Automatic delineation of the clinical target volume and organs at risk by deep learning for rectal cancer postoperative radiotherapy

Song, Ying; Hu, Junjie; Wu, Qiang; Feng, Xu; Nie, Shihong; Zhao, Yaqin; Bai, Song; Zhang, Yi

doi:10.1016/j.radonc.2020.01.020

Cited by 63 publications

(53 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast to traditional machine learning approaches that use handengineered image-processing routines, DL is able to learn complex information from large datasets. In recent years, DLbased approaches have shown great promise in medical imaging applications, including image synthesis (3,4) and automatic segmentation (5)(6)(7). There is great promise for DL to drastically accelerate delineation of the GTV and OARs in MR-Linac studies, yet a major hurdle remains the lack of large existing pre-contoured MRI datasets for training supervised segmentation networks.…”

Section: Introductionmentioning

confidence: 99%

CT-Based Pelvic T1-Weighted MR Image Synthesis Using UNet, UNet++ and Cycle-Consistent Generative Adversarial Network (Cycle-GAN)

et al. 2021

View full text Add to dashboard Cite

BackgroundComputed tomography (CT) and magnetic resonance imaging (MRI) are the mainstay imaging modalities in radiotherapy planning. In MR-Linac treatment, manual annotation of organs-at-risk (OARs) and clinical volumes requires a significant clinician interaction and is a major challenge. Currently, there is a lack of available pre-annotated MRI data for training supervised segmentation algorithms. This study aimed to develop a deep learning (DL)-based framework to synthesize pelvic T1-weighted MRI from a pre-existing repository of clinical planning CTs.MethodsMRI synthesis was performed using UNet++ and cycle-consistent generative adversarial network (Cycle-GAN), and the predictions were compared qualitatively and quantitatively against a baseline UNet model using pixel-wise and perceptual loss functions. Additionally, the Cycle-GAN predictions were evaluated through qualitative expert testing (4 radiologists), and a pelvic bone segmentation routine based on a UNet architecture was trained on synthetic MRI using CT-propagated contours and subsequently tested on real pelvic T1 weighted MRI scans.ResultsIn our experiments, Cycle-GAN generated sharp images for all pelvic slices whilst UNet and UNet++ predictions suffered from poorer spatial resolution within deformable soft-tissues (e.g. bladder, bowel). Qualitative radiologist assessment showed inter-expert variabilities in the test scores; each of the four radiologists correctly identified images as acquired/synthetic with 67%, 100%, 86% and 94% accuracy. Unsupervised segmentation of pelvic bone on T1-weighted images was successful in a number of test casesConclusionPelvic MRI synthesis is a challenging task due to the absence of soft-tissue contrast on CT. Our study showed the potential of deep learning models for synthesizing realistic MR images from CT, and transferring cross-domain knowledge which may help to expand training datasets for 21 development of MR-only segmentation models.

show abstract

Section: Introductionmentioning

confidence: 99%

CT-Based Pelvic T1-Weighted MR Image Synthesis Using UNet, UNet++ and Cycle-Consistent Generative Adversarial Network (Cycle-GAN)

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In recent years, convolutional neural networks (CNNs) have demonstrated their advantages in performing medical segmentation tasks [8][9][10]. In the field of radiotherapy, CNNs have been commonly used in the CTV or OAR delineation of brain tumor [11], head and neck (H&N) cancer [12][13][14][15][16][17], breast cancer [18,19], esophageal cancer [20], rectal cancer [21][22][23], bladder cancer [24] and so on. As a well-known CNN architecture for medical image segmentation, U-Net [25] was commonly used among all the CNN based contour delineation models.…”

mentioning

confidence: 99%

Development and validation of a deep learning algorithm for auto-delineation of clinical target volume and organs at risk in cervical cancer radiotherapy

