Segmentation Of Clinical Target Volume Research Articles

Automatic Segmentation of Clinical Target Volume and Organs-at-Risk for Breast Conservative Radiotherapy Using a Convolutional Neural Network.

ObjectiveDelineation of clinical target volume (CTV) and organs at risk (OARs) is important for radiotherapy but is time-consuming. We trained and evaluated a U-ResNet model to provide fast and consistent auto-segmentation.MethodsWe collected 160 patients’ CT scans with breast cancer who underwent breast-conserving surgery (BCS) and were treated with radiotherapy. CTV and OARs were delineated manually and were used for model training. The dice similarity coefficient (DSC) and 95th percentile Hausdorff distance (95HD) were used to assess the performance of our model. CTV and OARs were randomly selected as ground truth (GT) masks, and artificial intelligence (AI) masks were generated by the proposed model. Two clinicians randomly compared CTV score differences of the contour. The consistency between two clinicians was tested. Time cost for auto-delineation was evaluated.ResultsThe mean DSC values of the proposed method were 0.94, 0.95, 0.94, 0.96, 0.96 and 0.93 for breast CTV, contralateral breast, heart, right lung, left lung and spinal cord, respectively. The mean 95HD values were 4.31mm, 3.59mm, 4.86mm, 3.18mm, 2.79mm and 4.37mm for the above structures, respectively. The average CTV scores for AI and GT were 2.89 versus 2.92 when evaluated by oncologist A (P=0.612), and 2.75 versus 2.83 by oncologist B (P=0.213), with no statistically significant differences. The consistency between two clinicians was poor (kappa=0.282). The time for auto-segmentation of CTV and OARs was 10.03 s.ConclusionOur proposed model (U-ResNet) can improve the efficiency and accuracy of delineation compared with U-Net, performing equally well with the segmentation generated by oncologists.

Reliability of MRI radiomics features in MR-guided radiotherapy for prostate cancer: Repeatability, reproducibility, and within-subject agreement.

The MR-guided radiotherapy (MRgRT) images on the integrated MRI and linear accelerator (MR-LINAC) might facilitate radiomics analysis for longitudinal treatment response assessment. However, the reliability of MRgRT radiomics features is largely unknown. This study aims to investigate MRgRT radiomics feature reliability acquired using a standardized 3D-T2W-TSE sequence in terms of repeatability, reproducibility, and within-subject feature agreement on a 1.5T MR-simulator and a 1.5T MR-LINAC for prostate cancer (PC). Twenty-six consecutive PC patients who underwent one MRI-simulator scan and two MR-LINAC scans before dose delivery were retrospectively included. The three MRI datasets were rigidly co-registered. 1023 first-order and texture radiomics features were extracted with different intensity bin widths for each scan in the manually segmented clinical target volume (CTV) and planning target volume (PTV) by an experienced radiation oncologist. Intraclass correlation coefficient (ICC) was used to evaluate feature repeatability between MR-LINAC scans and reproducibility between MRI-simulator and MR-LINAC scans. The within-subject feature value agreements were evaluated using Bland-Altman analysis. The impact of inter-observer segmentation on the radiomics feature reliability was also examined based on the second manual segmentation of CTV and PTV by an MRI researcher. Based on the segmentation by the radiation oncologist and the default bin width of 25, 9.6%, 24.1%, 49.6%, and 16.8% of the total 1023 featuresexhibited excellent (ICC>0.9), good (0.9>ICC>0.75), moderate (0.75>ICC>0.5), and poor (ICC<0.5)repeatability in the CTV, and 9.2%, 26.8%, 50.5%, and 13.5% in the PTV, respectively.For reproducibility, the corresponding feature percentages were 8.9%, 19.7%, 41.9%, and 29.6% in the CTV, and 8.4%, 17.8%, 47.9%, and 26% in the PTV. Feature reliability was not notably influenced by intensity bin width for discretization. BA analysis revealed wide 95% limit-of-agreements and substantial biases of feature values between CTV and PTV and between any two MRI scans. The features even with excellent ICC were still subjected to considerable inter-scan feature variations in each individual subject. The analysis on the second segmentation by the MRI researcher showed insignificantly different feature repeatability and reproducibility in terms of ICC values. Only a small proportion of features exhibited excellent/good repeatability and reproducibility, highlighting the importance of reliable MRgRT feature selection. The within-subject feature values were subjected to considerable inter-scan variations, imposing a challenge on the determination of the smallest detectable change in future MRgRT delta-radiomics studies.

