Home    中文  
 
  • Search
  • lucene Search
  • Citation
  • Fig/Tab
  • Adv Search
Just Accepted  |  Current Issue  |  Archive  |  Featured Articles  |  Most Read  |  Most Download  |  Most Cited

Chinese Journal of Laparoscopic Surgery(Electronic Edition) ›› 2024, Vol. 17 ›› Issue (05): 290-294. doi: 10.3877/cma.j.issn.1674-6899.2024.05.007

• Original Articles • Previous Articles     Next Articles

Clinical application of laparoscopic intraoperative ultrasound automatic main pancreatic ductidentificationmod

Yi Zhao1, Changtian Li2, Wenbo Tang2, Xueting Bai2, Rong Liu2,()   

  1. 1.Medical School of Chinese PLA,Beijing 100853,China
    2.Department of Hepatobiliary and Pancreatic Surgery,The First Medical Center of PLA General Hospital,Beijing 100853,China
  • Received:2024-09-27 Online:2024-10-30 Published:2024-12-03
  • Contact: Rong Liu

Abstract:

Objective

To summarize and analyze the application of the deep learning intraoperative ultrasound(IOUS) main pancreatic duct automatic recognition model in IOUS skill training for surgeons and assisting in the locating of the main pancreatic duct in minimally invasive pancreatic surgery.

Methods

Use the main pancreatic duct automatic recognition model to assist 18 trainees in learning the recognition of IOUS main pancreatic duct images and collect examination data; Prospectively enroll 120 cases of minimally invasive pancreatic surgery that plan to use IOUS to locate the main pancreatic duct. For surgical patients,an automatic main pancreatic duct recognition model was used to assist in locating the main pancreatic duct during the operation. IOUS operation time, main pancreatic duct positioning success rate and baseline data were collected for analysis.

Results

For trainees, model-assisted examination can improve accuracy and answer time (100% vs. 86%,P<0.05, 6.6 min vs. 14.1 mins, P<0.05); Compared with the control group that does not use models, using deep learning model can improve the IOUS operation time (8.8 min vs. 13.6 min, P<0.05) and localization success rate (96.6% vs. 81.6%,P<0.05).

Conclusion

The deep learning IOUS main pancreatic duct automatic recognition model based on deep learning can help surgeons master IOUS skills faster and better, and can improve the speed and success rate of locating main pancreatic duct, assisting in safe and effective minimally invasive pancreatic surgery.

Key words: Pancreas, Minimally invasive surgery, Intraoperative ultrasound, Main pancreatic duct, Deep learning model

京ICP 备07035254号-20
Copyright © Chinese Journal of Laparoscopic Surgery(Electronic Edition), All Rights Reserved.
Tel: 01066937562 E-mail: zhonghuaqiangjing@126.com
Powered by Beijing Magtech Co. Ltd