Comprehensive and clinically accurate head and neck cancer organs-at-risk delineation on a multi-institutional study

• Published in: Nature communications Vol. 13; no. 1; p. 6137
• Main Authors: Ye, Xianghua, Guo, Dazhou, Ge, Jia, Yan, Senxiang, Xin, Yi, Song, Yuchen, Yan, Yongheng, Huang, Bing-shen, Hung, Tsung-Min, Zhu, Zhuotun, Peng, Ling, Ren, Yanping, Liu, Rui, Zhang, Gong, Mao, Mengyuan, Chen, Xiaohua, Lu, Zhongjie, Li, Wenxiang, Chen, Yuzhen, Huang, Lingyun, Xiao, Jing, Harrison, Adam P., Lu, Le, Lin, Chien-Yu, Jin, Dakai, Ho, Tsung-Ying
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 17.10.2022; Nature Publishing Group; Nature Portfolio
• Subjects: 631/114/1305; 692/4028/67/1536; 692/700/565/485; Automation; Complications; Deep learning; Error analysis; Error reduction; Head & neck cancer; Head and Neck Neoplasms - radiotherapy; Health risks; Humanities and Social Sciences; Humans; Image Processing, Computer-Assisted - methods; Labor costs; multidisciplinary; Neck; Organs at Risk; Patients; Radiation therapy; Radiometry; Risk; Science; Science (multidisciplinary); Segmentation
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-022-33178-z

Accurate organ-at-risk (OAR) segmentation is critical to reduce radiotherapy complications. Consensus guidelines recommend delineating over 40 OARs in the head-and-neck (H&N). However, prohibitive labor costs cause most institutions to delineate a substantially smaller subset of OARs, neglecting the dose distributions of other OARs. Here, we present an automated and highly effective stratified OAR segmentation (SOARS) system using deep learning that precisely delineates a comprehensive set of 42 H&N OARs. We train SOARS using 176 patients from an internal institution and independently evaluate it on 1327 external patients across six different institutions. It consistently outperforms other state-of-the-art methods by at least 3–5% in Dice score for each institutional evaluation (up to 36% relative distance error reduction). Crucially, multi-user studies demonstrate that 98% of SOARS predictions need only minor or no revisions to achieve clinical acceptance (reducing workloads by 90%). Moreover, segmentation and dosimetric accuracy are within or smaller than the inter-user variation. Accurate organ at risk (OAR) segmentation is critical to reduce the radiotherapy post-treatment complications. Here, the authors develop an automated OAR segmentation system to delineate a comprehensive set of 42 H&N OARs.