Surgical data science for safe cholecystectomy: a protocol for segmentation of hepatocystic anatomy and assessment of the critical view of safety
This work addresses the need for reliable and reproducible deep learning models in surgical safety, though it is incremental as it focuses on annotation guidelines rather than novel model development.
The paper tackles the problem of inconsistent data and annotations in deep learning models for surgical video analysis, specifically for assessing the critical view of safety in laparoscopic cholecystectomy, by proposing a protocol, checklists, and visual examples to standardize annotations.
Minimally invasive image-guided surgery heavily relies on vision. Deep learning models for surgical video analysis could therefore support visual tasks such as assessing the critical view of safety (CVS) in laparoscopic cholecystectomy (LC), potentially contributing to surgical safety and efficiency. However, the performance, reliability and reproducibility of such models are deeply dependent on the quality of data and annotations used in their development. Here, we present a protocol, checklists, and visual examples to promote consistent annotation of hepatocystic anatomy and CVS criteria. We believe that sharing annotation guidelines can help build trustworthy multicentric datasets for assessing generalizability of performance, thus accelerating the clinical translation of deep learning models for surgical video analysis.