CATARACTS: Challenge on automatic tool annotation for cataRACT surgery
Hassan Al Hajj
(1)
,
Mathieu Lamard
(1, 2)
,
Pierre-Henri Conze
(1, 3, 4)
,
Soumali Roychowdhury
(5)
,
Xiaowei Hu
(5)
,
Gabija Maršalkait ˙ E F
,
Odysseas Zisimopoulos
,
Ahmad Dedmari
(6)
,
Fenqiang Zhao
,
Jonas Prellberg
,
Manish Sahu
,
Adrian Galdran
,
Teresa Araújo
,
Duc My Vo
,
Chandan Panda
,
Navdeep Dahiya
,
Satoshi Kondo
,
Zhengbing Bian
,
Arash Vahdat
,
Jonas Bialopetravičius
,
Evangello Flouty
,
Chenhui Qiu
,
Sabrina Dill
,
Anirban Mukhopadhyay
,
Pedro Costa
,
Guilherme Aresta
,
Senthil Ramamurthy
,
Sang-Woong Lee
,
Aurélio Campilho
,
Stefan Zachow
,
Shunren Xia
,
Sailesh Conjeti
,
Danail Stoyanov
,
Jogundas Armaitis
,
Pheng-Ann Heng
,
William G Macready
,
Béatrice Cochener
(1, 2, 7)
,
Gwenolé Quellec
(1)
1
INSERM -
Institut National de la Santé et de la Recherche Médicale
2 UBO - Université de Brest
3 IMT Atlantique - ITI - Département lmage et Traitement Information
4 LaTIM - Laboratoire de Traitement de l'Information Medicale
5 CUHK - The Chinese University of Hong Kong [Hong Kong]
6 TUM - Technische Universität Munchen - Technical University Munich - Université Technique de Munich
7 Service d'ophtalmologie [Brest]
2 UBO - Université de Brest
3 IMT Atlantique - ITI - Département lmage et Traitement Information
4 LaTIM - Laboratoire de Traitement de l'Information Medicale
5 CUHK - The Chinese University of Hong Kong [Hong Kong]
6 TUM - Technische Universität Munchen - Technical University Munich - Université Technique de Munich
7 Service d'ophtalmologie [Brest]
Pierre-Henri Conze
- Function : Author
- PersonId : 174700
- IdHAL : pierre-henri-conze
- ORCID : 0000-0003-2214-3654
- IdRef : 238573486
Gabija Maršalkait ˙ E F
- Function : Author
Odysseas Zisimopoulos
- Function : Author
Fenqiang Zhao
- Function : Author
Jonas Prellberg
- Function : Author
Manish Sahu
- Function : Author
Adrian Galdran
- Function : Author
Teresa Araújo
- Function : Author
- PersonId : 795073
- ORCID : 0000-0001-9687-528X
Duc My Vo
- Function : Author
Chandan Panda
- Function : Author
Navdeep Dahiya
- Function : Author
Satoshi Kondo
- Function : Author
Zhengbing Bian
- Function : Author
Arash Vahdat
- Function : Author
Jonas Bialopetravičius
- Function : Author
Evangello Flouty
- Function : Author
Chenhui Qiu
- Function : Author
Sabrina Dill
- Function : Author
Anirban Mukhopadhyay
- Function : Author
Pedro Costa
- Function : Author
- PersonId : 764176
- ORCID : 0000-0002-1993-6701
Guilherme Aresta
- Function : Author
Senthil Ramamurthy
- Function : Author
Sang-Woong Lee
- Function : Author
Aurélio Campilho
- Function : Author
Stefan Zachow
- Function : Author
Shunren Xia
- Function : Author
Sailesh Conjeti
- Function : Author
Danail Stoyanov
- Function : Author
Jogundas Armaitis
- Function : Author
Pheng-Ann Heng
- Function : Author
William G Macready
- Function : Author
Gwenolé Quellec
- Function : Author
- PersonId : 182433
- IdHAL : gwenole-quellec
- ORCID : 0000-0003-1669-7140
Abstract
Surgical tool detection is attracting increasing attention from the medical image analysis community. The goal generally is not to precisely locate tools in images, but rather to indicate which tools are being used by the surgeon at each instant. The main motivation for annotating tool usage is to design efficient solutions for surgical workflow analysis, with potential applications in report generation, surgical training and even real-time decision support. Most existing tool annotation algorithms focus on laparo-scopic surgeries. However, with 19 million interventions per year, the most common surgical procedure in the world is cataract surgery. The CATARACTS challenge was organized in 2017 to evaluate tool annotation algorithms in the specific context of cataract surgery. It relies on more than nine hours of videos, from 50 cataract surgeries, in which the presence of 21 surgical tools was manually annotated by two experts. With 14 participating teams, this challenge can be considered a success. As might be expected,-H. Conze et al. / Medical Image Analysis 52 (2019) 24-41 25 the submitted solutions are based on deep learning. This paper thoroughly evaluates these solutions: in particular, the quality of their annotations are compared to that of human interpretations. Next, lessons learnt from the differential analysis of these solutions are discussed. We expect that they will guide the design of efficient surgery monitoring tools in the near future.