Affiliation:
1. Department of Ultrasound Beijing Friendship Hospital Capital Medical University Beijing China
2. Department of Radiation Oncology (Maastro) GROW‐School for Oncology Maastricht University Medical Centre+ Maastricht The Netherlands
3. Department of Obstetrics and Gynecology Beijing Chao‐Yang Hospital Capital Medical University Beijing China
4. Zhejiang Cancer Hospital Institute of Basic Medicine and Cancer (IBMC) Chinese Academy of Sciences Hangzhou Zhejiang China
Abstract
AbstractBackgroundUreteral injury is common during gynaecological laparoscopic surgery. Real‐time auto‐segmentation can assist gynaecologists in identifying the ureter and reduce intraoperative injury risk.MethodsA deep learning segmentation model was crafted for ureter recognition in surgical videos, utilising 3368 frames from 11 laparoscopic surgeries. Class activation maps enhanced the model's interpretability, showing its areas. The model's clinical relevance was validated through an End‐User Turing test and verified by three gynaecological surgeons.ResultsThe model registered a Dice score of 0.86, a Hausdorff 95 distance of 22.60, and processed images in 0.008 s on average. In complex surgeries, it pinpointed the ureter's position in real‐time. Fifty five surgeons across eight institutions found the model's accuracy, specificity, and sensitivity comparable to human performance. Yet, artificial intelligence experience influenced some subjective ratings.ConclusionsThe model offers precise real‐time ureter segmentation in laparoscopic surgery and can be a significant tool for gynaecologists to mitigate ureteral injuries.
Subject
Computer Science Applications,Biophysics,Surgery