EgoSurgery-Tool: A Dataset of Surgical Tool and Hand Detection from Egocentric Open Surgery Videos (2024-06-05T00:00:00.000000Z)

TL;DR

EgoSurgery-Tool is introduced, an extension of the existing EgoSurgery-Phase dataset, which contains real open surgery videos captured using an egocentric camera attached to the surgeon's head, along with phase annotations, and is superior to existing datasets due to its larger scale, greater variety of surgical tools, more annotations, and denser scenes.

Abstract

Surgical tool detection is a fundamental task for understanding egocentric open surgery videos. However, detecting surgical tools presents significant challenges due to their highly imbalanced class distribution, similar shapes and similar textures, and heavy occlusion. The lack of a comprehensive large-scale dataset compounds these challenges. In this paper, we introduce EgoSurgery-Tool, an extension of the existing EgoSurgery-Phase dataset, which contains real open surgery videos captured using an egocentric camera attached to the surgeon's head, along with phase annotations. EgoSurgery-Tool has been densely annotated with surgical tools and comprises over 49K surgical tool bounding boxes across 15 categories, constituting a large-scale surgical tool detection dataset. EgoSurgery-Tool also provides annotations for hand detection with over 46K hand-bounding boxes, capturing hand-object interactions that are crucial for understanding activities in egocentric open surgery. EgoSurgery-Tool is superior to existing datasets due to its larger scale, greater variety of surgical tools, more annotations, and denser scenes. We conduct a comprehensive analysis of EgoSurgery-Tool using nine popular object detectors to assess their effectiveness in both surgical tool and hand detection. The dataset will be released at https://github.com/Fujiry0/EgoSurgery.

Authors

Ryo Fujii

2 papers

Hideo Saito

1 papers

Hiroyuki Kajita

1 papers

EgoSurgery-Tool: A Dataset of Surgical Tool and Hand Detection from Egocentric Open Surgery Videos

TL;DR

Abstract

Authors

References25 items

EgoSurgery-Phase: A Dataset of Surgical Phase Recognition from Egocentric Open Surgery Videos

Weakly Semi-Supervised Tool Detection in Minimally Invasive Surgery Videos

Analyzing Surgical Technique in Diverse Open Surgical Videos With Multitask Machine Learning.

Intuitive Surgical SurgToolLoc Challenge Results: 2022-2023

Dense Distinct Query for End-to-End Object Detection

Surgical Tool Detection in Open Surgery Videos

A semi-supervised Teacher-Student framework for surgical tool detection and localization

DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection

Using Computer Vision to Automate Hand Detection and Tracking of Surgeon Movements in Videos of Open Surgery

Sparse R-CNN: End-to-End Object Detection with Learnable Proposals

Deformable DETR: Deformable Transformers for End-to-End Object Detection

VarifocalNet: An IoU-aware Dense Object Detector

Understanding Human Hands in Contact at Internet Scale

Objects as Points

Weakly-Supervised Learning for Tool Localization in Laparoscopic Videos

Tool Detection and Operative Skill Assessment in Surgical Videos Using Region-Based Convolutional Neural Networks

Cascade R-CNN: Delving Into High Quality Object Detection

Focal Loss for Dense Object Detection

Detection and Localization of Robotic Tools in Robot-Assisted Surgery Videos Using Deep Neural Networks for Region Proposal and Detection

Lending A Hand: Detecting Hands and Recognizing Activities in Complex Egocentric Interactions

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Microsoft COCO: Common Objects in Context

Real-Time Surgical Tool Detection in Minimally Invasive Surgery Based on Attention-Guided Convolutional Neural Network

mmlab detection toolbox and benchmark

Hand detection using multiple proposals

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names