Investigation of clinical target volume segmentation for whole breast irradiation using three-dimensional convolutional neural networks with gradient-weighted class activation mapping.

This study aims to implement three-dimensional convolutional neural networks (3D-CNN) for clinical target volume (CTV) segmentation for whole breast irradiation and investigate the focus of 3D-CNNs during decision-making using gradient-weighted class activation mapping (Grad-CAM). A 3D-UNet CNN was adopted to conduct automatic segmentation of the CTV for breast cancer. The 3D-UNet was trained using three datasets of left-, right-, and both left- and right-sided breast cancer patients. Segmentation accuracy was evaluated using the Dice similarity coefficient (DSC). Grad-CAM was applied to trained CNNs. The DSCs for the datasets of the left-, right-, and both left- and right-sided breasts were on an average 0.88, 0.89, and 0.85, respectively. The Grad-CAM heatmaps showed that the 3D-UNet used for segmentation determined the CTV region from the target-side breast tissue and by referring to the opposite-side breast. Although the size of the dataset was limited, DSC ≥ 0.85 was achieved for the segmentation of breast CTV using the 3D-UNet. Grad-CAM indicates the applicable scope and limitations of using a CNN by indicating the focus of such networks during decision-making.

Dosimetric Impact of Physician Style Variations in Contouring CTV for Postoperative Prostate Cancer: A Deep Learning—Based Simulation Study

Inter-observer variation is a significant problem in clinical target volume (CTV) segmentation in postoperative settings, where there is no gross tumor present. In this scenario, the CTV is not an anatomically established structure, but one determined by the physician based on the clinical guideline used, the preferred trade-off between tumor control and toxicity, their experience and training background, and other factors. This results in high inter-observer variability between physicians. This variability has been considered an issue, but the absence of multiple physician CTV contours for each patient and the significant amount of time required for dose planning based on each physician CTV have made it impractical to study its dosimetric consequences. In this study, we analyze the impact that variations in physician style have on dose to organs-at-risk (OAR) by simulating the clinical workflow via deep learning. For a given patient previously treated by one physician, we use deep learning–based tools to simulate how other physicians would contour the CTV and how the corresponding dose distributions would look for other physicians. To simulate multiple physician styles, we use a previously developed in-house CTV segmentation model that can produce physician style–aware segmentations. The corresponding dose distribution is predicted using another in-house deep learning tool, which, can predict dose within 3% of the prescription dose, on average, on the test data. For every test patient, four different physician style CTVs are considered, and four different dose distributions are analyzed. OAR dose metrics are compared, showing that even though physician style variations result in organs getting different doses, all the important dose metrics except maximum dose point are within the clinically acceptable limit.

A deep learning-based framework for segmenting invisible clinical target volumes with estimated uncertainties for post-operative prostate cancer radiotherapy.

In post-operative radiotherapy for prostate cancer, precisely contouring the clinical target volume (CTV) to be irradiated is challenging, because the cancerous prostate gland has been surgically removed, so the CTV encompasses the microscopic spread of tumor cells, which cannot be visualized in clinical images like computed tomography or magnetic resonance imaging. In current clinical practice, physicians' segment CTVs manually based on their relationship with nearby organs and other clinical information, but this allows large inter-physician variability. Automating post-operative prostate CTV segmentation with traditional image segmentation methods has yielded suboptimal results. We propose using deep learning to accurately segment post-operative prostate CTVs. The model proposed is trained using labels that were clinically approved and used for patient treatment. To segment the CTV, we segment nearby organs first, then use their relationship with the CTV to assist CTV segmentation. To ease the encoding of distance-based features, which are important for learning both the CTV contours' overlap with the surrounding OARs and the distance from their borders, we add distance prediction as an auxiliary task to the CTV network. To make the DL model practical for clinical use, we use Monte Carlo dropout (MCDO) to estimate model uncertainty. Using MCDO, we estimate and visualize the 95% upper and lower confidence bounds for each prediction which informs the physicians of areas that might require correction. The model proposed achieves an average Dice similarity coefficient (DSC) of 0.87 on a holdout test dataset, much better than established methods, such as atlas-based methods (DSC<0.7). The predicted contours agree with physician contours better than medical resident contours do. A reader study showed that the clinical acceptability of the automatically segmented CTV contours is equal to that of approved clinical contours manually drawn by physicians. Our deep learning model can accurately segment CTVs with the help of surrounding organ masks. Because the DL framework can outperform residents, it can be implemented practically in a clinical workflow to generate initial CTV contours or to guide residents in generating these contours for physicians to review and revise. Providing physicians with the 95% confidence bounds could streamline the review process for an efficient clinical workflow as this would enable physicians to concentrate their inspecting and editing efforts on the large uncertain areas.

