AUTHOR=Sha Xue , Wang Hui , Sha Hui , Xie Lu , Zhou Qichao , Zhang Wei , Yin Yong 

TITLE=Clinical target volume and organs at risk segmentation for rectal cancer radiotherapy using the Flex U-Net network

JOURNAL=Frontiers in Oncology

VOLUME=Volume 13 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2023.1172424

DOI=10.3389/fonc.2023.1172424

ISSN=2234-943X

ABSTRACT=Purpose/Objective(s): The aim of this study was to improve the accuracy of the clinical target volume (CTV) and organs at risk (OARs) segmentation for postoperative rectal cancer radiotherapy.
Materials/Methods: Computed tomography (CT) scans from 265 rectal cancer patients treated at our institution were collected to train and validate automatic contouring models. The regions of CTV and OARs were delineated by experienced radiologists as the ground truth. We improved the conventional U-Net and proposed Flex U-Net, which used a register model to correct the noise caused by manual annotation to refine the performance of the automatic segmentation model. Then, we compared the performance with U-Net and V-Net. The Dice similarity coefficient (DSC), Hausdorff distance (HD), and average symmetric surface distance (ASSD) were calculated for quantitative evaluation.
Results: Our proposed framework achieved Dice values of 0.817±0.071, 0.930±0.076, 0.927±0.03, and 0.925±0.03 for CTV, bladder, Femur head-L and Femur head-R, respectively. Conversely, the baseline results were 0.803±0.082, 0.917±0.105, 0.923±0.03 and 0.917±0.03, respectively. 
Conclusion: In conclusion, our proposed Flex U-Net can enable satisfactory CTV and OAR segmentation for rectal cancer and yield superior performance compared to conventional methods. Our proposed method provides an automatic, fast and consistent solution for CTV and OAR segmentation and shows potential to be generally applied for radiation therapy planning for a variety of cancers.