generation method which could strengthen the structural diversity of a training data set.

METHOD

The proposed method segments abdominal arteries from an abdominal computed tomography (CT) volume using a 3D fully convolutional network (FCN). We add two auxiliary tasks to the network to extract the skeleton context of abdominal arteries. In addition, our skeleton-based patch generation (SBPG) method further enables the FCN to segment small arteries. SBPG generates a 3D patch from a CT volume by leveraging artery skeleton information. These methods improve the segmentation accuracies of small arteries.

RESULTS

We used 20 cases of abdominal CT volumes to evaluate the proposed method. The experimental results showed that our method outperformed previous segmentation accuracies. The averaged precision rate, recall rate, and F-measure were 95.5%, 91.0%, and 93.2%, respectively. Compared to a baseline method, our method improved 1.5% the averaged recall rate and 0.7% the averaged F-measure.

CONCLUSIONS

We present a skeleton context-aware 3D FCN to segment abdominal arteries from an abdominal CT volume. In addition, we propose a 3D patch generation method. Our fully automated method segmented most of the abdominal artery regions. The method produced competitive segmentation performance compared to previous methods.

Multi-task deep learning for medical image computing and analysis: A review

The renaissance of deep learning has provided promising solutions to various tasks. While conventional deep learning models are constructed for a single specific task, multi-task deep learning (MTDL) that is capable to simultaneously accomplish at least two tasks has attracted research attention. MTDL is a joint learning paradigm that harnesses the inherent correlation of multiple related tasks to achieve reciprocal benefits in improving performance, enhancing generalizability, and reducing the overall computational cost. This review focuses on the advanced applications of MTDL for medical image computing and analysis. We first summarize four popular MTDL network architectures (i.e., cascaded, parallel, interacted, and hybrid). Then, we review the representative MTDL-based networks for eight application areas, including the brain, eye, chest, cardiac, abdomen, musculoskeletal, pathology, and other human body regions. While MTDL-based medical image processing has been flourishing and demonstrating outstanding performance in many tasks, in the meanwhile, there are performance gaps in some tasks, and accordingly we perceive the open challenges and the perspective trends. For instance, in the 2018 Ischemic Stroke Lesion Segmentation challenge, the reported top dice score of 0.51 and top recall of 0.55 achieved by the cascaded MTDL model indicate further research efforts in high demand to escalate the performance of current models.

Boundary-Sensitive Loss Function With Location Constraint for Hard Region Segmentation

In computer-aided diagnosis and treatment planning, accurate segmentation of medical images plays an essential role, especially for some hard regions including boundaries, small objects and background interference. However, existing segmentation loss functions including distribution-, region- and boundary-based losses cannot achieve satisfactory performances on these hard regions. In this paper, a boundary-sensitive loss function with location constraint is proposed for hard region segmentation in medical images, which provides three advantages: i) our Boundary-Sensitive loss (BS-loss) can automatically pay more attention to the hard-to-segment boundaries (e.g., thin structures and blurred boundaries), thus obtaining finer object boundaries; ii) BS-loss also can adjust its attention to small objects during training to segment them more accurately; and iii) our location constraint can alleviate the negative impact of the background interference, through the distribution matching of pixels between prediction and Ground Truth (GT) along each axis. By resorting to the proposed BS-loss and location constraint, the hard regions in both foreground and background are considered. Experimental results on three public datasets demonstrate the superiority of our method. Specifically, compared to the second-best method tested in this study, our method improves performance on hard regions in terms of Dice similarity coefficient (DSC) and 95% Hausdorff distance (95%HD) of up to 4.17% and 73% respectively. In addition, it also achieves the best overall segmentation performance. Hence, we can conclude that our method can accurately segment these hard regions and improve the overall segmentation performance in medical images.

An uncertainty-aware deep learning architecture with outlier mitigation for prostate gland segmentation in radiotherapy treatment planning

PURPOSE

Task automation is essential for efficient and consistent image segmentation in radiation oncology. We report on a deep learning architecture, comprising a U-Net and a variational autoencoder (VAE) for automatic contouring of the prostate gland incorporating interobserver variation for radiotherapy treatment planning. The U-Net/VAE generates an ensemble set of segmentations for each image CT slice. A novel outlier mitigation (OM) technique was implemented to enhance the model segmentation accuracy.

METHODS

The primary source dataset (source_prim) consisted of 19 200 CT slices (from 300 patient planning CT image datasets) with manually contoured prostate glands. A smaller secondary source dataset (source_sec) comprised 640 CT slices (from 10 patient CT datasets), where prostate glands were segmented by 5 independent physicians on each dataset to account for interobserver variability. Data augmentation via random rotation (<5 degrees), cropping, and horizontal flipping was applied to each dataset to increase sample size by a factor of 100. A probabilistic hierarchical U-Net with VAE was implemented and pretrained using the augmented source_prim dataset for 30 epochs. Model parameters of the U-Net/VAE were fine-tuned using the augmented source_sec dataset for 100 epochs. After the first round of training, outlier contours in the training dataset were automatically detected and replaced by the most accurate contours (based on Dice similarity coefficient, DSC) generated by the model. The U-Net/OM-VAE was retrained using the revised training dataset. Metrics for comparison included DSC, Hausdorff distance (HD, mm), normalized cross-correlation (NCC) coefficient, and center-of-mass (COM) distance (mm).

