A complete benchmark for polyp detection, segmentation and classification in colonoscopy images

IntroductionColorectal cancer (CRC) is one of the main causes of deaths worldwide. Early detection and diagnosis of its precursor lesion, the polyp, is key to reduce its mortality and to improve procedure efficiency. During the last two decades, several computational methods have been proposed to as...

Full description

Saved in:
Bibliographic Details
Main Authors: Yael Tudela, Mireia Majó, Neil de la Fuente, Adrian Galdran, Adrian Krenzer, Frank Puppe, Amine Yamlahi, Thuy Nuong Tran, Bogdan J. Matuszewski, Kerr Fitzgerald, Cheng Bian, Junwen Pan, Shijle Liu, Gloria Fernández-Esparrach, Aymeric Histace, Jorge Bernal
Format: Article
Language:English
Published: Frontiers Media S.A. 2024-09-01
Series:Frontiers in Oncology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fonc.2024.1417862/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850265256807366656
author Yael Tudela
Mireia Majó
Neil de la Fuente
Adrian Galdran
Adrian Krenzer
Frank Puppe
Amine Yamlahi
Thuy Nuong Tran
Bogdan J. Matuszewski
Kerr Fitzgerald
Cheng Bian
Junwen Pan
Shijle Liu
Gloria Fernández-Esparrach
Aymeric Histace
Jorge Bernal
author_facet Yael Tudela
Mireia Majó
Neil de la Fuente
Adrian Galdran
Adrian Krenzer
Frank Puppe
Amine Yamlahi
Thuy Nuong Tran
Bogdan J. Matuszewski
Kerr Fitzgerald
Cheng Bian
Junwen Pan
Shijle Liu
Gloria Fernández-Esparrach
Aymeric Histace
Jorge Bernal
author_sort Yael Tudela
collection DOAJ
description IntroductionColorectal cancer (CRC) is one of the main causes of deaths worldwide. Early detection and diagnosis of its precursor lesion, the polyp, is key to reduce its mortality and to improve procedure efficiency. During the last two decades, several computational methods have been proposed to assist clinicians in detection, segmentation and classification tasks but the lack of a common public validation framework makes it difficult to determine which of them is ready to be deployed in the exploration room.MethodsThis study presents a complete validation framework and we compare several methodologies for each of the polyp characterization tasks.ResultsResults show that the majority of the approaches are able to provide good performance for the detection and segmentation task, but that there is room for improvement regarding polyp classification.DiscussionWhile studied show promising results in the assistance of polyp detection and segmentation tasks, further research should be done in classification task to obtain reliable results to assist the clinicians during the procedure. The presented framework provides a standarized method for evaluating and comparing different approaches, which could facilitate the identification of clinically prepared assisting methods.
format Article
id doaj-art-059a0add1a84450499dc90757c953842
institution OA Journals
issn 2234-943X
language English
publishDate 2024-09-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Oncology
spelling doaj-art-059a0add1a84450499dc90757c9538422025-08-20T01:54:30ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2024-09-011410.3389/fonc.2024.14178621417862A complete benchmark for polyp detection, segmentation and classification in colonoscopy imagesYael Tudela0Mireia Majó1Neil de la Fuente2Adrian Galdran3Adrian Krenzer4Frank Puppe5Amine Yamlahi6Thuy Nuong Tran7Bogdan J. Matuszewski8Kerr Fitzgerald9Cheng Bian10Junwen Pan11Shijle Liu12Gloria Fernández-Esparrach13Aymeric Histace14Jorge Bernal15Computer Vision Center and Computer Science Department, Universitat Autònoma de Cerdanyola del Valles, Barcelona, SpainComputer Vision Center and Computer Science Department, Universitat Autònoma de Cerdanyola del Valles, Barcelona, SpainComputer Vision Center and Computer Science Department, Universitat Autònoma de Cerdanyola del Valles, Barcelona, SpainDepartment of Information and Communication Technologies, SymBioSys Research Group, BCNMedTech, Barcelona, SpainArtificial Intelligence and Knowledge Systems, Institute for Computer Science, Julius-Maximilians University of Würzburg, Würzburg, GermanyArtificial Intelligence and Knowledge Systems, Institute for Computer Science, Julius-Maximilians University of Würzburg, Würzburg, GermanyDivision of Intelligent Medical Systems, German Cancer Research Center (DKFZ), Heidelberg, GermanyDivision of Intelligent Medical Systems, German Cancer Research Center (DKFZ), Heidelberg, GermanyComputer Vision and Machine Learning (CVML) Research Group, University of Central Lancashir (UCLan), Preston, United KingdomComputer Vision and Machine Learning (CVML) Research Group, University of Central Lancashir (UCLan), Preston, United KingdomHebei University of Technology, Baoding, ChinaTianjin University, Tianjin, ChinaHebei University of Technology, Baoding, ChinaDigestive Endoscopy Unit, Hospital Clínic, Barcelona, SpainETIS UMR 8051, École Nationale Supérieure de l'Électronique et de ses Applications (ENSEA), Centre national de la recherche scientifique (CNRS), CY Paris Cergy University, Cergy, FranceComputer Vision Center and Computer Science Department, Universitat Autònoma de Cerdanyola del Valles, Barcelona, SpainIntroductionColorectal cancer (CRC) is one of the main causes of deaths worldwide. Early detection and diagnosis of its precursor lesion, the polyp, is key to reduce its mortality and to improve procedure efficiency. During the last two decades, several computational methods have been proposed to assist clinicians in detection, segmentation and classification tasks but the lack of