CATARACTS

用于手术工作流分析的自动工具注释
手术工具检测越来越受到医学图像处理界的关注 [1]。目标通常不是精确地定位图像中的工具，而是指示外科医生在每个瞬间正在使用哪些工具。注释工具使用的主要动机是为手术工作流分析设计有效的解决方案。分析手术工作流程在报告生成，手术培训甚至实时决策支持方面都有潜在的应用。

白内障手术
大多数现有的工具注释算法都集中在腹腔镜手术上 [1]。然而，世界上最常见的外科手术是白内障手术: 每年进行1900万白内障手术 [2]。白内障是眼睛内部的晶状体混浊，导致视力下降。手术的目的是切除这个晶状体，并用人工晶状体代替。整个过程只能用小切口进行。在离开眼睛之前，天然晶状体确实在高频超声设备的帮助下被切成小块。至于人工晶状体，在进入眼睛之前，它会在注射器内卷起。手术通常持续15分钟。在手术过程中，患者的眼睛在显微镜下，显微镜的输出被视频记录。

这项挑战的目的
组织此挑战是为了在白内障手术的特定背景下评估现有和新的工具注释算法。它依赖于来自50个白内障手术的9个多小时的视频，其中21个手术工具的存在由两名专家手动注释。我们希望这次比赛能激发对该程序的自动工具注释的研究。

请注意，此竞赛与会议无关。它将开放八个月 (从2017年4月1日到2017年11月30日)。在此期间结束时，将邀请十大算法的设计者为联合期刊论文做出贡献，以描述和总结所使用的方法以及挑战中的结果。该论文将提交给该领域的高影响力期刊。

Automatic Tool Annotation for Surgical Workflow Analysis

Surgical tool detection has attracted increasing attention from the medical image processing community [1]. The goal is typically not to precisely localize tools in images, but rather to indicate which surgical tools the surgeon is using at each moment. The primary motivation for annotating tool usage is to design effective solutions for surgical workflow analysis. Analyzing surgical workflows has potential applications in report generation, surgical training, and even real-time decision support.

Cataract Surgery
Most existing tool annotation algorithms focus on laparoscopic surgery [1]. However, the most common surgical procedure worldwide is cataract surgery, with 19 million cataract surgeries performed annually [2]. A cataract is the clouding of the eye's internal lens, which causes vision impairment. The goal of the surgery is to remove this lens and replace it with an intraocular lens (IOL). The entire procedure is performed exclusively through small incisions. Before being removed from the eye, the natural lens is first broken into small pieces with the help of high-frequency ultrasonic equipment. As for the intraocular lens, it is rolled up inside a syringe prior to being inserted into the eye. The procedure typically lasts 15 minutes. During the surgery, the patient's eye is placed under a surgical microscope, and the output of the microscope is recorded via video.

Purpose of This Challenge
This challenge was organized to evaluate both existing and novel tool annotation algorithms in the specific context of cataract surgery. It relies on over 9 hours of video from 50 cataract surgeries, where the presence of 21 surgical tools was manually annotated by two experts. We hope this competition will inspire research into automatic tool annotation for this procedure.

Please note that this competition is not affiliated with any conference. It will be open for eight months, from April 1, 2017, to November 30, 2017. At the end of this period, the designers of the top ten algorithms will be invited to contribute to a joint journal paper that describes and summarizes the methods used and the results obtained in the challenge. This paper will be submitted to a high-impact journal in this field.

搜集汇总

背景与挑战

背景概述

CATARACTS是一个白内障手术视频数据集，包含50个手术的9小时视频和21个手术工具的手动标注，旨在支持手术工具注释算法的研究和工作流分析应用。