Automated Detection of Colorectal Polyp Utilizing Deep Learning Methods With Explainable AI

<p dir="ltr">Detecting colorectal polyps promptly and accurately is crucial in preventing the progression of colorectal cancer. These polyps cause severe conditions in the colon or rectum, presenting a significant diagnostic challenge. Traditional manual detection through medical ima...

Full description

Saved in:
Bibliographic Details
Main Author: Md. Faysal Ahamed (21842396) (author)
Other Authors: Md. Rabiul Islam (9108985) (author), Md. Nahiduzzaman (17873875) (author), Md. Jawadul Karim (21842399) (author), Mohamed Arselene Ayari (16869978) (author), Amith Khandakar (14151981) (author)
Published: 2024
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513542144655360
author Md. Faysal Ahamed (21842396)
author2 Md. Rabiul Islam (9108985)
Md. Nahiduzzaman (17873875)
Md. Jawadul Karim (21842399)
Mohamed Arselene Ayari (16869978)
Amith Khandakar (14151981)
author2_role author
author
author
author
author
author_facet Md. Faysal Ahamed (21842396)
Md. Rabiul Islam (9108985)
Md. Nahiduzzaman (17873875)
Md. Jawadul Karim (21842399)
Mohamed Arselene Ayari (16869978)
Amith Khandakar (14151981)
author_role author
dc.creator.none.fl_str_mv Md. Faysal Ahamed (21842396)
Md. Rabiul Islam (9108985)
Md. Nahiduzzaman (17873875)
Md. Jawadul Karim (21842399)
Mohamed Arselene Ayari (16869978)
Amith Khandakar (14151981)
dc.date.none.fl_str_mv 2024-01-01T00:00:00Z
dc.identifier.none.fl_str_mv 10.1109/access.2024.3402818
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Automated_Detection_of_Colorectal_Polyp_Utilizing_Deep_Learning_Methods_With_Explainable_AI/29715848
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Biomedical engineering
Health sciences
Health services and systems
Information and computing sciences
Artificial intelligence
Localization
segmentation
YOLOv8
TR-SE-Net
squeeze-and-excite network
colonoscopy
deep learning
Kvasir-SEG
CVC-ClinicDB
PolypGen
ETIS-LaribPolypDB
EDD 2020
BKAI-IGH
explainable AI (XAI)
Colonoscopy
Solid modeling
Location awareness
Gastrointestinal tract
Training
Reliability
Real-time systems
dc.title.none.fl_str_mv Automated Detection of Colorectal Polyp Utilizing Deep Learning Methods With Explainable AI
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Detecting colorectal polyps promptly and accurately is crucial in preventing the progression of colorectal cancer. These polyps cause severe conditions in the colon or rectum, presenting a significant diagnostic challenge. Traditional manual detection through medical imaging is not only bulky and prone to errors but also incurs substantial costs, requiring expert endoscopist. Inefficient detection and treatment can lead to critical health complications. Addressing these issues, we extensively employed various configurations of the state-of-the-art YOLOv8 (n-nano, s-small, m-medium, l-large, and x-extra-large) models for effective polyp localization. Complementing this, we proposed a novel TR-SE-Net model for segmentation, integrating Squeeze-and-Excite Networks (SE-Net) to elevate performance and real-time processing capabilities. The Kvasir-SEG dataset is utilized for training and testing models, supplemented by external validation CVC-ClinicDB, PolypGen, ETIS-LaribPolypDB, EDD 2020, and BKAI-IGH to confirm their efficacy in processing unseen, real-time data. This study delves into the interpretability of these models using explainable AI (XAI), such as eigen visualization for localization and heatmap analysis for segmentation. This exploration provides deeper insights into the decision-making processes of the models, thereby enhancing their reliability. Notably, the YOLOv8m model showcased remarkable prediction speed (approximately 16.61 ms) and excelled in precision (0.946), recall (0.771), F1-score (0.85), mAP50 (0.886), and mAP50–95 (0.695), catering to diverse clinical scenarios. The TR-SE-Net demonstrated significant improvements in segmentation performances, including DSC (0.8754), F2-score (0.8786), precision (0.9027), recall (0.8879), accuracy (0.9647), competitive mIoU (0.7961), FPS (54), parameters (27.27 million), and flops (10.59 GMac). Furthermore, A graphical Computer Aided Diagnosis (CAD) system developed utilizing both models can substantially reduce the miss rate because segmentation will assist in polyp detection or vice versa if localization fails. Conclusively, integrating these advanced computer-aided methods substantially enhances colonoscopy procedures by mitigating the risks of colorectal cancer.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/deed.en" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2024.3402818" target="_blank">https://dx.doi.org/10.1109/access.2024.3402818</a></p>
eu_rights_str_mv openAccess
id Manara2_172a00171edb2174367406b136eb6e61
identifier_str_mv 10.1109/access.2024.3402818
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/29715848
publishDate 2024
