Deep Learning For Automatic Gross Tumor Volumes Contouring in Esophageal Cancer Based on Contrast-Enhanced Computed Tomography Images: A Multi-Institutional Study

Shuaitong Zhang; Kunwei Li; Yuchen Sun; Yun Wan; Yong Ao; Yinghua Zhong; Mingzhu Liang; Lizhu Wang; Xiangmeng Chen; Xiaofeng Pei; Yi Hu; Duanduan Chen; Man Li; Hong Shan

doi:10.1016/j.ijrobp.2024.02.035

Deep Learning For Automatic Gross Tumor Volumes Contouring in Esophageal Cancer Based on Contrast-Enhanced Computed Tomography Images: A Multi-Institutional Study

Int J Radiat Oncol Biol Phys. 2024 Mar 2:S0360-3016(24)00350-X. doi: 10.1016/j.ijrobp.2024.02.035. Online ahead of print.

Authors

Shuaitong Zhang¹, Kunwei Li², Yuchen Sun¹, Yun Wan³, Yong Ao⁴, Yinghua Zhong⁵, Mingzhu Liang⁶, Lizhu Wang⁶, Xiangmeng Chen⁷, Xiaofeng Pei⁸, Yi Hu⁹, Duanduan Chen¹⁰, Man Li¹¹, Hong Shan¹²

Affiliations

¹ School of Medical Technology, Beijing Institute of Technology, Beijing, China.
² Department of Radiology, The Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, Guangdong, China; Guangdong Provincial Key Laboratory of Biomedical Imaging and Guangdong Provincial Engineering Research Center of Molecular Imaging, Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, Guangdong, China.
³ Department of Radiology, Xinyi City People's Hospital, Xinyi, Guangdong, China.
⁴ Department of Thoracic Surgery, Sun Yat-sen University Cancer Center, Guangzhou, Guangdong, China; State Key Laboratory of Oncology in South China, Guangdong Esophageal Cancer Institute, Collaborative Innovation Center for Cancer Medicine, Guangzhou, Guangdong, China.
⁵ Department of Radiology, The Third People's Hospital of Zhuhai, Zhuhai, Guangdong, China.
⁶ Department of Radiology, The Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, Guangdong, China.
⁷ Department of Radiology, Jiangmen Central Hospital, Jiangmen, Guangdong, China.
⁸ Department of Radiation Oncology, The Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, Guangdong, China.
⁹ Department of Thoracic Surgery, Sun Yat-sen University Cancer Center, Guangzhou, Guangdong, China; State Key Laboratory of Oncology in South China, Guangdong Esophageal Cancer Institute, Collaborative Innovation Center for Cancer Medicine, Guangzhou, Guangdong, China. Electronic address: huyi@sysucc.org.cn.
¹⁰ School of Medical Technology, Beijing Institute of Technology, Beijing, China. Electronic address: duanduan@bit.edu.cn.
¹¹ Department of Radiology, The Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, Guangdong, China. Electronic address: liman26@mail.sysu.edu.cn.
¹² Department of Radiology, The Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, Guangdong, China; Department of Interventional Medicine, The Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, Guangdong, China. Electronic address: shanhong_2022@126.com.

PMID: 38432286
DOI: 10.1016/j.ijrobp.2024.02.035

Abstract

Purpose: To develop and externally validate an automatic artificial intelligence (AI) tool for delineating gross tumor volume (GTV) in patients with esophageal squamous cell carcinoma (ESCC), which can assist in neo-adjuvant or radical radiation therapy treatment planning.

Methods and materials: In this multi-institutional study, contrast-enhanced CT images from 580 eligible ESCC patients were retrospectively collected. The GTV contours delineated by 2 experts via consensus were used as ground truth. A 3-dimensional deep learning model was developed for GTV contouring in the training cohort and internally and externally validated in 3 validation cohorts. The AI tool was compared against 12 board-certified experts in 25 patients randomly selected from the external validation cohort to evaluate its assistance in improving contouring performance and reducing variation. Contouring performance was measured using dice similarity coefficient (DSC) and average surface distance. Additionally, our previously established radiomics model for predicting pathologic complete response was used to compare AI-generated and ground truth contours, to assess the potential of the AI contouring tool in radiomics analysis.

Results: The AI tool demonstrated good GTV contouring performance in multicenter validation cohorts, with median DSC values of 0.865, 0.876, and 0.866 and median average surface distance values of 0.939, 0.789, and 0.875 mm, respectively. Furthermore, the AI tool significantly improved contouring performance for half of 12 board-certified experts (DSC values, 0.794-0.835 vs 0.856-0.881, P = .003-0.048), reduced the intra- and interobserver variations by 37.4% and 55.2%, respectively, and saved contouring time by 77.6%. In the radiomics analysis, 88.7% of radiomic features from ground truth and AI-generated contours demonstrated stable reproducibility, and similar pathologic complete response prediction performance for these contours (P = .430) was observed.

Conclusions: Our AI contouring tool can improve GTV contouring performance and facilitate radiomics analysis in ESCC patients, which indicates its potential for GTV contouring during radiation therapy treatment planning and radiomics studies.