Liu

Guan

et al. 2020

Radiotherapy and Oncology

View full text Add to dashboard Cite

The delineation of the clinical target volume (CTV) is a crucial, laborious and subjective step in cervical cancer radiotherapy. The aim of this study was to propose and evaluate a novel end-to-end convolutional neural network (CNN) for fully automatic and accurate CTV in cervical cancer. Methods: A total of 237 computed tomography (CT) scans of patients with locally advanced cervical cancer were collected and evaluated. A novel 2.5D CNN network, called DpnUNet, was developed for CTV delineation and further applied for CTV and organ-at-risk (OAR) delineation simultaneously. Comprehensive comparisons and experiments were performed. The mean Dice similarity coefficient (DSC), 95th percentile Hausdorff distance (95HD) and subjective evaluation were used to assess the performance of this method. Results: The mean DSC and 95HD values were 0.86 and 5.34 mm for the delineated CTVs. The clinical experts' subjective assessments showed that 90% of the predicted contours were acceptable for clinical usage. The mean DSC and 95HD values were 0.91 and 4.05 mm for bladder, 0.85 and 2.16 mm for bone marrow, 0.90 and 1.27 mm for left femoral head, 0.90 and 1.51 mm for right femoral head, 0.82 and 4.29 mm for rectum, 0.85 and 4.35 mm for bowel bag, 0.82 and 4.96 mm for spinal cord respectively. The average delineation time for one patient's CT images was within 15 seconds. Conclusion:The experimental results demonstrate that the CTV and OARs delineated for cervical cancer by DpnUNet was in close agreement with the ground truth. DpnUNet could significantly reduce the radiation oncologists' contouring time.

show abstract

“…Automatic segmentation techniques especially based on CNN models have made significant progress with increasing reliability and accuracy in recent years, thus potentially relieving radiation oncologists from the time-cost of contouring. To the authors' knowledge, very few studies were reported on the automatic delineation of the CTV (29)(30)(31)(32) due to the ambiguous and blurred boundaries between the CTV and normal tissues, the potential for tumor spread or subclinical diseases in the CT images, and the inter-observer variability in recognition of anatomical structures. The current most common approach to evaluate automatic delineation of the CTV is to compare with GT contours using quantitative measures such as DSC and HD (33,34).…”

Section: Discussionmentioning

confidence: 99%

An Adversarial Deep-Learning-Based Model for Cervical Cancer CTV Segmentation With Multicenter Blinded Randomized Controlled Validation

et al. 2021

View full text Add to dashboard Cite

PurposeTo propose a novel deep-learning-based auto-segmentation model for CTV delineation in cervical cancer and to evaluate whether it can perform comparably well to manual delineation by a three-stage multicenter evaluation framework.MethodsAn adversarial deep-learning-based auto-segmentation model was trained and configured for cervical cancer CTV contouring using CT data from 237 patients. Then CT scans of additional 20 consecutive patients with locally advanced cervical cancer were collected to perform a three-stage multicenter randomized controlled evaluation involving nine oncologists from six medical centers. This evaluation system is a combination of objective performance metrics, radiation oncologist assessment, and finally the head-to-head Turing imitation test. Accuracy and effectiveness were evaluated step by step. The intra-observer consistency of each oncologist was also tested.ResultsIn stage-1 evaluation, the mean DSC and the 95HD value of the proposed model were 0.88 and 3.46 mm, respectively. In stage-2, the oncologist grading evaluation showed the majority of AI contours were comparable to the GT contours. The average CTV scores for AI and GT were 2.68 vs. 2.71 in week 0 (P = .206), and 2.62 vs. 2.63 in week 2 (P = .552), with no significant statistical differences. In stage-3, the Turing imitation test showed that the percentage of AI contours, which were judged to be better than GT contours by ≥5 oncologists, was 60.0% in week 0 and 42.5% in week 2. Most oncologists demonstrated good consistency between the 2 weeks (P > 0.05).ConclusionsThe tested AI model was demonstrated to be accurate and comparable to the manual CTV segmentation in cervical cancer patients when assessed by our three-stage evaluation framework.

show abstract

Automatic delineation of the clinical target volume and organs at risk by deep learning for rectal cancer postoperative radiotherapy

Cited by 63 publications

References 25 publications

CT-Based Pelvic T1-Weighted MR Image Synthesis Using UNet, UNet++ and Cycle-Consistent Generative Adversarial Network (Cycle-GAN)

CT-Based Pelvic T1-Weighted MR Image Synthesis Using UNet, UNet++ and Cycle-Consistent Generative Adversarial Network (Cycle-GAN)

Development and validation of a deep learning algorithm for auto-delineation of clinical target volume and organs at risk in cervical cancer radiotherapy

An Adversarial Deep-Learning-Based Model for Cervical Cancer CTV Segmentation With Multicenter Blinded Randomized Controlled Validation

Contact Info

Product

Resources

About