Early Operative Difficulty Assessment in Laparoscopic Cholecystectomy via Snapshot-Centric Video Analysis

TL;DR

This paper introduces SurgPrOD, a deep learning model that assesses early operative difficulty in laparoscopic cholecystectomy videos using snapshot-centric analysis, improving prediction accuracy and establishing a new benchmark.

Contribution

It presents a novel deep learning approach with a snapshot-centric attention module for early LCOD assessment and introduces the CholeScore dataset for validation.

Findings

SurgPrOD outperforms baseline models in F1 score and accuracy.

The model achieves at least 0.22 points higher on early prediction metrics.

It establishes a new benchmark for intraoperative video-based LCOD assessment.

Abstract

Purpose: Laparoscopic cholecystectomy (LC) operative difficulty (LCOD) is highly variable and influences outcomes. Despite extensive LC studies in surgical workflow analysis, limited efforts explore LCOD using intraoperative video data. Early recognition of LCOD could allow prompt review by expert surgeons, enhance operating room (OR) planning, and improve surgical outcomes. Methods: We propose the clinical task of early LCOD assessment using limited video observations. We design SurgPrOD, a deep learning model to assess LCOD by analyzing features from global and local temporal resolutions (snapshots) of the observed LC video. Also, we propose a novel snapshot-centric attention (SCA) module, acting across snapshots, to enhance LCOD prediction. We introduce the CholeScore dataset, featuring video-level LCOD labels to validate our method. Results: We evaluate SurgPrOD on 3 LCOD assessment scales in the CholeScore dataset. On our new metric assessing early and stable correct predictions, SurgPrOD surpasses baselines by at least 0.22 points. SurgPrOD improves over baselines by at least 9 and 5 percentage points in F1 score and top1-accuracy, respectively, demonstrating its effectiveness in correct predictions. Conclusion: We propose a new task for early LCOD assessment and a novel model, SurgPrOD analyzing surgical video from global and local perspectives. Our results on the CholeScore dataset establishes a new benchmark to study LCOD using intraoperative video data.