Feasibility of real-time artificial intelligence-assisted anatomical structure recognition during endoscopic submucosal dissection

Markus Wolfgang Scheppach; Hon Chi Yip; Yueyao Chen; Hongzheng Yang; Jianfeng Cao; Tiffany Chua; Qi Dou; Helen Mei Ling Meng; Yeung Yam; Philip W Chiu

doi:10.1055/a-2615-8008

Feasibility of real-time artificial intelligence-assisted anatomical structure recognition during endoscopic submucosal dissection

Endosc Int Open. 2025 Jun 17:13:a26158008. doi: 10.1055/a-2615-8008. eCollection 2025.

Authors

Markus Wolfgang Scheppach^{1

2

3}, Hon Chi Yip^{2

3}, Yueyao Chen⁴, Hongzheng Yang⁴, Jianfeng Cao⁴, Tiffany Chua^{5

3}, Qi Dou⁴, Helen Mei Ling Meng⁶, Yeung Yam⁷, Philip W Chiu^{2

3}

Affiliations

¹ Internal Medicine III - Gastroenterology, University of Augsburg Faculty of Medicine, Augsburg, Germany.
² Department of Surgery, Faculty of Medicine, The Chinese University of Hong Kong, Hong Kong SAR.
³ Institute of Digestive Disease, Faculty of Medicine, The Chinese University of Hong Kong, New Territories, Hong Kong SAR.
⁴ Department of Computer Science and Engineering, Faculty of Engineering, The Chinese University of Hong Kong, Hong Kong SAR.
⁵ Division of Gastroenterology, Hepatology & Nutrition, Department of Medicine, College of Medicine, University of Florida, Gainesville, United States.
⁶ Department of Systems Engineering and Engineering Management, Faculty of Engineering, The Chinese University of Hong Kong, Hong Kong SAR.
⁷ Department of Mechanical and Automation Engineering, Faculty of Engineering, the Chinese University of Hong Kong, Hong Kong SAR.

Abstract

Background and study aims: Endoscopic submucosal dissection (ESD) is a challenging minimally invasive resection technique with a long training period and relevant operator-dependent complications. Real-time artificial intelligence (AI) orientation support may improve safety and intervention speed.

Methods: A total of 1011 endoscopic still images from 30 ESDs were annotated for relevant anatomical structures and used for training of a deep learning algorithm. After internal and external validation, this algorithm was applied to 12 ESDs performed by either one expert or one novice in ESD using an in vivo porcine model.

Results: External validation yielded mean Dice Scores of 88%, 60%, 58%, and 92% for background, submucosal layer, submucosal blood vessels, and muscle layer, respectively. The system was successfully applied during all 12 ESDs. All resections were completed en bloc and without complications.

Conclusions: In this proof-of-concept study, feasibility of a real-time AI algorithm for anatomical structure delineation and orientation support during ESD was evaluated. The application proved safe and appropriate for routine procedures in humans. Further studies are needed to elucidate a potential clinical benefit of this new technology.

Keywords: Endoscopic resection (ESD, EMRc, ...); Endoscopic resection (polypectomy, ESD, EMRc, ...); Endoscopy Lower GI Tract; Endoscopy Upper GI Tract; Precancerous conditions & cancerous lesions (displasia and cancer) stomach.

The Author(s). This is an open access article published by Thieme under the terms of the Creative Commons Attribution License, permitting unrestricted use, distribution, and reproduction so long as the original work is properly cited. (https://creativecommons.org/licenses/by/4.0/).