a common public validation framework makes it difficult to determine which of them is ready to be deployed in the exploration room.MethodsThis study presents a complete validation framework and we compare several methodologies for each of the polyp characterization tasks.ResultsResults show that the majority of the approaches are able to provide good performance for the detection and segmentation task, but that there is room for improvement regarding polyp classification.DiscussionWhile studied show promising results in the assistance of polyp detection and segmentation tasks, further research should be done in classification task to obtain reliable results to assist the clinicians during the procedure. The presented framework provides a standarized method for evaluating and comparing different approaches, which could facilitate the identification of clinically prepared assisting methods.https://www.frontiersin.org/articles/10.3389/fonc.2024.1417862/fullcomputer-aided diagnosismedical imagingpolyp classificationpolyp detectionpolyp segmentation
spellingShingle Yael Tudela
Mireia Majó
Neil de la Fuente
Adrian Galdran
Adrian Krenzer
Frank Puppe
Amine Yamlahi
Thuy Nuong Tran
Bogdan J. Matuszewski
Kerr Fitzgerald
Cheng Bian
Junwen Pan
Shijle Liu
Gloria Fernández-Esparrach
Aymeric Histace
Jorge Bernal
A complete benchmark for polyp detection, segmentation and classification in colonoscopy images
Frontiers in Oncology
computer-aided diagnosis
medical imaging
polyp classification
polyp detection
polyp segmentation
title A complete benchmark for polyp detection, segmentation and classification in colonoscopy images
title_full A complete benchmark for polyp detection, segmentation and classification in colonoscopy images
title_fullStr A complete benchmark for polyp detection, segmentation and classification in colonoscopy images
title_full_unstemmed A complete benchmark for polyp detection, segmentation and classification in colonoscopy images
title_short A complete benchmark for polyp detection, segmentation and classification in colonoscopy images
title_sort complete benchmark for polyp detection segmentation and classification in colonoscopy images
topic computer-aided diagnosis
medical imaging
polyp classification
polyp detection
polyp segmentation
url https://www.frontiersin.org/articles/10.3389/fonc.2024.1417862/full
work_keys_str_mv AT yaeltudela acompletebenchmarkforpolypdetectionsegmentationandclassificationincolonoscopyimages
AT mireiamajo acompletebenchmarkforpolypdetectionsegmentationandclassificationincolonoscopyimages
AT neildelafuente acompletebenchmarkforpolypdetectionsegmentationandclassificationincolonoscopyimages
AT adriangaldran acompletebenchmarkforpolypdetectionsegmentationandclassificationincolonoscopyimages
AT adriankrenzer acompletebenchmarkforpolypdetectionsegmentationandclassificationincolonoscopyimages
AT frankpuppe acompletebenchmarkforpolypdetectionsegmentationandclassificationincolonoscopyimages
AT amineyamlahi acompletebenchmarkforpolypdetectionsegmentationandclassificationincolonoscopyimages
AT thuynuongtran acompletebenchmarkforpolypdetectionsegmentationandclassificationincolonoscopyimages
AT bogdanjmatuszewski acompletebenchmarkforpolypdetectionsegmentationandclassificationincolonoscopyimages
AT kerrfitzgerald acompletebenchmarkforpolypdetectionsegmentationandclassificationincolonoscopyimages
AT chengbian acompletebenchmarkforpolypdetectionsegmentationandclassificationincolonoscopyimages
AT junwenpan acompletebenchmarkforpolypdetectionsegmentationandclassificationincolonoscopyimages
AT shijleliu acompletebenchmarkforpolypdetectionsegmentationandclassificationincolonoscopyimages
AT gloriafernandezesparrach acompletebenchmarkforpolypdetectionsegmentationandclassificationincolonoscopyimages
AT aymerichistace acompletebenchmarkforpolypdetectionsegmentationandclassificationincolonoscopyimages
AT jorgebernal acompletebenchmarkforpolypdetectionsegmentationandclassificationincolonoscopyimages
AT yaeltudela completebenchmarkforpolypdetectionsegmentationandclassificationincolonoscopyimages
AT mireiamajo completebenchmarkforpolypdetectionsegmentationandclassificationincolonoscopyimages
AT neildelafuente completebenchmarkforpolypdetectionsegmentationandclassificationincolonoscopyimages
AT adriangaldran completebenchmarkforpolypdetectionsegmentationandclassificationincolonoscopyimages
AT adriankrenzer completebenchmarkforpolypdetectionsegmentationandclassificationincolonoscopyimages
AT frankpuppe completebenchmarkforpolypdetectionsegmentationandclassificationincolonoscopyimages
AT amineyamlahi completebenchmarkforpolypdetectionsegmentationandclassificationincolonoscopyimages
AT thuynuongtran completebenchmarkforpolypdetectionsegmentationandclassificationincolonoscopyimages
AT bogdanjmatuszewski completebenchmarkforpolypdetectionsegmentationandclassificationincolonoscopyimages
AT kerrfitzgerald completebenchmarkforpolypdetectionsegmentationandclassificationincolonoscopyimages
AT chengbian completebenchmarkforpolypdetectionsegmentationandclassificationincolonoscopyimages
AT junwenpan completebenchmarkforpolypdetectionsegmentationandclassificationincolonoscopyimages
AT shijleliu completebenchmarkforpolypdetectionsegmentationandclassificationincolonoscopyimages
AT gloriafernandezesparrach completebenchmarkforpolypdetectionsegmentationandclassificationincolonoscopyimages
AT aymerichistace completebenchmarkforpolypdetectionsegmentationandclassificationincolonoscopyimages
AT jorgebernal completebenchmarkforpolypdetectionsegmentationandclassificationincolonoscopyimages