Using neural networks to autonomously assess adequacy in intraoperative cholangiograms
Surgical Endoscopy · 2024
DOI: 10.1007/s00464-024-10768-0 ↗Kurz gefasst
Fachartikel in der Zeitschrift Surgical Endoscopy, 2024. Verfasst von Henry Badgery und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Upper Gastrointestinal Surgery, St Vincent's Hospital Melbourne, Melbourne, Australia. henry.badgery@svha.org.au. Hauptthemen laut MEDLINE: Cholangiography, Neural Networks, Computer, Cholecystectomy, Laparoscopic. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Epworth Foundation, University of Melbourne.
Abstract (Originalsprache)
Background
Intraoperative cholangiography (IOC) is a contrast-enhanced X-ray acquired during laparoscopic cholecystectomy. IOC images the biliary tree whereby filling defects, anatomical anomalies and duct injuries can be identified. In Australia, IOC are performed in over 81% of cholecystectomies compared with 20 to 30% internationally (Welfare AIoHa in Australian Atlas of Healthcare Variation, 2017). In this study, we aim to train artificial intelligence (AI) algorithms to interpret anatomy and recognise abnormalities in IOC images. This has potential utility in (a) intraoperative safety mechanisms to limit the risk of missed ductal injury or stone, (b) surgical training and coaching, and (c) auditing of cholangiogram quality. Methodology Semantic segmentation masks were applied to a dataset of 1000 cholangiograms with 10 classes. Classes corresponded to anatomy, filling defects and the cholangiogram catheter instrument. Segmentation masks were applied by a surgical trainee and reviewed by a radiologist. Two convolutional neural networks (CNNs), DeeplabV3+ and U-Net, were trained and validated using 900 (90%) labelled frames. Testing was conducted on 100 (10%) hold-out frames. CNN generated segmentation class masks were compared with ground truth segmentation masks to evaluate performance according to a pixel-wise comparison.
Results
The trained CNNs recognised all classes.. U-Net and DeeplabV3+ achieved a mean F1 of 0.64 and 0.70 respectively in class segmentation, excluding the background class. The presence of individual classes was correctly recognised in over 80% of cases. Given the limited local dataset, these results provide proof of concept in the development of an accurate and clinically useful tool to aid in the interpretation and quality control of intraoperative cholangiograms.
Conclusion
Our results demonstrate that a CNN can be trained to identify anatomical structures in IOC images. Future performance can be improved with the use of larger, more diverse training datasets. Implementation of this technology may provide cholangiogram quality control and improve intraoperative detection of ductal injuries or ductal injuries. Graphical abstract
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Upper Gastrointestinal Surgery, St Vincent's Hospital Melbourne, Melbourne, Australia. henry.badgery@svha.org.au.
- Department of Surgery, The University of Melbourne, St Vincent's Hospital, 41 Victoria Parade, Fitzroy, Melbourne, VIC, 3065, Australia. henry.badgery@svha.org.au.
- Department of Biomedical Engineering, The University of Melbourne, Parkville, Australia.
- Graeme Clark Institute for Biomedical Engineering, The University of Melbourne, Melbourne, VIC, Australia.
- School of Computing and Information Systems, The University of Melbourne, Parkville, Australia.
- Department of Radiology, St Vincent's Hospital Melbourne, Melbourne, Australia.
ORCID-Profile: Henry Badgery
Förderung
- Epworth Foundation
- University of Melbourne
Zitieren
APA
Badgery, H., Zhou, Y., Bailey, J., Brotchie, P., Chong, L., Croagh, D., Page, M., Davey, C. E., & Read, M. (2024). Using neural networks to autonomously assess adequacy in intraoperative cholangiograms. Surgical Endoscopy. https://doi.org/10.1007/s00464-024-10768-0
Vancouver
Badgery H, Zhou Y, Bailey J, Brotchie P, Chong L, Croagh D, et al. Using neural networks to autonomously assess adequacy in intraoperative cholangiograms. Surgical Endoscopy. 2024. doi:10.1007/s00464-024-10768-0
BibTeX
@article{Badgery2024,
author = {Badgery, Henry and Zhou, Yuning and Bailey, James and Brotchie, Peter and Chong, Lynn and Croagh, Daniel and Page, Mark and Davey, Catherine E and Read, Matthew},
title = {Using neural networks to autonomously assess adequacy in intraoperative cholangiograms},
journal = {Surgical Endoscopy},
year = {2024},
doi = {10.1007/s00464-024-10768-0}
}
EUVIMED