RESULTS

Results for U-Net/OM-VAE with outliers replaced in the training dataset versus U-Net/VAE without OM were as follows: DSC = 0.82 ± 0.01 versus 0.80 ± 0.02 (p = 0.019), HD = 9.18 ± 1.22 versus 10.18 ± 1.35 mm (p = 0.043), NCC = 0.59 ± 0.07 versus 0.62 ± 0.06, and COM = 3.36 ± 0.81 versus 4.77 ± 0.96 mm over the average of 15 contours. For the average of 15 highest accuracy contours, values were as follows: DSC = 0.90 ± 0.02 versus 0.85 ± 0.02, HD = 5.47 ± 0.02 versus 7.54 ± 1.36 mm, and COM = 1.03 ± 0.58 versus 1.46 ± 0.68 mm (p < 0.03 for all metrics). Results for the U-Net/OM-VAE with outliers removed were as follows: DSC = 0.78 ± 0.01, HD = 10.65 ± 1.95 mm, NCC = 0.46 ± 0.10, COM = 4.17 ± 0.79 mm for the average of 15 contours, and DSC = 0.88 ± 0.02, HD = 7.00 ± 1.17 mm, COM = 1.58 ± 0.63 mm for the average of 15 highest accuracy contours. All metrics for U-Net/VAE trained on the source_prim and source_sec datasets via pretraining, followed by fine-tuning, show statistically significant improvement over that trained on the source_sec dataset only. Finally, all metrics for U-Net/VAE with or without OM showed statistically significant improvement over those for the standard U-Net.

CONCLUSIONS

A VAE combined with a hierarchical U-Net and an OM strategy (U-Net/OM-VAE) demonstrates promise toward capturing interobserver variability and produces accurate prostate auto-contours for radiotherapy planning. The availability of multiple contours for each CT slice enables clinicians to determine trade-offs in selecting the "best fitting" contour on each CT slice. Mitigation of outlier contours in the training dataset improves prediction accuracy, but one must be wary of reduction in variability in the training dataset.

Automatic Plane of Minimal Hiatal Dimensions Extraction From 3D Female Pelvic Floor Ultrasound

There is an increasing interest in the applications of 3D ultrasound imaging of the pelvic floor to improve the diagnosis, treatment, and surgical planning of female pelvic floor dysfunction (PFD). Pelvic floor biometrics are obtained on an oblique image plane known as the plane of minimal hiatal dimensions (PMHD). Identifying this plane requires the detection of two anatomical landmarks, the pubic symphysis and anorectal angle. The manual detection of the anatomical landmarks and the PMHD in 3D pelvic ultrasound requires expert knowledge of the pelvic floor anatomy, and is challenging, time-consuming, and subject to human error. These challenges have hindered the adoption of such quantitative analysis in the clinic. This work presents an automatic approach to identify the anatomical landmarks and extract the PMHD from 3D pelvic ultrasound volumes. To demonstrate clinical utility and a complete automated clinical task, an automatic segmentation of the levator-ani muscle on the extracted PMHD images was also performed. Experiments using 73 test images of patients during a pelvic muscle resting state showed that this algorithm has the capability to accurately identify the PMHD with an average Dice of 0.89 and an average mean boundary distance of 2.25mm. Further evaluation of the PMHD detection algorithm using 35 images of patients performing pelvic muscle contraction resulted in an average Dice of 0.88 and an average mean boundary distance of 2.75mm. This work had the potential to pave the way towards the adoption of ultrasound in the clinic and development of personalized treatment for PFD.

Deep learning empowered volume delineation of whole-body organs-at-risk for accelerated radiotherapy

In radiotherapy for cancer patients, an indispensable process is to delineate organs-at-risk (OARs) and tumors. However, it is the most time-consuming step as manual delineation is always required from radiation oncologists. Herein, we propose a lightweight deep learning framework for radiotherapy treatment planning (RTP), named RTP-Net, to promote an automatic, rapid, and precise initialization of whole-body OARs and tumors. Briefly, the framework implements a cascade coarse-to-fine segmentation, with adaptive module for both small and large organs, and attention mechanisms for organs and boundaries. Our experiments show three merits: 1) Extensively evaluates on 67 delineation tasks on a large-scale dataset of 28,581 cases; 2) Demonstrates comparable or superior accuracy with an average Dice of 0.95; 3) Achieves near real-time delineation in most tasks with <2 s. This framework could be utilized to accelerate the contouring process in the All-in-One radiotherapy scheme, and thus greatly shorten the turnaround time of patients.

Grayscale self-adjusting network with weak feature enhancement for 3D lumbar anatomy segmentation

The automatic segmentation of lumbar anatomy is a fundamental problem for the diagnosis and treatment of lumbar disease. The recent development of deep learning techniques has led to remarkable progress in this task, including the possible segmentation of nerve roots, intervertebral discs, and dural sac in a single step. Despite these advances, lumbar anatomy segmentation remains a challenging problem due to the weak contrast and noise of input images, as well as the variability of intensities and size in lumbar structures across different subjects. To overcome these challenges, we propose a coarse-to-fine deep neural network framework for lumbar anatomy segmentation, which obtains a more accurate segmentation using two strategies. First, a progressive refinement process is employed to correct low-confidence regions by enhancing the feature representation in these regions. Second, a grayscale self-adjusting network (GSA-Net) is proposed to optimize the distribution of intensities dynamically. Experiments on datasets comprised of 3D computed tomography (CT) and magnetic resonance (MR) images show the advantage of our method over current segmentation approaches and its potential for diagnosing and lumbar disease treatment.

Can Generative Adversarial Networks help to overcome the limited data problem in segmentation?

PURPOSE

For image translational tasks, the application of deep learning methods showed that Generative Adversarial Network (GAN) architectures outperform the traditional U-Net networks, when using the same training data size. This study investigates whether this performance boost can also be expected for segmentation tasks with small training dataset size.

MATERIALS/METHODS

Two models were trained on varying training dataset sizes ranging from 1-100 patients: a) U-Net and b) U-Net with patch discriminator (conditional GAN). The performance of both models to segment the male pelvis on CT-data was evaluated (Dice similarity coefficient, Hausdorff) with respect to training data size.

RESULTS

No significant differences were observed between the U-Net and cGAN when the models were trained with the same training sizes up to 100 patients. The training dataset size had a significant impact on the models' performances, with vast improvements when increasing dataset sizes from 1 to 20 patients.

CONCLUSION

When introducing GANs for the segmentation task no significant performance boost was observed in our experiments, even in segmentation models developed on small datasets.

