EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Using neural networks to autonomously assess adequacy in intraoperative cholangiograms

Henry Badgery iD, Yuning Zhou, James Bailey, Peter Brotchie, Lynn Chong, Daniel Croagh, Mark Page, Catherine E Davey, Matthew Read

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.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

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)

CholangiographyNeural Networks, ComputerCholecystectomy, LaparoscopicHumansIntraoperative CareBile DuctsAlgorithms

Stichwörter der Autor:innen

Artificial intelligenceCholangiogramConvolutional neural networkLaparoscopic cholecystectomy

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}
}
Kostenlos starten →