Cargando…

Multi-Task Classification and Segmentation for Explicable Capsule Endoscopy Diagnostics

Capsule endoscopy is a leading diagnostic tool for small bowel lesions which faces certain challenges such as time-consuming interpretation and harsh optical environment inside the small intestine. Specialists unavoidably waste lots of time on searching for a high clearness degree image for accurate...

Descripción completa

Detalles Bibliográficos
Autores principales: Kong, Zishang, He, Min, Luo, Qianjiang, Huang, Xiansong, Wei, Pengxu, Cheng, Yalu, Chen, Luyang, Liang, Yongsheng, Lu, Yanchang, Li, Xi, Chen, Jie
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8417442/
https://www.ncbi.nlm.nih.gov/pubmed/34490342
http://dx.doi.org/10.3389/fmolb.2021.614277
_version_ 1783748381311500288
author Kong, Zishang
He, Min
Luo, Qianjiang
Huang, Xiansong
Wei, Pengxu
Cheng, Yalu
Chen, Luyang
Liang, Yongsheng
Lu, Yanchang
Li, Xi
Chen, Jie
author_facet Kong, Zishang
He, Min
Luo, Qianjiang
Huang, Xiansong
Wei, Pengxu
Cheng, Yalu
Chen, Luyang
Liang, Yongsheng
Lu, Yanchang
Li, Xi
Chen, Jie
author_sort Kong, Zishang
collection PubMed
description Capsule endoscopy is a leading diagnostic tool for small bowel lesions which faces certain challenges such as time-consuming interpretation and harsh optical environment inside the small intestine. Specialists unavoidably waste lots of time on searching for a high clearness degree image for accurate diagnostics. However, current clearness degree classification methods are based on either traditional attributes or an unexplainable deep neural network. In this paper, we propose a multi-task framework, called the multi-task classification and segmentation network (MTCSN), to achieve joint learning of clearness degree (CD) and tissue semantic segmentation (TSS) for the first time. In the MTCSN, the CD helps to generate better refined TSS, while TSS provides an explicable semantic map to better classify the CD. In addition, we present a new benchmark, named the Capsule-Endoscopy Crohn’s Disease dataset, which introduces the challenges faced in the real world including motion blur, excreta occlusion, reflection, and various complex alimentary scenes that are widely acknowledged in endoscopy examination. Extensive experiments and ablation studies report the significant performance gains of the MTCSN over state-of-the-art methods.
format Online
Article
Text
id pubmed-8417442
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-84174422021-09-05 Multi-Task Classification and Segmentation for Explicable Capsule Endoscopy Diagnostics Kong, Zishang He, Min Luo, Qianjiang Huang, Xiansong Wei, Pengxu Cheng, Yalu Chen, Luyang Liang, Yongsheng Lu, Yanchang Li, Xi Chen, Jie Front Mol Biosci Molecular Biosciences Capsule endoscopy is a leading diagnostic tool for small bowel lesions which faces certain challenges such as time-consuming interpretation and harsh optical environment inside the small intestine. Specialists unavoidably waste lots of time on searching for a high clearness degree image for accurate diagnostics. However, current clearness degree classification methods are based on either traditional attributes or an unexplainable deep neural network. In this paper, we propose a multi-task framework, called the multi-task classification and segmentation network (MTCSN), to achieve joint learning of clearness degree (CD) and tissue semantic segmentation (TSS) for the first time. In the MTCSN, the CD helps to generate better refined TSS, while TSS provides an explicable semantic map to better classify the CD. In addition, we present a new benchmark, named the Capsule-Endoscopy Crohn’s Disease dataset, which introduces the challenges faced in the real world including motion blur, excreta occlusion, reflection, and various complex alimentary scenes that are widely acknowledged in endoscopy examination. Extensive experiments and ablation studies report the significant performance gains of the MTCSN over state-of-the-art methods. Frontiers Media S.A. 2021-08-19 /pmc/articles/PMC8417442/ /pubmed/34490342 http://dx.doi.org/10.3389/fmolb.2021.614277 Text en Copyright © 2021 Kong, He, Luo, Huang, Wei, Cheng, Chen, Liang, Lu, Li and Chen. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Molecular Biosciences
Kong, Zishang
He, Min
Luo, Qianjiang
Huang, Xiansong
Wei, Pengxu
Cheng, Yalu
Chen, Luyang
Liang, Yongsheng
Lu, Yanchang
Li, Xi
Chen, Jie
Multi-Task Classification and Segmentation for Explicable Capsule Endoscopy Diagnostics
title Multi-Task Classification and Segmentation for Explicable Capsule Endoscopy Diagnostics
title_full Multi-Task Classification and Segmentation for Explicable Capsule Endoscopy Diagnostics
title_fullStr Multi-Task Classification and Segmentation for Explicable Capsule Endoscopy Diagnostics
title_full_unstemmed Multi-Task Classification and Segmentation for Explicable Capsule Endoscopy Diagnostics
title_short Multi-Task Classification and Segmentation for Explicable Capsule Endoscopy Diagnostics
title_sort multi-task classification and segmentation for explicable capsule endoscopy diagnostics
topic Molecular Biosciences
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8417442/
https://www.ncbi.nlm.nih.gov/pubmed/34490342
http://dx.doi.org/10.3389/fmolb.2021.614277
work_keys_str_mv AT kongzishang multitaskclassificationandsegmentationforexplicablecapsuleendoscopydiagnostics
AT hemin multitaskclassificationandsegmentationforexplicablecapsuleendoscopydiagnostics
AT luoqianjiang multitaskclassificationandsegmentationforexplicablecapsuleendoscopydiagnostics
AT huangxiansong multitaskclassificationandsegmentationforexplicablecapsuleendoscopydiagnostics
AT weipengxu multitaskclassificationandsegmentationforexplicablecapsuleendoscopydiagnostics
AT chengyalu multitaskclassificationandsegmentationforexplicablecapsuleendoscopydiagnostics
AT chenluyang multitaskclassificationandsegmentationforexplicablecapsuleendoscopydiagnostics
AT liangyongsheng multitaskclassificationandsegmentationforexplicablecapsuleendoscopydiagnostics
AT luyanchang multitaskclassificationandsegmentationforexplicablecapsuleendoscopydiagnostics
AT lixi multitaskclassificationandsegmentationforexplicablecapsuleendoscopydiagnostics
AT chenjie multitaskclassificationandsegmentationforexplicablecapsuleendoscopydiagnostics