Xiang-Lei Yuan1, Wei Liu1, Yan Liu2, Xian-Hui Zeng1, Yi Mou1, Chun-Cheng Wu1, Lian-Song Ye1, Yu-Hang Zhang1, Long He1, Jing Feng3, Wan-Hong Zhang4, Jun Wang5, Xin Chen6, Yan-Xing Hu7, Kai-Hua Zhang8, Bing Hu9. 1. Department of Gastroenterology, West China Hospital, Sichuan University, No. 37 Guo Xue Alley, Wu Hou District, Chengdu, 610041, China. 2. School of Automation, Nanjing University of Information Science and Technology, Nanjing, China. 3. Department of Gastroenterology, Zhongshan Hospital, Xiamen University, Xiamen, China. 4. Department of Gastroenterology, Cangxi People's Hospital, Guangyuan, China. 5. Department of Gastroenterology, Affiliated Hospital of North Sichuan Medical College, Nanchong, China. 6. The First People's Hospital of Shuangliu District, Chengdu, China. 7. Xiamen Innovision Medical Technology Co, Ltd., Xiamen, China. 8. ERCDF, Ministry of Education and School of Computing and Software, Nanjing University of Information Science and Technology, Nanjing, China. 9. Department of Gastroenterology, West China Hospital, Sichuan University, No. 37 Guo Xue Alley, Wu Hou District, Chengdu, 610041, China. hubingnj@163.com.
Abstract
BACKGROUND: Intrapapillary capillary loop (IPCL) is an important factor for predicting invasion depth of esophageal squamous cell carcinoma (ESCC). The invasion depth is closely related to the selection of treatment strategy. However, diagnosis of IPCLs is complicated and subject to interobserver variability. This study aimed to develop an artificial intelligence (AI) system to predict IPCLs subtypes of precancerous lesions and superficial ESCC. METHODS: Images of magnifying endoscopy with narrow band imaging from three hospitals were collected retrospectively. IPCLs subtypes were annotated on images by expert endoscopists according to Japanese Endoscopic Society classification. The performance of the AI system was evaluated using internal and external validation datasets (IVD and EVD) and compared with that of the 11 endoscopists. RESULTS: A total of 7094 images from 685 patients were used to train and validate the AI system. The combined accuracy of the AI system for diagnosing IPCLs subtypes in IVD and EVD was 91.3% and 89.8%, respectively. The AI system achieved better performance than endoscopists in predicting IPCLs subtypes and invasion depth. The ability of junior endoscopists to diagnose IPCLs subtypes (combined accuracy: 84.7% vs 78.2%, P < 0.0001) and invasion depth (combined accuracy: 74.4% vs 67.9%, P < 0.0001) were significantly improved with AI system assistance. Although there was no significant differences, the performance of senior endoscopists was slightly elevated. CONCLUSIONS: The proposed AI system could improve the diagnostic ability of endoscopists to predict IPCLs classification of precancerous lesions and superficial ESCC.
BACKGROUND: Intrapapillary capillary loop (IPCL) is an important factor for predicting invasion depth of esophageal squamous cell carcinoma (ESCC). The invasion depth is closely related to the selection of treatment strategy. However, diagnosis of IPCLs is complicated and subject to interobserver variability. This study aimed to develop an artificial intelligence (AI) system to predict IPCLs subtypes of precancerous lesions and superficial ESCC. METHODS: Images of magnifying endoscopy with narrow band imaging from three hospitals were collected retrospectively. IPCLs subtypes were annotated on images by expert endoscopists according to Japanese Endoscopic Society classification. The performance of the AI system was evaluated using internal and external validation datasets (IVD and EVD) and compared with that of the 11 endoscopists. RESULTS: A total of 7094 images from 685 patients were used to train and validate the AI system. The combined accuracy of the AI system for diagnosing IPCLs subtypes in IVD and EVD was 91.3% and 89.8%, respectively. The AI system achieved better performance than endoscopists in predicting IPCLs subtypes and invasion depth. The ability of junior endoscopists to diagnose IPCLs subtypes (combined accuracy: 84.7% vs 78.2%, P < 0.0001) and invasion depth (combined accuracy: 74.4% vs 67.9%, P < 0.0001) were significantly improved with AI system assistance. Although there was no significant differences, the performance of senior endoscopists was slightly elevated. CONCLUSIONS: The proposed AI system could improve the diagnostic ability of endoscopists to predict IPCLs classification of precancerous lesions and superficial ESCC.