Clinical target volume segmentation for stomach cancer by stochastic width deep neural network

Precise segmentation of clinical target volume (CTV) is the key to stomach cancer radiotherapy. We proposed a novel stochastic width-deep neural network (SW-DNN) for better automatically contouring stomach CTV. Stochastic width-deep neural network was an end-to-end approach, of which the core component was a novel SW mechanism that employed shortcut connections between the encoder and decoder in a random manner, and thus the width of the SW-DNN was stochastically adjustable to obtain improved segmentation results. In total, 150 stomach cancer patient computed tomography (CT) cases with the corresponding CTV labels were collected and used to train and evaluate the SW-DNN. Three common quantitative measures: true positive volume fraction (TPVF), positive predictive value (PPV), and Dice similarity coefficient (DSC) were used to evaluate the segmentation accuracy. Clinical target volumes calculated by SW-DNN had significant quantitative advantages over three state-of-the-art methods. The average DSC value of SW-DNN was 2.1%, 2.8%, and 3.6% higher than that of three state-of-the-art methods. The average DSC, TPVF, and PPV values of SW-DNN were 2.1%, 4.0%, and 0.3% higher than that of the corresponding constant width DNN. Stochastic width-deep neural network provided better performance for contouring stomach cancer CTV accurately and efficiently. It is a promising solution in clinical radiotherapy planning for stomach cancer.

DeepTarget: Gross tumor and clinical target volume segmentation in esophageal cancer radiotherapy.

Gross tumor volume (GTV) and clinical target volume (CTV) delineation are two critical steps in the cancer radiotherapy planning. GTV defines the primary treatment area of the gross tumor, while CTV outlines the sub-clinical malignant disease. Automatic GTV and CTV segmentation are both challenging for distinct reasons: GTV segmentation relies on the radiotherapy computed tomography (RTCT) image appearance, which suffers from poor contrast with the surrounding tissues, while CTV delineation relies on a mixture of predefined and judgement-based margins. High intra- and inter-user variability makes this a particularly difficult task. We develop tailored methods solving each task in the esophageal cancer radiotherapy, together leading to a comprehensive solution for the target contouring task. Specifically, we integrate the RTCT and positron emission tomography (PET) modalities together into a two-stream chained deep fusion framework taking advantage of both modalities to facilitate more accurate GTV segmentation. For CTV segmentation, since it is highly context-dependent-it must encompass the GTV and involved lymph nodes while also avoiding excessive exposure to the organs at risk-we formulate it as a deep contextual appearance-based problem using encoded spatial distances of these anatomical structures. This better emulates the margin- and appearance-based CTV delineation performed by oncologists. Adding to our contributions, for the GTV segmentation we propose a simple yet effective progressive semantically-nested network (PSNN) backbone that outperforms more complicated models. Our work is the first to provide a comprehensive solution for the esophageal GTV and CTV segmentation in radiotherapy planning. Extensive 4-fold cross-validation on 148 esophageal cancer patients, the largest analysis to date, was carried out for both tasks. The results demonstrate that our GTV and CTV segmentation approaches significantly improve the performance over previous state-of-the-art works, e.g., by 8.7% increases in Dice score (DSC) and 32.9mm reduction in Hausdorff distance (HD) for GTV segmentation, and by 3.4% increases in DSC and 29.4mm reduction in HD for CTV segmentation.

A deep learning method for real-time intraoperative US image segmentation in prostate brachytherapy.

This paper addresses the detection of the clinical target volume (CTV) in transrectal ultrasound (TRUS) image-guided intraoperative for permanent prostate brachytherapy. Developing a robust and automatic method to detect the CTV on intraoperative TRUS images is clinically important to have faster and reproducible interventions that can benefit both the clinical workflow and patient health. We present a multi-task deep learning method for an automatic prostate CTV boundary detection in intraoperative TRUS images by leveraging both the low-level and high-level (prior shape) information. Our method includes a channel-wise feature calibration strategy for low-level feature extraction and learning-based prior knowledge modeling for prostate CTV shape reconstruction. It employs CTV shape reconstruction from automatically sampled boundary surface coordinates (pseudo-landmarks) to detect the low-contrast and noisy regions across the prostate boundary, while being less biased from shadowing, inherent speckles, and artifact signals from the needle and implanted radioactive seeds. The proposed method was evaluated on a clinical database of 145 patients who underwent permanent prostate brachytherapy under TRUS guidance. Our method achieved a mean accuracy of [Formula: see text] and a mean surface distance error of [Formula: see text]. Extensive ablation and comparison studies show that our method outperformed previous deep learning-based methods by more than 7% for the Dice similarity coefficient and 6.9 mm reduced 3D Hausdorff distance error. Our study demonstrates the potential of shape model-based deep learning methods for an efficient and accurate CTV segmentation in an ultrasound-guided intervention. Moreover, learning both low-level features and prior shape knowledge with channel-wise feature calibration can significantly improve the performance of deep learning methods in medical image segmentation.

