Fully automatic multi‐organ segmentation for head and neck cancer radiotherapy using shape representation model constrained fully convolutional neural networks

Tong, Nuo; Gou, Shuiping; Yang, Shuyuan; Ruan, Dan; Sheng, Ke

doi:10.1002/mp.13147

Cited by 191 publications

(178 citation statements)

References 36 publications

Supporting

Mentioning

164

Contrasting

Unclassified

Order By: Relevance

“…Compared with other state‐of‐the‐art H&N segmentation methods on public H&N CT PDDCA dataset, SC‐GAN‐DenseNet outperforms SC‐GAN and atlas‐based, CNN‐based methods by a significant margin on both segmentation performance and speed. The proposed SC‐GAN‐DenseNet segmentation network also outperforms our previous segmentation network using SRM‐FC‐ResNet . Although the segmentation performance using our method is not statistically different than the model‐based and hierarchical vertex regression methods, our method is two orders of magnitude faster.…”

Section: Discussionmentioning

confidence: 73%

“…Learning and incorporating the shape characteristics of the OARs are of great importance when solving the image‐wise prediction problems . As shown in our previously study, a SRM increases the robustness and stability of the segmentation network without depending on an extensive patient dataset. Here, we constructed a similar model and employed it as prior information in the training stage of SC‐GAN.…”

Section: Methodsmentioning

confidence: 82%

“…The experimental results in Tables and demonstrate that the proposed segmentation method outperforms the conventional atlas‐based, model‐based, and CNN‐based method on the Dice's index and segmentation speed. Moreover, the paired Student's t‐test indicate that the improvement between SC‐GAN and SRM‐FC‐ResNet ( P = <0.05 ) on 7 OARs are statistically significant, as indicated by asterisks in Table . The comparison results with the SRM constrained FC‐ResNet indicate that adversarial training and dense connectivity further benefit the segmentation networks performance the in H&N multiorgan segmentation task.…”

Section: Methodsmentioning

confidence: 95%

“…Different from the loss terms utilized in the previously study, the reconstruction loss between D ( E ( S )) and the ground truth T is removed from the objective function of the segmentation network for the following reasons. First, the segmentation network optimization can focus on the voxel‐level consistency (segmentation loss), latent shape space consistency (shape representation loss), and higher order spatial consistency (adversarial loss).…”

Section: Methodsmentioning

confidence: 99%

“…The SRM network trained to capture the 3D OARs shape features were used to constrain the FC‐ResNet. We showed that superior H&N segmentation performance to state‐of‐the‐art methods could be achieved with the dual neural nets with a relatively small training dataset …”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Shape constrained fully convolutional DenseNet with adversarial training for multiorgan segmentation on head and neck CT and low‐field MR images

et al. 2019

Self Cite

View full text Add to dashboard Cite

Purpose Image‐guided radiotherapy provides images not only for patient positioning but also for online adaptive radiotherapy. Accurate delineation of organs‐at‐risk (OARs) on Head and Neck (H&N) CT and MR images is valuable to both initial treatment planning and adaptive planning, but manual contouring is laborious and inconsistent. A novel method based on the generative adversarial network (GAN) with shape constraint (SC‐GAN) is developed for fully automated H&N OARs segmentation on CT and low‐field MRI. Methods and material A deep supervised fully convolutional DenseNet is employed as the segmentation network for voxel‐wise prediction. A convolutional neural network (CNN)‐based discriminator network is then utilized to correct predicted errors and image‐level inconsistency between the prediction and ground truth. An additional shape representation loss between the prediction and ground truth in the latent shape space is integrated into the segmentation and adversarial loss functions to reduce false positivity and constrain the predicted shapes. The proposed segmentation method was first benchmarked on a public H&N CT database including 32 patients, and then on 25 0.35T MR images obtained from an MR‐guided radiotherapy system. The OARs include brainstem, optical chiasm, larynx (MR only), mandible, pharynx (MR only), parotid glands (both left and right), optical nerves (both left and right), and submandibular glands (both left and right, CT only). The performance of the proposed SC‐GAN was compared with GAN alone and GAN with the shape constraint (SC) but without the DenseNet (SC‐GAN‐ResNet) to quantify the contributions of shape constraint and DenseNet in the deep neural network segmentation. Results The proposed SC‐GAN slightly but consistently improve the segmentation accuracy on the benchmark H&N CT images compared with our previous deep segmentation network, which outperformed other published methods on the same or similar CT H&N dataset. On the low‐field MR dataset, the following average Dice's indices were obtained using improved SC‐GAN: 0.916 (brainstem), 0.589 (optical chiasm), 0.816 (mandible), 0.703 (optical nerves), 0.799 (larynx), 0.706 (pharynx), and 0.845 (parotid glands). The average surface distances ranged from 0.68 mm (brainstem) to 1.70 mm (larynx). The 95% surface distance ranged from 1.48 mm (left optical nerve) to 3.92 mm (larynx). Compared with CT, using 95% surface distance evaluation, the automated segmentation accuracy is higher on MR for the brainstem, optical chiasm, optical nerves and parotids, and lower for the mandible. The SC‐GAN performance is superior to SC‐GAN‐ResNet, which is more accurate than GAN alone on both the CT and MR datasets. The segmentation time for one patient is 14 seconds using a single GPU. Conclusion The performance of our previous shape constrained fully CNNs for H&N segmentation is further improved by incorporating GAN and DenseNet. With the novel segmentation method, we showed that the low‐field MR images acquired on a MR‐guided radiation radiotherapy syste...