Shadow-Consistent Semi-Supervised Learning for Prostate Ultrasound Segmentation

Prostate segmentation in transrectal ultrasound (TRUS) image is an essential prerequisite for many prostate-related clinical procedures, which, however, is also a long-standing problem due to the challenges caused by the low image quality and shadow artifacts. In this paper, we propose a Shadow-consistent Semi-supervised Learning (SCO-SSL) method with two novel mechanisms, namely shadow augmentation (Shadow-AUG) and shadow dropout (Shadow-DROP), to tackle this challenging problem. Specifically, Shadow-AUG enriches training samples by adding simulated shadow artifacts to the images to make the network robust to the shadow patterns. Shadow-DROP enforces the segmentation network to infer the prostate boundary using the neighboring shadow-free pixels. Extensive experiments are conducted on two large clinical datasets (a public dataset containing 1,761 TRUS volumes and an in-house dataset containing 662 TRUS volumes). In the fully-supervised setting, a vanilla U-Net equipped with our Shadow-AUG&Shadow-DROP outperforms the state-of-the-arts with statistical significance. In the semi-supervised setting, even with only 20% labeled training data, our SCO-SSL method still achieves highly competitive performance, suggesting great clinical value in relieving the labor of data annotation. Source code is released at https://github.com/DIAL-RPI/SCO-SSL.

Automatic segmentation of high-risk clinical target volume for tandem-and-ovoids brachytherapy patients using an asymmetric dual-path convolutional neural network

PURPOSES

Preimplant diagnostic magnetic resonance imaging is the gold standard for image-guided tandem-and-ovoids (T&O) brachytherapy for cervical cancer. However, high dose rate brachytherapy planning is typically done on postimplant CT-based high-risk clinical target volume (HR-CTVCT ) because the transfer of preimplant Magnetic resonance (MR)-based HR-CTV (HR-CTVMR ) to the postimplant planning CT is difficult due to anatomical changes caused by applicator insertion, vaginal packing, and the filling status of the bladder and rectum. This study aims to train a dual-path convolutional neural network (CNN) for automatic segmentation of HR-CTVCT on postimplant planning CT with guidance from preimplant diagnostic MR.

METHODS

Preimplant T2-weighted MR and postimplant CT images for 65 (48 for training, eight for validation, and nine for testing) patients were retrospectively solicited from our institutional database. MR was aligned to the corresponding CT using rigid registration. HR-CTVCT and HR-CTVMR were manually contoured on CT and MR by an experienced radiation oncologist. All images were then resampled to a spatial resolution of 0.5 × 0.5 × 1.25 mm. A dual-path 3D asymmetric CNN architecture with two encoding paths was built to extract CT and MR image features. The MR was masked by HR-CTVMR contour while the entire CT volume was included. The network put an asymmetric weighting of 18:6 for CT: MR. Voxel-based dice similarity coefficient (DSCV ), sensitivity, precision, and 95% Hausdorff distance (95-HD) were used to evaluate model performance. Cross-validation was performed to assess model stability. The study cohort was divided into a small tumor group (<20 cc), medium tumor group (20-40 cc), and large tumor group (>40 cc) based on the HR-CTVCT for model evaluation. Single-path CNN models were trained with the same parameters as those in dual-path models.

RESULTS

For this patient cohort, the dual-path CNN model improved each of our objective findings, including DSCV , sensitivity, and precision, with an average improvement of 8%, 7%, and 12%, respectively. The 95-HD was improved by an average of 1.65 mm compared to the single-path model with only CT images as input. In addition, the area under the curve for different networks was 0.86 (dual-path with CT and MR) and 0.80 (single-path with CT), respectively. The dual-path CNN model with asymmetric weighting achieved the best performance with DSCV of 0.65 ± 0.03 (0.61-0.70), 0.79 ± 0.02 (0.74-0.85), and 0.75 ± 0.04 (0.68-0.79) for small, medium, and large group. 95-HD were 7.34 (5.35-10.45) mm, 5.48 (3.21-8.43) mm, and 6.21 (5.34-9.32) mm for the three size groups, respectively.

CONCLUSIONS

An asymmetric CNN model with two encoding paths from preimplant MR (masked by HR-CTVMR ) and postimplant CT images was successfully developed for automatic segmentation of HR-CTVCT for T&O brachytherapy patients.

Dosimetric impact of deep learning-based CT auto-segmentation on radiation therapy treatment planning for prostate cancer

Background

The 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.

Methods

A 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.

Results

3D 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\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$_{60/65/70\,{\mathrm{Gy}}}$$\end{document}60/65/70Gy for the bladder and V\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$_{50/65/70\,{\mathrm{Gy}}}$$\end{document}50/65/70Gy for the rectum, showed agreement between dose distributions within \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\pm \, 5\%$$\end{document}±5% and \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\pm \,2\%$$\end{document}±2%, respectively. The D\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$_{98/2\%}$$\end{document}98/2% and V\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$_{95\%}$$\end{document}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.

Conclusions

The 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.

SOMA: Subject-, object-, and modality-adapted precision atlas approach for automatic anatomy recognition and delineation in medical images

PURPOSE

In the multi-atlas segmentation (MAS) method, a large enough atlas set, which can cover the complete spectrum of the whole population pattern of the target object will benefit the segmentation quality. However, the difficulty in obtaining and generating such a large set of atlases and the computational burden required in the segmentation procedure make this approach impractical. In this paper, we propose a method called SOMA to select subject-, object-, and modality-adapted precision atlases for automatic anatomy recognition in medical images with pathology, following the idea that different regions of the target object in a novel image can be recognized by different atlases with regionally best similarity, so that effective atlases have no need to be globally similar to the target subject and also have no need to be overall similar to the target object.

METHODS

The SOMA method consists of three main components: atlas building, object recognition, and object delineation. Considering the computational complexity, we utilize an all-to-template strategy to align all images to the same image space belonging to the root image determined by the minimum spanning tree (MST) strategy among a subset of radiologically near-normal images. The object recognition process is composed of two stages: rough recognition and refined recognition. In rough recognition, subimage matching is conducted between the test image and each image of the whole atlas set, and only the atlas corresponding to the best-matched subimage contributes to the recognition map regionally. The frequency of best match for each atlas is recorded by a counter, and the atlases with the highest frequencies are selected as the precision atlases. In refined recognition, only the precision atlases are examined, and the subimage matching is conducted in a nonlocal manner of searching to further increase the accuracy of boundary matching. Delineation is based on a U-net-based deep learning network, where the original gray scale image together with the fuzzy map from refined recognition compose a two-channel input to the network, and the output is a segmentation map of the target object.

