Comparative Validation of Polyp Detection Methods in Video Colonoscopy : Results from the MICCAI 2015 Endoscopic Vision Challenge
Bernal del Nozal, Jorge (Universitat Autònoma de Barcelona)
Tajkbaksh, Nima (Arizona State University)
Sánchez, F. Javier (Centre de Visió per Computador)
Matuszewski, Bogdan J. (University of Central Lancashire)
Chen, Hao (The Chinese University of Hong Kong. Department of Computer Science and Engineering)
Yu, Lequan (The Chinese University of Hong Kong. Department of Computer Science and Engineering)
Angermann, Quentin (University of Cergy-Pontoise)
Romain, Olivier (University of Cergy-Pontoise)
Rustad, Bjørn (Oslo University Hospital (Oslo, Noruega))
Balasingham, Ilangko (Oslo University Hospital (Oslo, Noruega))
Pogorelov, Konstantin (University of Oslo)
Choi, Sungbin (Seoul National University)
Debard, Quentin (University of Nice-Sophia Antipolis)
Maier-Hein, Lena (German Cancer Research Center (DKFZ))
Speidel, Stefanie (Karlsruhe Institute of Technology. Institute for Anthropomatics)
Stoyanov, Danail (University College London. Department of Computer Science)
Brandao, Patrick (University College London. Department of Computer Science)
Córdova, Henry (Hospital Clínic i Provincial de Barcelona)
Sánchez-Montes, Cristina (Hospital Clínic i Provincial de Barcelona)
Gurudu, Suryakanth R. (Mayo Clinic. Division of Gastroenterology and Hepatology)
Fernández-Esparrach, Gloria (Hospital Clínic i Provincial de Barcelona)
Dray, Xavier (University of Cergy-Pontoise)
Liang, Jianming (Arizona State University)
Histace, Aymeric (University of Cergy-Pontoise)

Date:	2017
Abstract:	Colonoscopy is the gold standard for colon cancer screening though some polyps are still missed, thus preventing early disease detection and treatment. Several computational systems have been proposed to assist polyp detection during colonoscopy but so far without consistent evaluation. The lack of publicly available annotated databases has made it difficult to compare methods and to assess if they achieve performance levels acceptable for clinical use. The Automatic Polyp Detection sub-challenge, conducted as part of the Endoscopic Vision Challenge (http://endovis. grand-challenge. org) at the international conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) in 2015, was an effort to address this need. In this paper, we report the results of this comparative evaluation of polyp detection methods, as well as describe additional experiments to further explore differences between methods. We define performance metrics and provide evaluation databases that allow comparison of multiple methodologies. Results show that convolutional neural networks are the state of the art. Nevertheless, it is also demonstrated that combining different methodologies can lead to an improved overall performance.
Grants:	Ministerio de Economía y Competitividad DPI2015-65286-R Generalitat de Catalunya 2014/SGR-1470 Generalitat de Catalunya 2014/SGR-135 European Commission 37960
Rights:	Aquest material està protegit per drets d'autor i/o drets afins. Podeu utilitzar aquest material en funció del que permet la legislació de drets d'autor i drets afins d'aplicació al vostre cas. Per a d'altres usos heu d'obtenir permís del(s) titular(s) de drets.
Language:	Anglès
Document:	Article ; recerca ; Versió acceptada per publicar
Subject:	Endoscopic vision ; Polyp detection ; Handcrafted features ; Machine learning ; Validation framework
Published in:	IEEE Transactions on Medical Imaging, Vol. 36, Num. 6 (June 2017) , p. 1231-1249, ISSN 1558-254X

DOI: 10.1109/TMI.2017.2664042

Postprint 18 p, 7.6 MB

The record appears in these collections:
Articles > Research articles
Articles > Published articles