show abstract

Section: Discussionmentioning

confidence: 73%

Section: Methodsmentioning

confidence: 82%

Section: Methodsmentioning

confidence: 95%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Shape constrained fully convolutional DenseNet with adversarial training for multiorgan segmentation on head and neck CT and low‐field MR images

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

Automatic segmentation and applicator reconstruction for CT‐based brachytherapy of cervical cancer using 3D convolutional neural networks

Zhang

Yang

Jiang

et al. 2020

J Applied Clin Med Phys

View full text Add to dashboard Cite

In this study, we present deep learning‐based approaches to automatic segmentation and applicator reconstruction with high accuracy and efficiency in the planning computed tomography (CT) for cervical cancer brachytherapy (BT). A novel three‐dimensional (3D) convolutional neural network (CNN) architecture was proposed and referred to as DSD‐UNET. The dataset of 91 patients received CT‐based BT of cervical cancer was used to train and test DSD‐UNET model for auto‐segmentation of high‐risk clinical target volume (HR‐CTV) and organs at risk (OARs). Automatic applicator reconstruction was achieved with DSD‐UNET‐based segmentation of applicator components followed by 3D skeletonization and polynomial curve fitting. Digitization of the channel paths for tandem and ovoid applicator in the planning CT was evaluated utilizing the data from 32 patients. Dice similarity coefficient (DSC), Jaccard Index (JI), and Hausdorff distance (HD) were used to quantitatively evaluate the accuracy. The segmentation performance of DSD‐UNET was compared with that of 3D U‐Net. Results showed that DSD‐UNET method outperformed 3D U‐Net on segmentations of all the structures. The mean DSC values of DSD‐UNET method were 86.9%, 82.9%, and 82.1% for bladder, HR‐CTV, and rectum, respectively. For the performance of automatic applicator reconstruction, outstanding segmentation accuracy was first achieved for the intrauterine and ovoid tubes (average DSC value of 92.1%, average HD value of 2.3 mm). Finally, HDs between the channel paths determined automatically and manually were 0.88 ± 0.12 mm, 0.95 ± 0.16 mm, and 0.96 ± 0.15 mm for the intrauterine, left ovoid, and right ovoid tubes, respectively. The proposed DSD‐UNET method outperformed the 3D U‐Net and could segment HR‐CTV, bladder, and rectum with relatively good accuracy. Accurate digitization of the channel paths could be achieved with the DSD‐UNET‐based method. The proposed approaches could be useful to improve the efficiency and consistency of treatment planning for cervical cancer BT.

show abstract

Evaluation of deep learning‐based auto‐segmentation algorithms for delineating clinical target volume and organs at risk involving data for 125 cervical cancer patients

Zhi

Chang

Zhao

et al. 2020

J Applied Clin Med Phys

View full text Add to dashboard Cite

Objective: To evaluate the accuracy of a deep learning-based auto-segmentation mode to that of manual contouring by one medical resident, where both entities tried to mimic the delineation "habits" of the same clinical senior physician. Methods: This study included 125 cervical cancer patients whose clinical target volumes (CTVs) and organs at risk (OARs) were delineated by the same senior physician. Of these 125 cases, 100 were used for model training and the remaining 25 for model testing. In addition, the medical resident instructed by the senior physician for approximately 8 months delineated the CTVs and OARs for the testing cases. The dice similarity coefficient (DSC) and the Hausdorff Distance (HD) were used to evaluate the delineation accuracy for CTV, bladder, rectum, small intestine, femoral-head-left, and femoral-head-right. Results: The DSC values of the auto-segmentation model and manual contouring by the resident were, respectively, 0.86 and 0.83 for the CTV (P < 0.05), 0.91 and 0.91 for the bladder (P > 0.05), 0.88 and 0.84 for the femoral-head-right (P < 0.05), 0.88 and 0.84 for the femoral-head-left (P < 0.05), 0.86 and 0.81 for the small intestine (P < 0.05), and 0.81 and 0.84 for the rectum (P > 0.05). The HD (mm) values were, respectively, 14.84 and 18.37 for the CTV (P < 0.05), 7.82 and 7.63 for the bladder (P > 0.05), 6.18 and 6.75 for the femoral-head-right (P > 0.05), 6.17 and 6.31 for the femoral-head-left (P > 0.05), 22.21 and 26.70 for the small intestine (P > 0.05), and 7.04 and 6.13 for the rectum (P > 0.05). The auto-segmentation model took approximately 2 min to delineate the CTV and OARs while the resident took approximately 90 min to complete the same task. Conclusion: The auto-segmentation model was as accurate as the medical resident but with much better efficiency in this study. Furthermore, the auto-segmentation approach offers additional perceivable advantages of being consistent and ever improving when compared with manual approaches.

show abstract

Fully automatic multi‐organ segmentation for head and neck cancer radiotherapy using shape representation model constrained fully convolutional neural networks

Cited by 191 publications

References 36 publications

Shape constrained fully convolutional DenseNet with adversarial training for multiorgan segmentation on head and neck CT and low‐field MR images

Shape constrained fully convolutional DenseNet with adversarial training for multiorgan segmentation on head and neck CT and low‐field MR images

Automatic segmentation and applicator reconstruction for CT‐based brachytherapy of cervical cancer using 3D convolutional neural networks

Evaluation of deep learning‐based auto‐segmentation algorithms for delineating clinical target volume and organs at risk involving data for 125 cervical cancer patients

Contact Info

Product

Resources

About