Bi-attention DoubleUNet: A deep learning approach for carotid artery segmentation in transverse view images for non-invasive stenosis diagnosis

The carotid artery is a vital blood vessel that supplies oxygenated blood to the brain. Blockages in this artery can lead to life-threatening illnesses, making accurate diagnosis essential. While ultrasound (US) imaging is the primary diagnostic tool, evaluations by trained operators can be subjecti...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Najmath, Ottakath (author)
مؤلفون آخرون: Akbari, Younes (author), Al-Maadeed, Somaya Ali (author), Bouridane, Ahmed (author), Zughaier, Susu M. (author), Chowdhury, Muhammad E.H. (author)
التنسيق: article
منشور في: 2024
الموضوعات:
الوصول للمادة أونلاين:http://dx.doi.org/10.1016/j.bspc.2024.106350
https://www.sciencedirect.com/science/article/pii/S1746809424004087
http://hdl.handle.net/10576/55190
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1857415084529156096
author Najmath, Ottakath
author2 Akbari, Younes
Al-Maadeed, Somaya Ali
Bouridane, Ahmed
Zughaier, Susu M.
Chowdhury, Muhammad E.H.
author2_role author
author
author
author
author
author_facet Najmath, Ottakath
Akbari, Younes
Al-Maadeed, Somaya Ali
Bouridane, Ahmed
Zughaier, Susu M.
Chowdhury, Muhammad E.H.
author_role author
dc.creator.none.fl_str_mv Najmath, Ottakath
Akbari, Younes
Al-Maadeed, Somaya Ali
Bouridane, Ahmed
Zughaier, Susu M.
Chowdhury, Muhammad E.H.
dc.date.none.fl_str_mv 2024-05-20T08:26:51Z
2024-04-13
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv http://dx.doi.org/10.1016/j.bspc.2024.106350
Ottakath, N., Akbari, Y., Al-Maadeed, S. A., Bouridane, A., Zughaier, S. M., & Chowdhury, M. E. (2024). Bi-attention DoubleUNet: A deep learning approach for carotid artery segmentation in transverse view images for non-invasive stenosis diagnosis. Biomedical Signal Processing and Control, 94, 106350.
1746-8094
https://www.sciencedirect.com/science/article/pii/S1746809424004087
http://hdl.handle.net/10576/55190
94
1746-8108
dc.language.none.fl_str_mv en
dc.publisher.none.fl_str_mv Elsevier
dc.rights.none.fl_str_mv http://creativecommons.org/licenses/by/4.0/
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Carotid artery segmentation
Transverse mode
Attention network
DoubleUnet
Bottleneck attention module
dc.title.none.fl_str_mv Bi-attention DoubleUNet: A deep learning approach for carotid artery segmentation in transverse view images for non-invasive stenosis diagnosis
dc.type.none.fl_str_mv Article
info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/article
description The carotid artery is a vital blood vessel that supplies oxygenated blood to the brain. Blockages in this artery can lead to life-threatening illnesses, making accurate diagnosis essential. While ultrasound (US) imaging is the primary diagnostic tool, evaluations by trained operators can be subjective and imprecise. An automated approach can provide a more reliable and accurate evaluation of the carotid artery’s condition. To achieve this, the artery must first be identified and isolated from US images. This paper proposes an automated segmentation method for the carotid artery in transverse B-mode ultrasound images, using a Bi-attention DoubleUnet architecture which incorporates spatial attention and channel wise attention using Bottleneck attention module. The method is evaluated on a dataset of transverse images acquired from two devices. The obtained results exhibit higher performance than existing methods with a dice index of 95.96%, IoU of 97.92%, Precision of 98.35% and recall of 97.57% on combined dataset. Another variant of doubleUnet with SE layer and without ASPP (Artous Spatial Pyramidal Pooling) is presented where the modified DoubleUnet with SE realized an average IoU of 92.805%, Dice of 96.215%, precision of 98.82%, and recall of 93.84% representing average results across datasets. These approaches can significantly improve the efficiency and accuracy of carotid artery disease diagnosis and treatment, ultimately improving patient outcomes.
eu_rights_str_mv openAccess
format article
id qu_45802462a205bd4f1fbb25a40b17e287
identifier_str_mv Ottakath, N., Akbari, Y., Al-Maadeed, S. A., Bouridane, A., Zughaier, S. M., & Chowdhury, M. E. (2024). Bi-attention DoubleUNet: A deep learning approach for carotid artery segmentation in transverse view images for non-invasive stenosis diagnosis. Biomedical Signal Processing and Control, 94, 106350.