Clinical application and evaluation of automatic segmentation model based on deep learning for breast cancer radiotherapy

Objective In this study, the deep learning algorithm and the commercial planning system were integrated to establish and validate an automatic segmentation platform for clinical target volume (CTV) and organs at risk (OARs) in breast cancer patients. Methods A total of 400 patients with left and right breast cancer receiving radiotherapy after breast-conserving surgery in Cancer Hospital CAMS were enrolled in this study. A deep residual convolutional neural network was used to train CTV and OARs segmentation models. An end-to-end deep learning-based automatic segmentation platform (DLAS) was established. The accuracy of the DLAS platform delineation was verified using 42 left breast cancer and 40 right breast cancer patients. The overall Dice Similarity Coefficient (DSC) and the average Hausdorff Distance (AHD) were calculated. The relationship between the relative layer position and the DSC value of each layer (DSC_s) was calculated and analyzed layer-by-layer. Results The mean overall DSC and AHD of global CTV in left/right breast cancer patients were 0.87/0.88 and 9.38/8.71 mm. The average overall DSC and AHD range for all OARs in left/right breast cancer patients were ranged from 0.86 to 0.97 and 0.89 to 9.38 mm. The layer-by-layer analysis of CTV and OARs reached 0.90 or above, indicating that the doctors were only required to make slight or no modification, and the DSC_s ≥ 0.9 of CTV automatic delineation accounted for approximately 44.7% of the layers. The automatic delineation range for OARs was 50.9%-89.6%. For DSC_s< 0.7, the DSC_s values of CTV and the regions of interest other than the spinal cord were significantly decreased in the boundary regions on both sides (layer positions 0-0.2, and 0.8-1.0), and the level of decrease toward the edge was more pronounced. The spinal cord was delineated in a full-scale manner, and no significant decrease in DSC_s was observed in a particular area. Conclusions The end-to-end automatic segmentation platform based on deep learning can integrate the breast cancer segmentation model and achieve excellent automatic segmentation effect. In the boundary areas on both sides of the superior and inferior directions, the consistency of the delineation decreases more obviously, which needs to be further improved. Key words: Automatic segmentation; Deep learning; Breast neoplasm/radiotherapy

A study of positioning orientation effect on segmentation accuracy using convolutional neural networks for rectal cancer.

PurposeConvolutional neural networks (CNN) have greatly improved medical image segmentation. A robust model requires training data can represent the entire dataset. One of the differing characteristics comes from variability in patient positioning (prone or supine) for radiotherapy. In this study, we investigated the effect of position orientation on segmentation using CNN.MethodsData of 100 patients (50 in supine and 50 in prone) with rectal cancer were collected for this study. We designed three sets of experiments for comparison: (a) segmentation using the model trained with data from the same orientation; (b) segmentation using the model trained with data from the opposite orientation; (c) segmentation using the model trained with data from both orientations. We performed fivefold cross‐validation. The performance was evaluated on segmentation of the clinical target volume (CTV), bladder, and femurs with Dice similarity coefficient (DSC) and Hausdorff distance (HD).ResultsCompared with models trained on cases positioned in the same orientation, the models trained with cases positioned in the opposite orientation performed significantly worse (P < 0.05) on CTV and bladder segmentation, but had comparable accuracy for femurs (P > 0.05). The average DSC values were 0.74 vs 0.84, 0.85 vs 0.88, and 0.91 vs 0.91 for CTV, bladder, and femurs, respectively. The corresponding HD values (mm) were 16.6 vs 14.6, 8.4 vs 8.1, and 6.3 vs 6.3, respectively. The models trained with data from both orientations have comparable accuracy (P > 0.05), with average DSC of 0.84, 0.88, and 0.91 and HD of 14.4, 8.1, and 6.3, respectively.ConclusionsOrientation affects the accuracy for CTV and bladder, but has negligible effect on the femurs. The model trained from data combining both orientations performs as well as a model trained with data from the same orientation for all the organs. These observations can offer guidance on the choice of training data for accurate segmentation.