PSA-Net: Deep learning–based physician style–aware segmentation network for postoperative prostate cancer clinical target volumes
作者：
Highlights：
• Physicians have learnable CTV segmentation styles that have no significant impact on patient outcome
• A novel physician style-aware segmentation architecture that can mimic different physician styles for CTV segmentation
• Stylistic variations exist between institutions that follow the same segmentation guidelines
• The proposed method is highly effective in adapting CTV segmentation to new institutional styles
摘要
•Physicians have learnable CTV segmentation styles that have no significant impact on patient outcome•A novel physician style-aware segmentation architecture that can mimic different physician styles for CTV segmentation•Stylistic variations exist between institutions that follow the same segmentation guidelines•The proposed method is highly effective in adapting CTV segmentation to new institutional styles
论文关键词：Medical image segmentation,Observer variation,Deep learning,Radiation therapy
论文评审过程：Received 15 February 2021, Revised 7 October 2021, Accepted 12 October 2021, Available online 18 October 2021, Version of Record 28 October 2021.
论文官网地址：https://doi.org/10.1016/j.artmed.2021.102195