RESULTS

Experiments are conducted on computed tomography (CT) images with different qualities in two body regions - head and neck (H&N) and thorax, from 298 subjects with nine objects and 241 subjects with six objects, respectively. Most objects achieve a localization error within two voxels after refined recognition, with marked improvement in localization accuracy from rough to refined recognition of 0.6-3 mm in H&N and 0.8-4.9 mm in thorax, and also in delineation accuracy (Dice coefficient) from refined recognition to delineation of 0.01-0.11 in H&N and 0.01-0.18 in thorax.

CONCLUSIONS

The SOMA method shows high accuracy and robustness in anatomy recognition and delineation. The improvements from rough to refined recognition and further to delineation, as well as immunity of recognition accuracy to varying image and object qualities, demonstrate the core principles of SOMA where segmentation accuracy increases with precision atlases and gradually refined object matching.

Synthetic CT-aided multiorgan segmentation for CBCT-guided adaptive pancreatic radiotherapy

PURPOSE

The delineation of organs at risk (OARs) is fundamental to cone-beam CT (CBCT)-based adaptive radiotherapy treatment planning, but is time consuming, labor intensive, and subject to interoperator variability. We investigated a deep learning-based rapid multiorgan delineation method for use in CBCT-guided adaptive pancreatic radiotherapy.

METHODS

To improve the accuracy of OAR delineation, two innovative solutions have been proposed in this study. First, instead of directly segmenting organs on CBCT images, a pretrained cycle-consistent generative adversarial network (cycleGAN) was applied to generating synthetic CT images given CBCT images. Second, an advanced deep learning model called mask-scoring regional convolutional neural network (MS R-CNN) was applied on those synthetic CT to detect the positions and shapes of multiple organs simultaneously for final segmentation. The OAR contours delineated by the proposed method were validated and compared with expert-drawn contours for geometric agreement using the Dice similarity coefficient (DSC), 95th percentile Hausdorff distance (HD95), mean surface distance (MSD), and residual mean square distance (RMS).

RESULTS

Across eight abdominal OARs including duodenum, large bowel, small bowel, left and right kidneys, liver, spinal cord, and stomach, the geometric comparisons between automated and expert contours are as follows: 0.92 (0.89-0.97) mean DSC, 2.90 mm (1.63-4.19 mm) mean HD95, 0.89 mm (0.61-1.36 mm) mean MSD, and 1.43 mm (0.90-2.10 mm) mean RMS. Compared to the competing methods, our proposed method had significant improvements (p < 0.05) in all the metrics for all the eight organs. Once the model was trained, the contours of eight OARs can be obtained on the order of seconds.

CONCLUSIONS

We demonstrated the feasibility of a synthetic CT-aided deep learning framework for automated delineation of multiple OARs on CBCT. The proposed method could be implemented in the setting of pancreatic adaptive radiotherapy to rapidly contour OARs with high accuracy.

Automatic Segmentation of Pelvic Cancers Using Deep Learning: State-of-the-Art Approaches and Challenges

The recent rise of deep learning (DL) and its promising capabilities in capturing non-explicit detail from large datasets have attracted substantial research attention in the field of medical image processing. DL provides grounds for technological development of computer-aided diagnosis and segmentation in radiology and radiation oncology. Amongst the anatomical locations where recent auto-segmentation algorithms have been employed, the pelvis remains one of the most challenging due to large intra- and inter-patient soft-tissue variabilities. This review provides a comprehensive, non-systematic and clinically-oriented overview of 74 DL-based segmentation studies, published between January 2016 and December 2020, for bladder, prostate, cervical and rectal cancers on computed tomography (CT) and magnetic resonance imaging (MRI), highlighting the key findings, challenges and limitations.

Automated delineation of head and neck organs at risk using synthetic MRI-aided mask scoring regional convolutional neural network

PURPOSE

Auto-segmentation algorithms offer a potential solution to eliminate the labor-intensive, time-consuming, and observer-dependent manual delineation of organs-at-risk (OARs) in radiotherapy treatment planning. This study aimed to develop a deep learning-based automated OAR delineation method to tackle the current challenges remaining in achieving reliable expert performance with the state-of-the-art auto-delineation algorithms.

METHODS

The accuracy of OAR delineation is expected to be improved by utilizing the complementary contrasts provided by computed tomography (CT) (bony-structure contrast) and magnetic resonance imaging (MRI) (soft-tissue contrast). Given CT images, synthetic MR images were firstly generated by a pre-trained cycle-consistent generative adversarial network. The features of CT and synthetic MRI were then extracted and combined for the final delineation of organs using mask scoring regional convolutional neural network. Both in-house and public datasets containing CT scans from head-and-neck (HN) cancer patients were adopted to quantitatively evaluate the performance of the proposed method against current state-of-the-art algorithms in metrics including Dice similarity coefficient (DSC), 95th percentile Hausdorff distance (HD95), mean surface distance (MSD), and residual mean square distance (RMS).

RESULTS

Across all of 18 OARs in our in-house dataset, the proposed method achieved an average DSC, HD95, MSD, and RMS of 0.77 (0.58-0.90), 2.90 mm (1.32-7.63 mm), 0.89 mm (0.42-1.85 mm), and 1.44 mm (0.71-3.15 mm), respectively, outperforming the current state-of-the-art algorithms by 6%, 16%, 25%, and 36%, respectively. On public datasets, for all nine OARs, an average DSC of 0.86 (0.73-0.97) were achieved, 6% better than the competing methods.

CONCLUSION

We demonstrated the feasibility of a synthetic MRI-aided deep learning framework for automated delineation of OARs in HN radiotherapy treatment planning. The proposed method could be adopted into routine HN cancer radiotherapy treatment planning to rapidly contour OARs with high accuracy.

