摘要
Purpose Fast and accurate outlining of the organs at risk (OARs) and high-risk clinical tumor volume (HRCTV) is especially important in high-dose-rate brachytherapy due to the highly time-intensive online treatment planning process and the high dose gradient around the HRCTV. This study aims to apply a self-configured ensemble method for fast and reproducible auto-segmentation of OARs and HRCTVs in gynecological cancer. Materials and methods We applied nnU-Net (no new U-Net), an automatically adapted deep convolutional neural network based on U-Net, to segment the bladder, rectum and HRCTV on CT images in gynecological cancer. In nnU-Net, three architectures, including 2D U-Net, 3D U-Net and 3D-Cascade U-Net, were trained and finally ensembled. 207 cases were randomly chosen for training, and 30 for testing. Quantitative evaluation used well-established image segmentation metrics, including dice similarity coefficient (DSC), 95% Hausdorff distance (HD95%), and average surface distance (ASD). Qualitative analysis of automated segmentation results was performed visually by two radiation oncologists. The dosimetric evaluation was performed by comparing the dose-volume parameters of both predicted segmentation and human contouring. Results nnU-Net obtained high qualitative and quantitative segmentation accuracy on the test dataset and performed better than previously reported methods in bladder and rectum segmentation. In quantitative evaluation, 3D-Cascade achieved the best performance in the bladder (DSC: 0.936 +/- 0.051, HD95%: 3.503 +/- 1.956, ASD: 0.944 +/- 0.503), rectum (DSC: 0.831 +/- 0.074, HD95%: 7.579 +/- 5.857, ASD: 3.6 +/- 3.485), and HRCTV (DSC: 0.836 +/- 0.07, HD95%: 7.42 +/- 5.023, ASD: 2.094 +/- 1.311). According to the qualitative evaluation, over 76% of the test data set had no or minor visually detectable errors in segmentation. Conclusion This work showed nnU-Net's superiority in segmenting OARs and HRCTV in gynecological brachytherapy cases in our center, among which 3D-Cascade shows the highest accuracy in segmentation across different applicators and patient anatomy.
学科与关键词
- Pelvic U-Net: multi-label semantic segmentation of pelvic organs at risk for radiation therapy anal cancer patients using a deeply supervised shuffle attention convolutional neural networkLempart, Michael*; Nilsson, Martin P.; Scherman, Jonas; Gustafsson, Christian Jamtheim; Nilsson, Mikael; Alkner, Sara; Engleson, Jens; Adrian, Gabriel; Munck af Rosenschold, Per; Olsson, Lars E.Radiation Oncology, 2022, 17(1): 114.被引 4
- A Feasibility Study of Deep Learning-Based Auto-Segmentation Directly Used in VMAT Planning Design and Optimization for Cervical CancerChen, Along; Chen, Fei; Li, Xiaofang; Zhang, Yazhi; Chen, Li; Chen, Lixin*; Zhu, Jinhan*Frontiers in Oncology, 2022, 12: 908903.
- Delineation of clinical target volume and organs at risk in cervical cancer radiotherapy by deep learning networksTian, Miao; Wang, Hongqiu; Liu, Xingang; Ye, Yuyun; Ouyang, Ganlu; Shen, Yali; Li, Zhiping; Wang, Xin*; Wu, Shaozhi*Medical Physics, 2023, 50(10): 6354-6365.被引 5
