A Comprehensive Video Dataset for Surgical Laparoscopic Action Analysis

Abstract Laparoscopic surgery has been widely used in various surgical fields due to its minimally invasive and rapid recovery benefits. However, it demands a high level of technical expertise from surgeons. While advancements in computer vision and deep learning have significantly contributed to su...

Full description

Saved in:
Bibliographic Details
Main Authors: Zi Ye, Ru Zhou, Zili Deng, Dan Wang, Ying Zhu, Xiaoli Jin, Lijun Zhang, Tianxiang Chen, Hanwei Zhang, Mingliang Wang
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Data
Online Access:https://doi.org/10.1038/s41597-025-05093-7
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849325737358655488
author Zi Ye
Ru Zhou
Zili Deng
Dan Wang
Ying Zhu
Xiaoli Jin
Lijun Zhang
Tianxiang Chen
Hanwei Zhang
Mingliang Wang
author_facet Zi Ye
Ru Zhou
Zili Deng
Dan Wang
Ying Zhu
Xiaoli Jin
Lijun Zhang
Tianxiang Chen
Hanwei Zhang
Mingliang Wang
author_sort Zi Ye
collection DOAJ
description Abstract Laparoscopic surgery has been widely used in various surgical fields due to its minimally invasive and rapid recovery benefits. However, it demands a high level of technical expertise from surgeons. While advancements in computer vision and deep learning have significantly contributed to surgical action recognition, the effectiveness of these technologies is hindered by the limitations of existing publicly available datasets, such as their small scale, high homogeneity, and inconsistent labeling quality. To address the above issues, we developed the SLAM dataset (Surgical LAparoscopic Motions), which encompasses various surgical types such as laparoscopic cholecystectomy and appendectomy. The dataset includes annotations for seven key actions: Abdominal Entry, Use Clip, Hook Cut, Suturing, Panoramic View, Local Panoramic View, and Suction. In total, it includes 4,097 video clips, each labeled with corresponding action categories. In addition, we comprehensively validated the dataset using the ViViT model, and the experimental results showed that the dataset exhibited superior training and testing capabilities in laparoscopic surgical action recognition, with the highest classification accuracy of 85.90%. As a publicly available benchmark resource, the SLAM dataset aims to promote the development of laparoscopic surgical action recognition and artificial intelligence-driven surgery, supporting intelligent surgical robots and surgical automation.
format Article
id doaj-art-8eb5f0e165d94e0c9cb6bc1bfb1519e3
institution Kabale University
issn 2052-4463
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Data
spelling doaj-art-8eb5f0e165d94e0c9cb6bc1bfb1519e32025-08-20T03:48:19ZengNature PortfolioScientific Data2052-44632025-05-0112111010.1038/s41597-025-05093-7A Comprehensive Video Dataset for Surgical Laparoscopic Action AnalysisZi Ye0Ru Zhou1Zili Deng2Dan Wang3Ying Zhu4Xiaoli Jin5Lijun Zhang6Tianxiang Chen7Hanwei Zhang8Mingliang Wang9Department of General Surgery, RuiJin Hospital LuWan Branch, Shanghai Jiaotong University School of MedicineDepartment of General Surgery, RuiJin Hospital LuWan Branch, Shanghai Jiaotong University School of MedicineHangzhou Institute for Advanced Study, University of Chinese Academy of SciencesHangzhou Institute for Advanced Study, University of Chinese Academy of SciencesHangzhou Institute for Advanced Study, University of Chinese Academy of SciencesDepartment of General Surgery, RuiJin Hospital LuWan Branch, Shanghai Jiaotong University School of MedicineInstitute of Software, Chinese Academy of SciencesSchool of Cyber Space and Technology, University of Science and Technology of ChinaInstitute of Intelligent Software, GuangzhouDepartment of General Surgery, RuiJin Hospital LuWan Branch, Shanghai Jiaotong University School