Detection of multiple lesions of gastrointestinal tract for endoscopy using artificial intelligence model: a pilot study

• Published in: Surgical endoscopy Vol. 35; no. 12; pp. 6532 - 6538
• Main Authors: Guo, Linjie, Gong, Hui, Wang, Qiushi, Zhang, Qiongying, Tong, Huan, Li, Jing, Lei, Xiang, Xiao, Xue, Li, Chuanhui, Jiang, Jinsun, Hu, Bing, Song, Jie, Tang, Chengwei, Huang, Zhiyin
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.12.2021; Springer Nature B.V
• Subjects: Abdominal Surgery; Artificial Intelligence; Cancer; Datasets; Efficiency; Endoscopy; Endoscopy, Gastrointestinal; Gastroenterology; Gastrointestinal Tract; Gynecology; Hepatology; Humans; Medical diagnosis; Medicine; Medicine & Public Health; Neural Networks, Computer; Pilot Projects; Polyps; Proctology; Surgery; Ulcers; Gastrointestinal endoscopy; Multiple-lesion detection; Deep convolutional neural network; Computer-aided diagnosis
• ISSN: 0930-2794; 1432-2218
• DOI: 10.1007/s00464-020-08150-x

Background This study was aimed to develop a computer-aided diagnosis (CAD) system with deep-learning technique and to validate its efficiency on detecting the four categories of lesions such as polyps, advanced cancer, erosion/ulcer and varices at endoscopy. Methods A deep convolutional neural network (CNN) that consists of more than 50 layers were trained with a big dataset containing 327,121 white light images (WLI) of endoscopy from 117,005 cases collected from 2012 to 2017. Two CAD models were developed using images with or without annotation of the training dataset. The efficiency of the CAD system detecting the four categories of lesions was validated by another dataset containing consecutive cases from 2018 to 2019. Results A total of 1734 cases with 33,959 images were included in the validation datasets which containing lesions of polyps 1265, advanced cancer 500, erosion/ulcer 486, and varices 248. The CAD system developed in this study may detect polyps, advanced cancer, erosion/ulcer and varices as abnormality with the sensitivity of 88.3% and specificity of 90.3%, respectively, in 0.05 s. The training datasets with annotation may enhance either sensitivity or specificity about 20%, p  = 0.000. The sensitivities and specificities for polyps, advanced cancer, erosion/ulcer and varices reached about 90%, respectively. The detect efficiency for the four categories of lesions reached to 89.7%. Conclusion The CAD model for detection of multiple lesions in gastrointestinal lumen would be potentially developed into a double check along with real-time assessment and interpretation of the findings encountered by the endoscopists and may be a benefit to reduce the events of missing lesions.