An optimized two-stage cascaded deep neural network for adrenal segmentation on CT images

Segmentation of adrenal glands from CT images is a crucial step in the AI-assisted diagnosis of adrenal gland-related disease. However, highly intrasubject variability in shape and adhesive boundaries with surrounding tissues make accurate segmentation of the adrenal gland a challenging task. In the current study, we proposed a novel two-stage deep neural network for adrenal gland segmentation in an end-to-end fashion. In the first stage, a localization network that aims to determine the candidate volume of the target organ was used in the preprocessing step to reduce class imbalance and computational burden. Then, in the second stage, a Small-organNet model trained with a novel boundary attention focal loss was designed to refine the boundary of the organ within the screened volume. The experimental results show that our proposed cascaded framework outperforms the state-of-the-art deep learning method in segmenting the adrenal gland with respect to accuracy; it requires fewer trainable parameters and imposes a smaller demand on computational resources.

Scale- and Slice-aware Net (S2 aNet) for 3D segmentation of organs and musculoskeletal structures in pelvic MRI

PURPOSE

MRI of organs and musculoskeletal structures in the female pelvis presents a unique display of pelvic anatomy. Automated segmentation of pelvic structures plays an important role in personalized diagnosis and treatment on pelvic structures disease. Pelvic organ systems are very complicated, and it is a challenging task for 3D segmentation of massive pelvic structures on MRI.

METHODS

A new Scale- and Slice-aware Net ( S 2 aNet) is presented for 3D dense segmentation of 54 organs and musculoskeletal structures in female pelvic MR images. A Scale-aware module is designed to capture the spatial and semantic information of different-scale structures. A Slice-aware module is introduced to model similar spatial relationships of consecutive slices in 3D data. Moreover, S 2 aNet leverages a weight-adaptive loss optimization strategy to reinforce the supervision with more discriminative capability on hard samples and categories.

RESULTS

Experiments have been performed on a pelvic MRI cohort of 27 MR images from 27 patient cases. Across the cohort and 54 categories of organs and musculoskeletal structures manually delineated, S 2 aNet was shown to outperform the UNet framework and other state-of-the-art fully convolutional networks in terms of sensitivity, Dice similarity coefficient and relative volume difference.

CONCLUSION

The experimental results on the pelvic 3D MR dataset show that the proposed S 2 aNet achieves excellent segmentation results compared to other state-of-the-art models. To our knowledge, S 2 aNet is the first model to achieve 3D dense segmentation for 54 musculoskeletal structures on pelvic MRI, which will be leveraged to the clinical application under the support of more cases in the future.

Development of in-house fully residual deep convolutional neural network-based segmentation software for the male pelvic CT

BACKGROUND

This study aimed to (1) develop a fully residual deep convolutional neural network (CNN)-based segmentation software for computed tomography image segmentation of the male pelvic region and (2) demonstrate its efficiency in the male pelvic region.

METHODS

A total of 470 prostate cancer patients who had undergone intensity-modulated radiotherapy or volumetric-modulated arc therapy were enrolled. Our model was based on FusionNet, a fully residual deep CNN developed to semantically segment biological images. To develop the CNN-based segmentation software, 450 patients were randomly selected and separated into the training, validation and testing groups (270, 90, and 90 patients, respectively). In Experiment 1, to determine the optimal model, we first assessed the segmentation accuracy according to the size of the training dataset (90, 180, and 270 patients). In Experiment 2, the effect of varying the number of training labels on segmentation accuracy was evaluated. After determining the optimal model, in Experiment 3, the developed software was used on the remaining 20 datasets to assess the segmentation accuracy. The volumetric dice similarity coefficient (DSC) and the 95th-percentile Hausdorff distance (95%HD) were calculated to evaluate the segmentation accuracy for each organ in Experiment 3.

RESULTS

In Experiment 1, the median DSC for the prostate were 0.61 for dataset 1 (90 patients), 0.86 for dataset 2 (180 patients), and 0.86 for dataset 3 (270 patients), respectively. The median DSCs for all the organs increased significantly when the number of training cases increased from 90 to 180 but did not improve upon further increase from 180 to 270. The number of labels applied during training had a little effect on the DSCs in Experiment 2. The optimal model was built by 270 patients and four organs. In Experiment 3, the median of the DSC and the 95%HD values were 0.82 and 3.23 mm for prostate; 0.71 and 3.82 mm for seminal vesicles; 0.89 and 2.65 mm for the rectum; 0.95 and 4.18 mm for the bladder, respectively.

CONCLUSIONS

We have developed a CNN-based segmentation software for the male pelvic region and demonstrated that the CNN-based segmentation software is efficient for the male pelvic region.

Effects of sample size and data augmentation on U-Net-based automatic segmentation of various organs

Deep learning has demonstrated high efficacy for automatic segmentation in contour delineation, which is crucial in radiation therapy planning. However, the collection, labeling, and management of medical imaging data can be challenging. This study aims to elucidate the effects of sample size and data augmentation on the automatic segmentation of computed tomography images using U-Net, a deep learning method. For the chest and pelvic regions, 232 and 556 cases are evaluated, respectively. We investigate multiple conditions by changing the sum of the training and validation datasets across a broad range of values: 10-200 and 10-500 cases for the chest and pelvic regions, respectively. A U-Net is constructed, and horizontal-flip data augmentation, which produces left and right inverse images resulting in twice the number of images, is compared with no augmentation for each training session. All lung cases and more than 100 prostate, bladder, and rectum cases indicate that adding horizontal-flip data augmentation is almost as effective as doubling the number of cases. The slope of the Dice similarity coefficient (DSC) in all organs decreases rapidly until approximately 100 cases, stabilizes after 200 cases, and shows minimal changes as the number of cases is increased further. The DSCs stabilize at a smaller sample size with the incorporation of data augmentation in all organs except the heart. This finding is applicable to the automation of radiation therapy for rare cancers, where large datasets may be difficult to obtain.