of MedicineAbstract Laparoscopic surgery has been widely used in various surgical fields due to its minimally invasive and rapid recovery benefits. However, it demands a high level of technical expertise from surgeons. While advancements in computer vision and deep learning have significantly contributed to surgical action recognition, the effectiveness of these technologies is hindered by the limitations of existing publicly available datasets, such as their small scale, high homogeneity, and inconsistent labeling quality. To address the above issues, we developed the SLAM dataset (Surgical LAparoscopic Motions), which encompasses various surgical types such as laparoscopic cholecystectomy and appendectomy. The dataset includes annotations for seven key actions: Abdominal Entry, Use Clip, Hook Cut, Suturing, Panoramic View, Local Panoramic View, and Suction. In total, it includes 4,097 video clips, each labeled with corresponding action categories. In addition, we comprehensively validated the dataset using the ViViT model, and the experimental results showed that the dataset exhibited superior training and testing capabilities in laparoscopic surgical action recognition, with the highest classification accuracy of 85.90%. As a publicly available benchmark resource, the SLAM dataset aims to promote the development of laparoscopic surgical action recognition and artificial intelligence-driven surgery, supporting intelligent surgical robots and surgical automation.https://doi.org/10.1038/s41597-025-05093-7
spellingShingle Zi Ye
Ru Zhou
Zili Deng
Dan Wang
Ying Zhu
Xiaoli Jin
Lijun Zhang
Tianxiang Chen
Hanwei Zhang
Mingliang Wang
A Comprehensive Video Dataset for Surgical Laparoscopic Action Analysis
Scientific Data
title A Comprehensive Video Dataset for Surgical Laparoscopic Action Analysis
title_full A Comprehensive Video Dataset for Surgical Laparoscopic Action Analysis
title_fullStr A Comprehensive Video Dataset for Surgical Laparoscopic Action Analysis
title_full_unstemmed A Comprehensive Video Dataset for Surgical Laparoscopic Action Analysis
title_short A Comprehensive Video Dataset for Surgical Laparoscopic Action Analysis
title_sort comprehensive video dataset for surgical laparoscopic action analysis
url https://doi.org/10.1038/s41597-025-05093-7
work_keys_str_mv AT ziye acomprehensivevideodatasetforsurgicallaparoscopicactionanalysis
AT ruzhou acomprehensivevideodatasetforsurgicallaparoscopicactionanalysis
AT zilideng acomprehensivevideodatasetforsurgicallaparoscopicactionanalysis
AT danwang acomprehensivevideodatasetforsurgicallaparoscopicactionanalysis
AT yingzhu acomprehensivevideodatasetforsurgicallaparoscopicactionanalysis
AT xiaolijin acomprehensivevideodatasetforsurgicallaparoscopicactionanalysis
AT lijunzhang acomprehensivevideodatasetforsurgicallaparoscopicactionanalysis
AT tianxiangchen acomprehensivevideodatasetforsurgicallaparoscopicactionanalysis
AT hanweizhang acomprehensivevideodatasetforsurgicallaparoscopicactionanalysis
AT mingliangwang acomprehensivevideodatasetforsurgicallaparoscopicactionanalysis
AT ziye comprehensivevideodatasetforsurgicallaparoscopicactionanalysis
AT ruzhou comprehensivevideodatasetforsurgicallaparoscopicactionanalysis
AT zilideng comprehensivevideodatasetforsurgicallaparoscopicactionanalysis
AT danwang comprehensivevideodatasetforsurgicallaparoscopicactionanalysis
AT yingzhu comprehensivevideodatasetforsurgicallaparoscopicactionanalysis
AT xiaolijin comprehensivevideodatasetforsurgicallaparoscopicactionanalysis
AT lijunzhang comprehensivevideodatasetforsurgicallaparoscopicactionanalysis
AT tianxiangchen comprehensivevideodatasetforsurgicallaparoscopicactionanalysis
AT hanweizhang comprehensivevideodatasetforsurgicallaparoscopicactionanalysis
AT mingliangwang comprehensivevideodatasetforsurgicallaparoscopicactionanalysis