Journal
ANNALS OF SURGERY
Volume 276, Issue 2, Pages 363-369Publisher
LIPPINCOTT WILLIAMS & WILKINS
DOI: 10.1097/SLA.0000000000004594
Keywords
artificial intelligence; bile duct injury; cholecystectomy; Convolutional neural network; deep learning; deep neural network; go zone; machine learning; no-go zone; patient safety
Categories
Funding
- Olympus
Ask authors/readers for more resources
This study developed and evaluated artificial intelligence models that can identify safe and dangerous zones, as well as anatomical landmarks, during laparoscopic cholecystectomy (LC). The models showed promising results in accurately identifying these areas, indicating the potential for real-time guidance in surgery to minimize adverse events.
Objective: The aim of this study was to develop and evaluate the performance of artificial intelligence (AI) models that can identify safe and dangerous zones of dissection, and anatomical landmarks during laparoscopic cholecystectomy (LC). Summary Background Data: Many adverse events during surgery occur due to errors in visual perception and judgment leading to misinterpretation of anatomy. Deep learning, a subfield of AI, can potentially be used to provide real-time guidance intraoperatively. Methods: Deep learning models were developed and trained to identify safe (Go) and dangerous (No-Go) zones of dissection, liver, gallbladder, and hepatocystic triangle during LC. Annotations were performed by 4 high-volume surgeons. AI predictions were evaluated using 10-fold cross-validation against annotations by expert surgeons. Primary outcomes were intersection- over-union (IOU) and F1 score (validated spatial correlation indices), and secondary outcomes were pixel-wise accuracy, sensitivity, specificity, +/- standard deviation. Results: AI models were trained on 2627 random frames from 290 LC videos, procured from 37 countries, 136 institutions, and 153 surgeons. Mean IOU, F1 score, accuracy, sensitivity, and specificity for the AI to identify Go zones were 0.53 (+/- 0.24), 0.70 (+/- 0.28), 0.94 (+/- 0.05), 0.69 (+/- 0.20). and 0.94 (+/- 0.03), respectively. For No-Go zones, these metrics were 0.71 (+/- 0.29), 0.83 (+/- 0.31), 0.95 (+/- 0.06), 0.80 (+/- 0.21), and 0.98 (+/- 0.05), respectively. Mean IOU for identification of the liver, gallbladder, and hepatocystic triangle were: 0.86 (+/- 0.12), 0.72 (+/- 0.19), and 0.65 (+/- 0.22), respectively. Conclusions: AI can be used to identify anatomy within the surgical field. This technology may eventually be used to provide real-time guidance and minimize the risk of adverse events.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available