Artificial intelligence assisted detection of superficial esophageal squamous cell carcinoma in white-light endoscopic images by using a generalized system

Yadong Feng; Yan Liang; Peng Li; Qigang Long; Jie Song; Mengjie Li; Xiaofen Wang; Cui-E Cheng; Kai Zhao; Jifeng Ma; Lingxiao Zhao

doi:10.1007/s12672-023-00694-3

Artificial intelligence assisted detection of superficial esophageal squamous cell carcinoma in white-light endoscopic images by using a generalized system

Discov Oncol. 2023 May 19;14(1):73. doi: 10.1007/s12672-023-00694-3.

Authors

Yadong Feng^#^{1

2}, Yan Liang^#³, Peng Li^#^{4

5}, Qigang Long^{4

5}, Jie Song³, Mengjie Li³, Xiaofen Wang³, Cui-E Cheng⁶, Kai Zhao⁷, Jifeng Ma⁸, Lingxiao Zhao^{9

10}

Affiliations

¹ Department of Gastroenterology, Zhongda Hospital Southeast University, 87 Dingjiaqiao Street, Nanjing, 210009, China. drfengyd@126.com.
² Department of Gastroenterology, the Affiliated Changshu Hospital of Nantong University, Changshu No. 2 People's Hospital, 18 Taishan Road, Suzhou, 215500, China. drfengyd@126.com.
³ Department of Gastroenterology, Zhongda Hospital Southeast University, 87 Dingjiaqiao Street, Nanjing, 210009, China.
⁴ Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, 88 Keling Road, Suzhou, 215163, China.
⁵ School of Biomedical Engineering (Suzhou), Division of Life Sciences and Medicine, University of Science and Technology of China, 96 Jinzhai Road, Hefei, 230026, China.
⁶ Department of Gastroenterology, the Affiliated Changshu Hospital of Nantong University, Changshu No. 2 People's Hospital, 18 Taishan Road, Suzhou, 215500, China.
⁷ Department of Gastroenterology, Changzhou Jintan First People's Hospital Affiliated to Jiangsu University, 500 Jintan Avenue, Jintan, 210036, China.
⁸ Department of Gastroenterology, General Global Maanshan 17th Metallurgy Hospital, 828 West Hunan Road, Maanshan, 243011, China.
⁹ Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, 88 Keling Road, Suzhou, 215163, China. zhaolx@sibet.ac.cn.
¹⁰ School of Biomedical Engineering (Suzhou), Division of Life Sciences and Medicine, University of Science and Technology of China, 96 Jinzhai Road, Hefei, 230026, China. zhaolx@sibet.ac.cn.

^# Contributed equally.

Abstract

Background: The use of artificial intelligence (AI) assisted white light imaging (WLI) detection systems for superficial esophageal squamous cell carcinoma (SESCC) is limited by training with images from one specific endoscopy platform.

Methods: In this study, we developed an AI system with a convolutional neural network (CNN) model using WLI images from Olympus and Fujifilm endoscopy platforms. The training dataset consisted of 5892 WLI images from 1283 patients, and the validation dataset included 4529 images from 1224 patients. We assessed the diagnostic performance of the AI system and compared it with that of endoscopists. We analyzed the system's ability to identify cancerous imaging characteristics and investigated the efficacy of the AI system as an assistant in diagnosis.

Results: In the internal validation set, the AI system's per-image analysis had a sensitivity, specificity, accuracy, positive predictive value (PPV), and negative predictive value (NPV) of 96.64%, 95.35%, 91.75%, 90.91%, and 98.33%, respectively. In patient-based analysis, these values were 90.17%, 94.34%, 88.38%, 89.50%, and 94.72%, respectively. The diagnostic results in the external validation set were also favorable. The CNN model's diagnostic performance in recognizing cancerous imaging characteristics was comparable to that of expert endoscopists and significantly higher than that of mid-level and junior endoscopists. This model was competent in localizing SESCC lesions. Manual diagnostic performances were significantly improved with the assistance by AI system, especially in terms of accuracy (75.12% vs. 84.95%, p = 0.008), specificity (63.29% vs. 76.59%, p = 0.017) and PPV (64.95% vs. 75.23%, p = 0.006).

Conclusions: The results of this study demonstrate that the developed AI system is highly effective in automatically recognizing SESCC, displaying impressive diagnostic performance, and exhibiting strong generalizability. Furthermore, when used as an assistant in the diagnosis process, the system improved manual diagnostic performance.

Abstract

Grants and funding