TY - JOUR
T1 - A comprehensive analysis of classification methods in gastrointestinal endoscopy imaging
AU - Jha, Debesh
AU - Ali, Sharib
AU - Hicks, Steven
AU - Thambawita, Vajira
AU - Borgli, Hanna
AU - Smedsrud, Pia H.
AU - de Lange, Thomas
AU - Pogorelov, Konstantin
AU - Wang, Xiaowei
AU - Harzig, Philipp
AU - Tran, Minh Triet
AU - Meng, Wenhua
AU - Hoang, Trung Hieu
AU - Dias, Danielle
AU - Ko, Tobey H.
AU - Agrawal, Taruna
AU - Ostroukhova, Olga
AU - Khan, Zeshan
AU - Atif Tahir, Muhammad
AU - Liu, Yang
AU - Chang, Yuan
AU - Kirkerød, Mathias
AU - Johansen, Dag
AU - Lux, Mathias
AU - Johansen, Håvard D.
AU - Riegler, Michael A.
AU - Halvorsen, Pål
N1 - Funding Information:
The research is partially funded by the PRIVATON project (#263248) and the Autocap project (#282315) from the Research Council of Norway (CRN). Our experiments were performed on the Experimental Infrastructure for Exploration of Exascale Computing (eX3) system, which is financially supported by CRN under contract 270053. D. Jha is funded by PRIVATON project and S. Ali is supported by the National Institute for Health Research (NIHR) Oxford Biomedical Research Centre (BRC). The views expressed are those of the author(s) and not necessarily those of the NHS, the NIHR or the Department of Health.
PY - 2021/5
Y1 - 2021/5
N2 - Gastrointestinal (GI) endoscopy has been an active field of research motivated by the large number of highly lethal GI cancers. Early GI cancer precursors are often missed during the endoscopic surveillance. The high missed rate of such abnormalities during endoscopy is thus a critical bottleneck. Lack of attentiveness due to tiring procedures, and requirement of training are few contributing factors. An automatic GI disease classification system can help reduce such risks by flagging suspicious frames and lesions. GI endoscopy consists of several multi-organ surveillance, therefore, there is need to develop methods that can generalize to various endoscopic findings. In this realm, we present a comprehensive analysis of the Medico GI challenges: Medical Multimedia Task at MediaEval 2017, Medico Multimedia Task at MediaEval 2018, and BioMedia ACM MM Grand Challenge 2019. These challenges are initiative to set-up a benchmark for different computer vision methods applied to the multi-class endoscopic images and promote to build new approaches that could reliably be used in clinics. We report the performance of 21 participating teams over a period of three consecutive years and provide a detailed analysis of the methods used by the participants, highlighting the challenges and shortcomings of the current approaches and dissect their credibility for the use in clinical settings. Our analysis revealed that the participants achieved an improvement on maximum Mathew correlation coefficient (MCC) from 82.68% in 2017 to 93.98% in 2018 and 95.20% in 2019 challenges, and a significant increase in computational speed over consecutive years.
AB - Gastrointestinal (GI) endoscopy has been an active field of research motivated by the large number of highly lethal GI cancers. Early GI cancer precursors are often missed during the endoscopic surveillance. The high missed rate of such abnormalities during endoscopy is thus a critical bottleneck. Lack of attentiveness due to tiring procedures, and requirement of training are few contributing factors. An automatic GI disease classification system can help reduce such risks by flagging suspicious frames and lesions. GI endoscopy consists of several multi-organ surveillance, therefore, there is need to develop methods that can generalize to various endoscopic findings. In this realm, we present a comprehensive analysis of the Medico GI challenges: Medical Multimedia Task at MediaEval 2017, Medico Multimedia Task at MediaEval 2018, and BioMedia ACM MM Grand Challenge 2019. These challenges are initiative to set-up a benchmark for different computer vision methods applied to the multi-class endoscopic images and promote to build new approaches that could reliably be used in clinics. We report the performance of 21 participating teams over a period of three consecutive years and provide a detailed analysis of the methods used by the participants, highlighting the challenges and shortcomings of the current approaches and dissect their credibility for the use in clinical settings. Our analysis revealed that the participants achieved an improvement on maximum Mathew correlation coefficient (MCC) from 82.68% in 2017 to 93.98% in 2018 and 95.20% in 2019 challenges, and a significant increase in computational speed over consecutive years.
KW - Artificial intelligence
KW - BioMedia 2019 grand challenge
KW - Computer-aided detection and diagnosis
KW - Gastrointestinal endoscopy challenges
KW - Medical imaging
KW - Medico Task 2017
KW - Medico Task 2018
UR - http://www.scopus.com/inward/record.url?scp=85102631146&partnerID=8YFLogxK
U2 - 10.1016/j.media.2021.102007
DO - 10.1016/j.media.2021.102007
M3 - Journal article
C2 - 33740740
AN - SCOPUS:85102631146
SN - 1361-8415
VL - 70
JO - Medical Image Analysis
JF - Medical Image Analysis
M1 - 102007
ER -