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Automated Detection of Colorectal Polyp Utilizing Deep Learning Methods With Explainable AIMd. Faysal Ahamed (21842396)Md. Rabiul Islam (9108985)Md. Nahiduzzaman (17873875)Md. Jawadul Karim (21842399)Mohamed Arselene Ayari (16869978)Amith Khandakar (14151981)EngineeringBiomedical engineeringHealth sciencesHealth services and systemsInformation and computing sciencesArtificial intelligenceLocalizationsegmentationYOLOv8TR-SE-Netsqueeze-and-excite networkcolonoscopydeep learningKvasir-SEGCVC-ClinicDBPolypGenETIS-LaribPolypDBEDD 2020BKAI-IGHexplainable AI (XAI)ColonoscopySolid modelingLocation awarenessGastrointestinal tractTrainingReliabilityReal-time systems<p dir="ltr">Detecting colorectal polyps promptly and accurately is crucial in preventing the progression of colorectal cancer. These polyps cause severe conditions in the colon or rectum, presenting a significant diagnostic challenge. Traditional manual detection through medical imaging is not only bulky and prone to errors but also incurs substantial costs, requiring expert endoscopist. Inefficient detection and treatment can lead to critical health complications. Addressing these issues, we extensively employed various configurations of the state-of-the-art YOLOv8 (n-nano, s-small, m-medium, l-large, and x-extra-large) models for effective polyp localization. Complementing this, we proposed a novel TR-SE-Net model for segmentation, integrating Squeeze-and-Excite Networks (SE-Net) to elevate performance and real-time processing capabilities. The Kvasir-SEG dataset is utilized for training and testing models, supplemented by external validation CVC-ClinicDB, PolypGen, ETIS-LaribPolypDB, EDD 2020, and BKAI-IGH to confirm their efficacy in processing unseen, real-time data. This study delves into the interpretability of these models using explainable AI (XAI), such as eigen visualization for localization and heatmap analysis for segmentation. This exploration provides deeper insights into the decision-making processes of the models, thereby enhancing their reliability. Notably, the YOLOv8m model showcased remarkable prediction speed (approximately 16.61 ms) and excelled in precision (0.946), recall (0.771), F1-score (0.85), mAP50 (0.886), and mAP50–95 (0.695), catering to diverse clinical scenarios. The TR-SE-Net demonstrated significant improvements in segmentation performances, including DSC (0.8754), F2-score (0.8786), precision (0.9027), recall (0.8879), accuracy (0.9647), competitive mIoU (0.7961), FPS (54), parameters (27.27 million), and flops (10.59 GMac). Furthermore, A graphical Computer Aided Diagnosis (CAD) system developed utilizing both models can substantially reduce the miss rate because segmentation will assist in polyp detection or vice versa if localization fails. Conclusively, integrating these advanced computer-aided methods substantially enhances colonoscopy procedures by mitigating the risks of colorectal cancer.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/deed.en" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2024.3402818" target="_blank">https://dx.doi.org/10.1109/access.2024.3402818</a></p>2024-01-01T00:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/access.2024.3402818https://figshare.com/articles/journal_contribution/Automated_Detection_of_Colorectal_Polyp_Utilizing_Deep_Learning_Methods_With_Explainable_AI/29715848CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/297158482024-01-01T00:00:00Z
spellingShingle Automated Detection of Colorectal Polyp Utilizing Deep Learning Methods With Explainable AI
Md. Faysal Ahamed (21842396)
Engineering
Biomedical engineering
Health sciences
Health services and systems
Information and computing sciences
Artificial intelligence
Localization
segmentation
YOLOv8
TR-SE-Net
squeeze-and-excite network
colonoscopy
deep learning
Kvasir-SEG
CVC-ClinicDB
PolypGen
ETIS-LaribPolypDB
EDD 2020
BKAI-IGH
explainable AI (XAI)
Colonoscopy
Solid modeling
Location awareness
Gastrointestinal tract
Training
Reliability
Real-time systems
status_str publishedVersion
title Automated Detection of Colorectal Polyp Utilizing Deep Learning Methods With Explainable AI
title_full Automated Detection of Colorectal Polyp Utilizing Deep Learning Methods With Explainable AI
title_fullStr Automated Detection of Colorectal Polyp Utilizing Deep Learning Methods With Explainable AI
title_full_unstemmed Automated Detection of Colorectal Polyp Utilizing Deep Learning Methods With Explainable AI
title_short Automated Detection of Colorectal Polyp Utilizing Deep Learning Methods With Explainable AI
title_sort Automated Detection of Colorectal Polyp Utilizing Deep Learning Methods With Explainable AI
topic Engineering
Biomedical engineering
Health sciences
Health services and systems
Information and computing sciences
Artificial intelligence
Localization
segmentation
YOLOv8
TR-SE-Net
squeeze-and-excite network
colonoscopy
deep learning
Kvasir-SEG
CVC-ClinicDB
PolypGen
ETIS-LaribPolypDB
EDD 2020
BKAI-IGH
explainable AI (XAI)
Colonoscopy
Solid modeling
Location awareness
Gastrointestinal tract
Training
Reliability
Real-time systems