Joint Landmark and Structure Learning for Automatic Evaluation of Developmental Dysplasia of the Hip

The ultrasound (US) screening of the infant hip is vital for early diagnosis of developmental dysplasia of the hip (DDH). The US diagnosis of DDH refers to measuring alpha and beta angles that quantify hip joint development. These two angles are calculated from key anatomical landmarks and structures of the hip. However, this measurement process is not trivial for sonographers and usually requires a thorough understanding of complex anatomical structures. In this study, we propose a multi-task framework to learn the relationships among landmarks and structures jointly and automatically evaluate DDH. Our multi-task networks are equipped with three novel modules. Firstly, we adopt Mask R-CNN as the basic framework to detect and segment key anatomical structures and add one landmark detection branch to form a new multi-task framework. Secondly, we propose a novel shape similarity loss to refine the incomplete anatomical structure prediction robustly and accurately. Thirdly, we further incorporate the landmark-structure consistent prior to ensure the consistency of the bony rim estimated from the segmented structure and the detected landmark. In our experiments, 1,231 US images of the infant hip from 632 patients are collected, of which 247 images from 126 patients are tested. The average errors in alpha and beta angles are 2.221 and 2.899. About 93% and 85% estimates of alpha and beta angles have errors less than 5 degrees, respectively. Experimental results demonstrate that the proposed method can accurately and robustly realize the automatic evaluation of DDH, showing great potential for clinical application.

Asymmetric multi-task attention network for prostate bed segmentation in computed tomography images

Post-prostatectomy radiotherapy requires accurate annotation of the prostate bed (PB), i.e., the residual tissue after the operative removal of the prostate gland, to minimize side effects on surrounding organs-at-risk (OARs). However, PB segmentation in computed tomography (CT) images is a challenging task, even for experienced physicians. This is because PB is almost a "virtual" target with non-contrast boundaries and highly variable shapes depending on neighboring OARs. In this work, we propose an asymmetric multi-task attention network (AMTA-Net) for the concurrent segmentation of PB and surrounding OARs. Our AMTA-Net mimics experts in delineating the non-contrast PB by explicitly leveraging its critical dependency on the neighboring OARs (i.e., the bladder and rectum), which are relatively easy to distinguish in CT images. Specifically, we first adopt a U-Net as the backbone network for the low-level (or prerequisite) task of the OAR segmentation. Then, we build an attention sub-network upon the backbone U-Net with a series of cascaded attention modules, which can hierarchically transfer the OAR features and adaptively learn discriminative representations for the high-level (or primary) task of the PB segmentation. We comprehensively evaluate the proposed AMTA-Net on a clinical dataset composed of 186 CT images. According to the experimental results, our AMTA-Net significantly outperforms current clinical state-of-the-arts (i.e., atlas-based segmentation methods), indicating the value of our method in reducing time and labor in the clinical workflow. Our AMTA-Net also presents better performance than the technical state-of-the-arts (i.e., the deep learning-based segmentation methods), especially for the most indistinguishable and clinically critical part of the PB boundaries. Source code is released at https://github.com/superxuang/amta-net.

A review of deep learning based methods for medical image multi-organ segmentation

Deep learning has revolutionized image processing and achieved the-state-of-art performance in many medical image segmentation tasks. Many deep learning-based methods have been published to segment different parts of the body for different medical applications. It is necessary to summarize the current state of development for deep learning in the field of medical image segmentation. In this paper, we aim to provide a comprehensive review with a focus on multi-organ image segmentation, which is crucial for radiotherapy where the tumor and organs-at-risk need to be contoured for treatment planning. We grouped the surveyed methods into two broad categories which are 'pixel-wise classification' and 'end-to-end segmentation'. Each category was divided into subgroups according to their network design. For each type, we listed the surveyed works, highlighted important contributions and identified specific challenges. Following the detailed review, we discussed the achievements, shortcomings and future potentials of each category. To enable direct comparison, we listed the performance of the surveyed works that used thoracic and head-and-neck benchmark datasets.

Segmentation evaluation with sparse ground truth data: Simulating true segmentations as perfect/imperfect as those generated by humans

Fully annotated data sets play important roles in medical image segmentation and evaluation. Expense and imprecision are the two main issues in generating ground truth (GT) segmentations. In this paper, in an attempt to overcome these two issues jointly, we propose a method, named SparseGT, which exploit variability among human segmenters to maximally save manual workload in GT generation for evaluating actual segmentations by algorithms. Pseudo ground truth (p-GT) segmentations are created by only a small fraction of workload and with human-level perfection/imperfection, and they can be used in practice as a substitute for fully manual GT in evaluating segmentation algorithms at the same precision. p-GT segmentations are generated by first selecting slices sparsely, where manual contouring is conducted only on these sparse slices, and subsequently filling segmentations on other slices automatically. By creating p-GT with different levels of sparseness, we determine the largest workload reduction achievable for each considered object, where the variability of the generated p-GT is statistically indistinguishable from inter-segmenter differences in full manual GT segmentations for that object. Furthermore, we investigate the segmentation evaluation errors introduced by variability in manual GT by applying p-GT in evaluation of actual segmentations by an algorithm. Experiments are conducted on ∼500 computed tomography (CT) studies involving six objects in two body regions, Head & Neck and Thorax, where optimal sparseness and corresponding evaluation errors are determined for each object and each strategy. Our results indicate that creating p-GT by the concatenated strategy of uniformly selecting sparse slices and filling segmentations via deep-learning (DL) network show highest manual workload reduction by ∼80-96% without sacrificing evaluation accuracy compared to fully manual GT. Nevertheless, other strategies also have obvious contributions in different situations. A non-uniform strategy for slice selection shows its advantage for objects with irregular shape change from slice to slice. An interpolation strategy for filling segmentations can achieve ∼60-90% of workload reduction in simulating human-level GT without the need of an actual training stage and shows potential in enlarging data sets for training p-GT generation networks. We conclude that not only over 90% reduction in workload is feasible without sacrificing evaluation accuracy but also the suitable strategy and the optimal sparseness level achievable for creating p-GT are object- and application-specific.

