Artificial Intelligence‐Guided Total Mesorectal Excision: Development of a Deep Learning Model to Identify the Pelvic Fascial Plane Anatomy
Open Access
- 9 July 2025
- journal article
- Published by Wiley in Annals of Gastroenterological Surgery
- Vol. 9 (6) , 1225-1232
Abstract
Aim: Total mesorectal excision entails dissection of the “holy plane” without damaging the mesorectal and parietal pelvic fasciae. We aimed to train a deep learning model to identify the anatomical landmarks of the pelvic fascial surface during total mesorectal excision and evaluate its performance to validate artificial intelligence‐guided total mesorectal excision. Methods: In this single‐center, retrospective, observational study, a deep learning model that can automatically identify the anatomical landmarks in the pelvic fascial plane during laparoscopic total mesorectal excision in real time was developed. Target anatomical landmarks included the mesorectal fascia, parietal pelvic fascia, and the holy plane between them. Feature Pyramid Networks and EfficientNetB7 were adopted as the neural network architecture and backbone network, respectively. The surgical videos used for training and validation data were different. The Dice Similarity Coefficient, recall, and Normalized Surface Dice, which were calculated using five‐fold cross‐validation, were used as the evaluation metrics. Results: Overall, 2861 images from 157 surgical videos were annotated and used for the training and validation datasets. In the semantic segmentation task, the Dice Similarity Coefficients for the mesorectal fascia, parietal pelvic fascia, and holy plane were 90.4%, 90.6%, and 68.5%, respectively. The Normalized Surface Dices for the three fasciae were 70.4%, 73.2%, and 54.6%, respectively. Conclusions: We constructed a deep learning model that recognizes three regions for total mesorectal excision—the mesorectal fascia, parietal pelvic fascia, and intervening holy plane—with a relatively high Dice Similarity Coefficient, successfully providing proof of concept for artificial intelligence‐guided total mesorectal excision.Keywords
Funding Information
- Terumo Foundation for Life Sciences and Arts (22‐T008)
This publication has 31 references indexed in Scilit:
- Real-time vascular anatomical image navigation for laparoscopic surgery: experimental studySurgical Endoscopy, 2022
- Optimising functional outcomes in rectal cancer surgeryLangenbeck's Archives of Surgery, 2020
- Grey areas and evidence gaps in the management of rectal cancer as revealed by comparing recommendations from clinical guidelinesCancer Treatment Reviews, 2020
- The Rise of Colorectal Cancer in Asia: Epidemiology, Screening, and ManagementCurrent Gastroenterology Reports, 2019
- Image-guided real-time navigation for transanal total mesorectal excision: a pilot studyTechniques in Coloproctology, 2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- World Medical Association Declaration of HelsinkiJAMA, 2013
- Initial results of MR-guided liver resection in a high-field open MRISurgical Endoscopy, 2010
- Usefulness of intraoperative magnetic resonance imaging for glioma surgery2006
- The mesorectum in rectal cancer surgery—the clue to pelvic recurrence?British Journal of Surgery, 1982