An artificial intelligence model developed for marking detection and incision guidance during esophageal endoscopic submucosal dissection (ESD) demonstrated promising performance. Compared to junior endoscopists, the AI achieved a notable accuracy of 63.21%, precision rates of up to 85.76%, and an average distance error of 0.096, significantly outperforming junior practitioners while matching senior endoscopists. These results suggest the model could enhance the safety and effectiveness of minimally invasive treatments for early esophageal cancer.
Journal Article by Liu R, Yuan X (…) Hu B et 12 al. in Surg Endosc
© 2025. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.