CholecInstanceSeg: A Tool Instance Segmentation Dataset for Laparoscopic Surgery

2024-06-23

arXiv.org

AI Summary

Existing laparoscopic surgical instrument instance segmentation datasets suffer from limited scale, sparse annotations, and predominant reliance on porcine models—failing to support algorithm development for real-world clinical settings. To address this, we introduce CholecInstanceSeg: the first large-scale, open benchmark dataset specifically designed for human laparoscopic cholecystectomy. It comprises 85 surgical videos (41.9k frames) with 64.4k high-quality instance-level annotations, each assigned a unique ID and accompanied by pixel-accurate semantic masks. Annotations were produced via multi-expert collaboration and rigorously validated using IoU-based statistical analysis and cross-model verification with Mask R-CNN. CholecInstanceSeg fills a critical gap in clinically relevant, human-surgery instrumentation benchmarks. Experiments demonstrate substantial improvements in localization accuracy and segmentation robustness under real surgical conditions, establishing a standardized foundation for both algorithm training and fair, reproducible evaluation.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: Crowd Sourcing and Human Computation

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

In laparoscopic and robotic surgery, precise tool instance segmentation is an essential technology for advanced computer-assisted interventions. Although publicly available procedures of routine surgeries exist, they often lack comprehensive annotations for tool instance segmentation. Additionally, the majority of standard datasets for tool segmentation are derived from porcine(pig) surgeries. To address this gap, we introduce CholecInstanceSeg, the largest open-access tool instance segmentation dataset to date. Derived from the existing CholecT50 and Cholec80 datasets, CholecInstanceSeg provides novel annotations for laparoscopic cholecystectomy procedures in patients. Our dataset comprises 41.9k annotated frames extracted from 85 clinical procedures and 64.4k tool instances, each labelled with semantic masks and instance IDs. To ensure the reliability of our annotations, we perform extensive quality control, conduct label agreement statistics, and benchmark the segmentation results with various instance segmentation baselines. CholecInstanceSeg aims to advance the field by offering a comprehensive and high-quality open-access dataset for the development and evaluation of tool instance segmentation algorithms.

Problem

• Lack of comprehensive tool instance segmentation annotations in laparoscopic surgery
• Existing datasets mainly from porcine surgeries, not human procedures
• Need for high-quality open-access dataset for algorithm development

Innovation

• Largest open-access tool instance segmentation dataset
• Comprehensive annotations for laparoscopic cholecystectomy procedures
• Extensive quality control and label agreement statistics