CATARACTS: Challenge on automatic tool annotation for cataRACT surgery

• Tipo: Artigo em Revista Científica Internacional
• Data: 2019

Autores

Hassan Al Hajj (Autor) Outra; Mathieu Lamard (Autor) Outra; Pierre-Henri Conze (Autor) Outra; Soumali Roychowdhury (Autor) Outra; Xiaowei Hu (Autor) Outra; Gabija Mar¨alkaite (Autor) Outra; Odysseas Zisimopoulos (Autor) Outra; Muneer Ahmad Dedmari (Autor) Outra; Fenqiang Zhao (Autor) Outra; Jonas Prellberg (Autor) Outra; Manish Sahu (Autor) Outra; Adrian Galdran (Autor) Outra; Teresa Araújo (Autor) Outra; Duc My Vo (Autor) Outra; Chandan Panda (Autor) Outra; Navdeep Dahiya (Autor) Outra; Satoshi Kondo (Autor) Outra; Zhengbing Bian (Autor) Outra; Arash Vahdat (Autor) Outra; Jonas Bialopetravicius (Autor) Outra; Evangello Flouty (Autor) Outra; Chenhui Qiu (Autor) Outra; Sabrina Dill (Autor) Outra; Anirban Mukhopadhyay (Autor) Outra; Pedro Costa (Autor) Outra; Guilherme Aresta (Autor) Outra; Senthil Ramamurthy (Autor) Outra; Sang-Woong Lee (Autor) Outra; Aurélio Campilho (Autor) FEUP; Stefan Zachow (Autor) Outra; Shunren Xia (Autor) Outra; Sailesh Conjeti (Autor) Outra; Danail Stoyanov (Autor) Outra; Jogundas Armaitis (Autor) Outra; Pheng-Ann Henge (Autor) Outra; William G. Macready (Autor) Outra; Béatrice Cochener (Autor) Outra; Gwenolé Quellec (Autor) Outra

Revista

Título: Medical Image Analysis

Vol. 52

Páginas: 24-41

ISSN: 1361-8415

Editora: Elsevier

Indexação

ISI Web of Knowledge - 0 Citações

Scopus - 1 Citação

Outras Informações

ID Authenticus: P-00P-X1V

DOI: 10.1016/j.media.2018.11.008

Abstract (EN): 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 laparoscopic 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, 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.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 18