CholecInstanceSeg: A Tool Instance Segmentation Dataset for Laparoscopic Surgery

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. Addit...

Full description

Saved in:
Bibliographic Details
Main Authors: Oluwatosin Alabi, Ko Ko Zayar Toe, Zijian Zhou, Charlie Budd, Nicholas Raison, Miaojing Shi, Tom Vercauteren
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Data
Online Access:https://doi.org/10.1038/s41597-025-05163-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849731974935085056
author Oluwatosin Alabi
Ko Ko Zayar Toe
Zijian Zhou
Charlie Budd
Nicholas Raison
Miaojing Shi
Tom Vercauteren
author_facet Oluwatosin Alabi
Ko Ko Zayar Toe
Zijian Zhou
Charlie Budd
Nicholas Raison
Miaojing Shi
Tom Vercauteren
author_sort Oluwatosin Alabi
collection DOAJ
description 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.
format Article
id doaj-art-fe782bbccb7d4643bd5ee7c4e5800afc
institution DOAJ
issn 2052-4463
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Data
spelling doaj-art-fe782bbccb7d4643bd5ee7c4e5800afc2025-08-20T03:08:22ZengNature PortfolioScientific Data2052-44632025-05-0112111210.1038/s41597-025-05163-wCholecInstanceSeg: A Tool Instance Segmentation Dataset for Laparoscopic SurgeryOluwatosin Alabi0Ko Ko Zayar Toe1Zijian Zhou2Charlie Budd3Nicholas Raison4Miaojing Shi5Tom Vercauteren6Kings College London, Surgical & Interventional EngineeringKings College Hospital Denmark Hill, departmentDepartment of Informatics, King’s College LondonKings College London, Surgical & Interventional EngineeringKings College London, Surgical & Interventional EngineeringTongji University, College of Electronic and Information EngineeringKings College London, Surgical & Interventional EngineeringAbstract 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.https://doi.org/10.1038/s41597-025-05163-w
spellingShingle Oluwatosin Alabi
Ko Ko Zayar Toe
Zijian Zhou
Charlie Budd
Nicholas Raison
Miaojing Shi
Tom Vercauteren
CholecInstanceSeg: A Tool Instance Segmentation Dataset for Laparoscopic Surgery
Scientific Data
title CholecInstanceSeg: A Tool Instance Segmentation Dataset for Laparoscopic Surgery
title_full CholecInstanceSeg: A Tool Instance Segmentation Dataset for Laparoscopic Surgery
title_fullStr CholecInstanceSeg: A Tool Instance Segmentation Dataset for Laparoscopic Surgery
title_full_unstemmed CholecInstanceSeg: A Tool Instance Segmentation Dataset for Laparoscopic Surgery
title_short CholecInstanceSeg: A Tool Instance Segmentation Dataset for Laparoscopic Surgery
title_sort cholecinstanceseg a tool instance segmentation dataset for laparoscopic surgery
url https://doi.org/10.1038/s41597-025-05163-w
work_keys_str_mv AT oluwatosinalabi cholecinstancesegatoolinstancesegmentationdatasetforlaparoscopicsurgery
AT kokozayartoe cholecinstancesegatoolinstancesegmentationdatasetforlaparoscopicsurgery
AT zijianzhou cholecinstancesegatoolinstancesegmentationdatasetforlaparoscopicsurgery
AT charliebudd cholecinstancesegatoolinstancesegmentationdatasetforlaparoscopicsurgery
AT nicholasraison cholecinstancesegatoolinstancesegmentationdatasetforlaparoscopicsurgery
AT miaojingshi cholecinstancesegatoolinstancesegmentationdatasetforlaparoscopicsurgery
AT tomvercauteren cholecinstancesegatoolinstancesegmentationdatasetforlaparoscopicsurgery