Comparative validation of polyp detection methods in video colonoscopy: Results from the MICCAI 2015 endoscopic vision challenge

Jorge Bernal, Nima Tajkbaksh, Francisco Javier Sánchez, Bogdan J. Matuszewski, Hao Chen, Lequan Yu, Quentin Angermann, Olivier Romain, Bjørn Rustad, Ilangko Balasingham, Konstantin Pogorelov, Sungbin Choi, Quentin Debard, Lena Maier-Hein, Stefanie Speidel, Danail Stoyanov, Patrick Brandao, Henry Córdova, Cristina Sánchez-Montes, Suryakanth R. GuruduGloria Fernández-Esparrach, Xavier Dray, Jianming Liang, Aymeric Histace

Research output: Contribution to journalReview article

55 Citations (Scopus)

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 subchallenge, 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.

Original languageEnglish (US)
Article number7840040
Pages (from-to)1231-1249
Number of pages19
JournalIEEE Transactions on Vehicular Technology
Volume36
Issue number6
DOIs
StatePublished - Jun 1 2017
Externally publishedYes

Fingerprint

Medical Image
Computing
Screening
Evaluation
Neural networks
Methodology
Performance Metrics
Gold
Cancer
Experiments
Neural Networks
Vision
Experiment

Keywords

  • Endoscopic vision
  • Handcrafted features
  • Machine learning
  • Polyp detection
  • Validation framework

ASJC Scopus subject areas

  • Automotive Engineering
  • Aerospace Engineering
  • Computer Networks and Communications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Comparative validation of polyp detection methods in video colonoscopy : Results from the MICCAI 2015 endoscopic vision challenge. / Bernal, Jorge; Tajkbaksh, Nima; Sánchez, Francisco Javier; Matuszewski, Bogdan J.; Chen, Hao; Yu, Lequan; Angermann, Quentin; Romain, Olivier; Rustad, Bjørn; Balasingham, Ilangko; Pogorelov, Konstantin; Choi, Sungbin; Debard, Quentin; Maier-Hein, Lena; Speidel, Stefanie; Stoyanov, Danail; Brandao, Patrick; Córdova, Henry; Sánchez-Montes, Cristina; Gurudu, Suryakanth R.; Fernández-Esparrach, Gloria; Dray, Xavier; Liang, Jianming; Histace, Aymeric.

In: IEEE Transactions on Vehicular Technology, Vol. 36, No. 6, 7840040, 01.06.2017, p. 1231-1249.

Research output: Contribution to journalReview article

Bernal, J, Tajkbaksh, N, Sánchez, FJ, Matuszewski, BJ, Chen, H, Yu, L, Angermann, Q, Romain, O, Rustad, B, Balasingham, I, Pogorelov, K, Choi, S, Debard, Q, Maier-Hein, L, Speidel, S, Stoyanov, D, Brandao, P, Córdova, H, Sánchez-Montes, C, Gurudu, SR, Fernández-Esparrach, G, Dray, X, Liang, J & Histace, A 2017, 'Comparative validation of polyp detection methods in video colonoscopy: Results from the MICCAI 2015 endoscopic vision challenge', IEEE Transactions on Vehicular Technology, vol. 36, no. 6, 7840040, pp. 1231-1249. https://doi.org/10.1109/TMI.2017.2664042
Bernal, Jorge ; Tajkbaksh, Nima ; Sánchez, Francisco Javier ; Matuszewski, Bogdan J. ; Chen, Hao ; Yu, Lequan ; Angermann, Quentin ; Romain, Olivier ; Rustad, Bjørn ; Balasingham, Ilangko ; Pogorelov, Konstantin ; Choi, Sungbin ; Debard, Quentin ; Maier-Hein, Lena ; Speidel, Stefanie ; Stoyanov, Danail ; Brandao, Patrick ; Córdova, Henry ; Sánchez-Montes, Cristina ; Gurudu, Suryakanth R. ; Fernández-Esparrach, Gloria ; Dray, Xavier ; Liang, Jianming ; Histace, Aymeric. / Comparative validation of polyp detection methods in video colonoscopy : Results from the MICCAI 2015 endoscopic vision challenge. In: IEEE Transactions on Vehicular Technology. 2017 ; Vol. 36, No. 6. pp. 1231-1249.
@article{c058b44d5ac04a4f8fda96db6b3260ff,
title = "Comparative validation of polyp detection methods in video colonoscopy: Results from the MICCAI 2015 endoscopic vision challenge",
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 subchallenge, 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.",
keywords = "Endoscopic vision, Handcrafted features, Machine learning, Polyp detection, Validation framework",
author = "Jorge Bernal and Nima Tajkbaksh and S{\'a}nchez, {Francisco Javier} and Matuszewski, {Bogdan J.} and Hao Chen and Lequan Yu and Quentin Angermann and Olivier Romain and Bj{\o}rn Rustad and Ilangko Balasingham and Konstantin Pogorelov and Sungbin Choi and Quentin Debard and Lena Maier-Hein and Stefanie Speidel and Danail Stoyanov and Patrick Brandao and Henry C{\'o}rdova and Cristina S{\'a}nchez-Montes and Gurudu, {Suryakanth R.} and Gloria Fern{\'a}ndez-Esparrach and Xavier Dray and Jianming Liang and Aymeric Histace",
year = "2017",
month = "6",
day = "1",
doi = "10.1109/TMI.2017.2664042",
language = "English (US)",
volume = "36",
pages = "1231--1249",
journal = "IEEE Transactions on Vehicular Technology",
issn = "0018-9545",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "6",

}

TY - JOUR

T1 - Comparative validation of polyp detection methods in video colonoscopy

T2 - Results from the MICCAI 2015 endoscopic vision challenge

AU - Bernal, Jorge

AU - Tajkbaksh, Nima

AU - Sánchez, Francisco Javier

AU - Matuszewski, Bogdan J.

AU - Chen, Hao

AU - Yu, Lequan

AU - Angermann, Quentin

AU - Romain, Olivier

AU - Rustad, Bjørn

AU - Balasingham, Ilangko

AU - Pogorelov, Konstantin

AU - Choi, Sungbin

AU - Debard, Quentin

AU - Maier-Hein, Lena

AU - Speidel, Stefanie

AU - Stoyanov, Danail

AU - Brandao, Patrick

AU - Córdova, Henry

AU - Sánchez-Montes, Cristina

AU - Gurudu, Suryakanth R.

AU - Fernández-Esparrach, Gloria

AU - Dray, Xavier

AU - Liang, Jianming

AU - Histace, Aymeric

PY - 2017/6/1

Y1 - 2017/6/1

N2 - 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 subchallenge, 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.

AB - 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 subchallenge, 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.

KW - Endoscopic vision

KW - Handcrafted features

KW - Machine learning

KW - Polyp detection

KW - Validation framework

UR - http://www.scopus.com/inward/record.url?scp=85021449496&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021449496&partnerID=8YFLogxK

U2 - 10.1109/TMI.2017.2664042

DO - 10.1109/TMI.2017.2664042

M3 - Review article

C2 - 28182555

AN - SCOPUS:85021449496

VL - 36

SP - 1231

EP - 1249

JO - IEEE Transactions on Vehicular Technology

JF - IEEE Transactions on Vehicular Technology

SN - 0018-9545

IS - 6

M1 - 7840040

ER -