Multi-Scale Context-Guided Deep Network for Automated Lesion Segmentation With Endoscopy Images of Gastrointestinal Tract

Accurate lesion segmentation based on endoscopy images is a fundamental task for the automated diagnosis of gastrointestinal tract (GI Tract) diseases. Previous studies usually use hand-crafted features for representing endoscopy images, while feature definition and lesion segmentation are treated as two standalone tasks. Due to the possible heterogeneity between features and segmentation models, these methods often result in sub-optimal performance. Several fully convolutional networks have been recently developed to jointly perform feature learning and model training for GI Tract disease diagnosis. However, they generally ignore local spatial details of endoscopy images, as down-sampling operations (e.g., pooling and convolutional striding) may result in irreversible loss of image spatial information. To this end, we propose a multi-scale context-guided deep network (MCNet) for end-to-end lesion segmentation of endoscopy images in GI Tract, where both global and local contexts are captured as guidance for model training. Specifically, one global subnetwork is designed to extract the global structure and high-level semantic context of each input image. Then we further design two cascaded local subnetworks based on output feature maps of the global subnetwork, aiming to capture both local appearance information and relatively high-level semantic information in a multi-scale manner. Those feature maps learned by three subnetworks are further fused for the subsequent task of lesion segmentation. We have evaluated the proposed MCNet on 1,310 endoscopy images from the public EndoVis-Ab and CVC-ClinicDB datasets for abnormal segmentation and polyp segmentation, respectively. Experimental results demonstrate that MCNet achieves [Formula: see text] and [Formula: see text] mean intersection over union (mIoU) on two datasets, respectively, outperforming several state-of-the-art approaches in automated lesion segmentation with endoscopy images of GI Tract.

End-To-End Computerized Diagnosis of Spondylolisthesis Using Only Lumbar X-rays

Lumbar spondylolisthesis (LS) is the anterior shift of one of the lower vertebrae about the subjacent vertebrae. There are several symptoms to define LS, and these symptoms are not detected in the early stages of LS. This leads to disease progress further without being identified. Thus, advanced treatment mechanisms are required to implement for diagnosing LS, which is crucial in terms of early diagnosis, rehabilitation, and treatment planning. Herein, a transfer learning-based CNN model is developed that uses only lumbar X-rays. The model was trained with 1922 images, and 187 images were used for validation. Later, the model was tested with 598 images. During training, the model extracts the region of interests (ROIs) via Yolov3, and then the ROIs are split into training and validation sets. Later, the ROIs are fed into the fine-tuned MobileNet CNN to accomplish the training. However, during testing, the images enter the model, and then they are classified as spondylolisthesis or normal. The end-to-end transfer learning-based CNN model reached the test accuracy of 99%, whereas the test sensitivity was 98% and the test specificity 99%. The performance results are encouraging and state that the model can be used in outpatient clinics where any experts are not present.

Multi-task edge-recalibrated network for male pelvic multi-organ segmentation on CT images

Automated male pelvic multi-organ segmentation on CT images is highly desired for applications, including radiotherapy planning. To further improve the performance and efficiency of existing automated segmentation methods, in this study, we propose a multi-task edge-recalibrated network (MTER-Net), which aims to overcome the challenges, including blurry boundaries, large inter-patient appearance variations, and low soft-tissue contrast. The proposed MTER-Net is equipped with the following novel components. (a) To exploit the saliency and stability of femoral heads, we employed a light-weight localization module to locate the target region and efficiently remove the complex background. (b) We add an edge stream to the regular segmentation stream to focus on processing the edge-related information, distinguish the organs with blurry boundaries, and then boost the overall segmentation performance. Between the regular segmentation stream and edge stream, we introduce an edge recalibration module at each resolution level to connect the intermediate layers and deliver the higher-level activations from the regular stream to the edge stream to denoise the irrelevant activations. (c) Finally, using a 3D Atrous Spatial Pyramid Pooling (ASPP) feature fusion module, we fuse the features at different scales in the regular stream and the predictions from the edge stream to form the final segmentation result. The proposed segmentation network was evaluated on 200 prostate cancer patient CT images with manually delineated contours of bladder, rectum, seminal vesicle, and prostate. The segmentation performance of the proposed method was quantitatively evaluated using three metrics including Dice similarity coefficient (DSC), average surface distance (ASD), and 95% surface distance (95SD). The proposed MTER-Net achieves average DSC of 86.35%, ASD of 1.09 mm, and 95SD of 3.53 mm on the four organs, which outperforms the state-of-the-art segmentation networks by a large margin. Specifically, the quantitative DSC evaluation results of the four organs are 96.49% (bladder), 86.39% (rectum), 76.38% (seminal vesicle), and 86.14% (prostate), respectively. In conclusion, we demonstrate that the proposed MTER-Net efficiently attains superior performance to state-of-the-art pelvic organ segmentation methods.

Boundary Coding Representation for Organ Segmentation in Prostate Cancer Radiotherapy

Accurate segmentation of the prostate and organs at risk (OARs, e.g., bladder and rectum) in male pelvic CT images is a critical step for prostate cancer radiotherapy. Unfortunately, the unclear organ boundary and large shape variation make the segmentation task very challenging. Previous studies usually used representations defined directly on unclear boundaries as context information to guide segmentation. Those boundary representations may not be so discriminative, resulting in limited performance improvement. To this end, we propose a novel boundary coding network (BCnet) to learn a discriminative representation for organ boundary and use it as the context information to guide the segmentation. Specifically, we design a two-stage learning strategy in the proposed BCnet: 1) Boundary coding representation learning. Two sub-networks under the supervision of the dilation and erosion masks transformed from the manually delineated organ mask are first separately trained to learn the spatial-semantic context near the organ boundary. Then we encode the organ boundary based on the predictions of these two sub-networks and design a multi-atlas based refinement strategy by transferring the knowledge from training data to inference. 2) Organ segmentation. The boundary coding representation as context information, in addition to the image patches, are used to train the final segmentation network. Experimental results on a large and diverse male pelvic CT dataset show that our method achieves superior performance compared with several state-of-the-art methods.

