A benchmark for video-based laparoscopic skill analysis and assessment

2026-02-10

AI Summary

This work addresses the challenge of automated laparoscopic surgical skill assessment, which has been hindered by the scarcity of large-scale annotated datasets. To this end, we introduce LASANA, a novel dataset comprising 1,270 stereoscopic video clips capturing a naturally distributed range of surgical proficiency levels. Each clip is annotated with structured skill scores and task-specific error labels provided by multiple expert raters. LASANA constitutes the first large-scale, multi-rater benchmark in this domain, accompanied by standardized train/validation/test splits and baseline deep learning models. The dataset enables the development and fair comparison of algorithms for both skill evaluation and error detection, establishing a reproducible evaluation framework to support future research in surgical AI.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Natural Language Processing: Safety and Robustness
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Security and Privacy: Large-scale security measurements

Abstract

Laparoscopic surgery is a complex surgical technique that requires extensive training. Recent advances in deep learning have shown promise in supporting this training by enabling automatic video-based assessment of surgical skills. However, the development and evaluation of deep learning models is currently hindered by the limited size of available annotated datasets. To address this gap, we introduce the Laparoscopic Skill Analysis and Assessment (LASANA) dataset, comprising 1270 stereo video recordings of four basic laparoscopic training tasks. Each recording is annotated with a structured skill rating, aggregated from three independent raters, as well as binary labels indicating the presence or absence of task-specific errors. The majority of recordings originate from a laparoscopic training course, thereby reflecting a natural variation in the skill of participants. To facilitate benchmarking of both existing and novel approaches for video-based skill assessment and error recognition, we provide predefined data splits for each task. Furthermore, we present baseline results from a deep learning model as a reference point for future comparisons.

Problem

• laparoscopic surgery
• surgical skill assessment
• video-based analysis
• annotated dataset
• benchmark

Innovation

• laparoscopic skill assessment
• video-based benchmark
• surgical training dataset
• deep learning for surgery
• error recognition