Evaluation of Deep Learning to Augment Image-Guided Radiotherapy for Head and Neck and Prostate Cancers

Importance

Personalized radiotherapy planning depends on high-quality delineation of target tumors and surrounding organs at risk (OARs). This process puts additional time burdens on oncologists and introduces variability among both experts and institutions.

Objective

To explore clinically acceptable autocontouring solutions that can be integrated into existing workflows and used in different domains of radiotherapy.

Design, Setting, and Participants

This quality improvement study used a multicenter imaging data set comprising 519 pelvic and 242 head and neck computed tomography (CT) scans from 8 distinct clinical sites and patients diagnosed either with prostate or head and neck cancer. The scans were acquired as part of treatment dose planning from patients who received intensity-modulated radiation therapy between October 2013 and February 2020. Fifteen different OARs were manually annotated by expert readers and radiation oncologists. The models were trained on a subset of the data set to automatically delineate OARs and evaluated on both internal and external data sets. Data analysis was conducted October 2019 to September 2020.

Main Outcomes and Measures

The autocontouring solution was evaluated on external data sets, and its accuracy was quantified with volumetric agreement and surface distance measures. Models were benchmarked against expert annotations in an interobserver variability (IOV) study. Clinical utility was evaluated by measuring time spent on manual corrections and annotations from scratch.

Results

A total of 519 participants' (519 [100%] men; 390 [75%] aged 62-75 years) pelvic CT images and 242 participants' (184 [76%] men; 194 [80%] aged 50-73 years) head and neck CT images were included. The models achieved levels of clinical accuracy within the bounds of expert IOV for 13 of 15 structures (eg, left femur, κ = 0.982; brainstem, κ = 0.806) and performed consistently well across both external and internal data sets (eg, mean [SD] Dice score for left femur, internal vs external data sets: 98.52% [0.50] vs 98.04% [1.02]; P = .04). The correction time of autogenerated contours on 10 head and neck and 10 prostate scans was measured as a mean of 4.98 (95% CI, 4.44-5.52) min/scan and 3.40 (95% CI, 1.60-5.20) min/scan, respectively, to ensure clinically accepted accuracy. Manual segmentation of the head and neck took a mean 86.75 (95% CI, 75.21-92.29) min/scan for an expert reader and 73.25 (95% CI, 68.68-77.82) min/scan for a radiation oncologist. The autogenerated contours represented a 93% reduction in time.

Conclusions and Relevance

In this study, the models achieved levels of clinical accuracy within expert IOV while reducing manual contouring time and performing consistently well across previously unseen heterogeneous data sets. With the availability of open-source libraries and reliable performance, this creates significant opportunities for the transformation of radiation treatment planning.

Complete abdomen and pelvis segmentation using U-net variant architecture

PURPOSE

Organ segmentation of computed tomography (CT) imaging is essential for radiotherapy treatment planning. Treatment planning requires segmentation not only of the affected tissue, but nearby healthy organs-at-risk, which is laborious and time-consuming. We present a fully automated segmentation method based on the three-dimensional (3D) U-Net convolutional neural network (CNN) capable of whole abdomen and pelvis segmentation into 33 unique organ and tissue structures, including tissues that may be overlooked by other automated segmentation approaches such as adipose tissue, skeletal muscle, and connective tissue and vessels. Whole abdomen segmentation is capable of quantifying exposure beyond a handful of organs-at-risk to all tissues within the abdomen.

METHODS

Sixty-six (66) CT examinations of 64 individuals were included in the training and validation sets and 18 CT examinations from 16 individuals were included in the test set. All pixels in each examination were segmented by image analysts (with physician correction) and assigned one of 33 labels. Segmentation was performed with a 3D U-Net variant architecture which included residual blocks, and model performance was quantified on 18 test cases. Human interobserver variability (using semiautomated segmentation) was also reported on two scans, and manual interobserver variability of three individuals was reported on one scan. Model performance was also compared to several of the best models reported in the literature for multiple organ segmentation.

RESULTS

The accuracy of the 3D U-Net model ranges from a Dice coefficient of 0.95 in the liver, 0.93 in the kidneys, 0.79 in the pancreas, 0.69 in the adrenals, and 0.51 in the renal arteries. Model accuracy is within 5% of human segmentation in eight of 19 organs and within 10% accuracy in 13 of 19 organs.

CONCLUSIONS

The CNN approaches the accuracy of human tracers and on certain complex organs displays more consistent prediction than human tracers. Fully automated deep learning-based segmentation of CT abdomen has the potential to improve both the speed and accuracy of radiotherapy dose prediction for organs-at-risk.

Asymmetrical Multi-task Attention U-Net for the Segmentation of Prostate Bed in CT Image

Segmentation of the prostate bed, the residual tissue after the removal of the prostate gland, is an essential prerequisite for post-prostatectomy radiotherapy but also a challenging task due to its non-contrast boundaries and highly variable shapes relying on neighboring organs. In this work, we propose a novel deep learning-based method to automatically segment this "invisible target". As the main idea of our design, we expect to get reference from the surrounding normal structures (bladder&rectum) and take advantage of this information to facilitate the prostate bed segmentation. To achieve this goal, we first use a U-Net as the backbone network to perform the bladder&rectum segmentation, which serves as a low-level task that can provide references to the high-level task of the prostate bed segmentation. Based on the backbone network, we build a novel attention network with a series of cascaded attention modules to further extract discriminative features for the high-level prostate bed segmentation task. Since the attention network has one-sided dependency on the backbone network, simulating the clinical workflow to use normal structures to guide the segmentation of radiotherapy target, we name the final composition model asymmetrical multi-task attention U-Net. Extensive experiments on a clinical dataset consisting of 186 CT images demonstrate the effectiveness of this new design and the superior performance of the model in comparison to the conventional atlas-based methods for prostate bed segmentation. The source code is publicly available at https://github.com/superxuang/amta-net.