1746-8094
94
1746-8108
language_invalid_str_mv en
network_acronym_str qu
network_name_str Qatar University repository
oai_identifier_str oai:qspace.qu.edu.qa:10576/55190
publishDate 2024
publisher.none.fl_str_mv Elsevier
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv http://creativecommons.org/licenses/by/4.0/
spelling Bi-attention DoubleUNet: A deep learning approach for carotid artery segmentation in transverse view images for non-invasive stenosis diagnosisNajmath, OttakathAkbari, YounesAl-Maadeed, Somaya AliBouridane, AhmedZughaier, Susu M.Chowdhury, Muhammad E.H.Carotid artery segmentationTransverse modeAttention networkDoubleUnetBottleneck attention moduleThe carotid artery is a vital blood vessel that supplies oxygenated blood to the brain. Blockages in this artery can lead to life-threatening illnesses, making accurate diagnosis essential. While ultrasound (US) imaging is the primary diagnostic tool, evaluations by trained operators can be subjective and imprecise. An automated approach can provide a more reliable and accurate evaluation of the carotid artery’s condition. To achieve this, the artery must first be identified and isolated from US images. This paper proposes an automated segmentation method for the carotid artery in transverse B-mode ultrasound images, using a Bi-attention DoubleUnet architecture which incorporates spatial attention and channel wise attention using Bottleneck attention module. The method is evaluated on a dataset of transverse images acquired from two devices. The obtained results exhibit higher performance than existing methods with a dice index of 95.96%, IoU of 97.92%, Precision of 98.35% and recall of 97.57% on combined dataset. Another variant of doubleUnet with SE layer and without ASPP (Artous Spatial Pyramidal Pooling) is presented where the modified DoubleUnet with SE realized an average IoU of 92.805%, Dice of 96.215%, precision of 98.82%, and recall of 93.84% representing average results across datasets. These approaches can significantly improve the efficiency and accuracy of carotid artery disease diagnosis and treatment, ultimately improving patient outcomes.This document is the results of the research project funded by the Qatar University, High impact grant.This research work was made possible by research grant support (QUHI-CENG-22/23-548) from Qatar University Research Fund in Qatar.Elsevier2024-05-20T08:26:51Z2024-04-13Articleinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://dx.doi.org/10.1016/j.bspc.2024.106350Ottakath, N., Akbari, Y., Al-Maadeed, S. A., Bouridane, A., Zughaier, S. M., & Chowdhury, M. E. (2024). Bi-attention DoubleUNet: A deep learning approach for carotid artery segmentation in transverse view images for non-invasive stenosis diagnosis. Biomedical Signal Processing and Control, 94, 106350.1746-8094https://www.sciencedirect.com/science/article/pii/S1746809424004087http://hdl.handle.net/10576/55190941746-8108enhttp://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:qspace.qu.edu.qa:10576/551902024-07-23T10:58:45Z
spellingShingle Bi-attention DoubleUNet: A deep learning approach for carotid artery segmentation in transverse view images for non-invasive stenosis diagnosis
Najmath, Ottakath
Carotid artery segmentation
Transverse mode
Attention network
DoubleUnet
Bottleneck attention module
status_str publishedVersion
title Bi-attention DoubleUNet: A deep learning approach for carotid artery segmentation in transverse view images for non-invasive stenosis diagnosis
title_full Bi-attention DoubleUNet: A deep learning approach for carotid artery segmentation in transverse view images for non-invasive stenosis diagnosis
title_fullStr Bi-attention DoubleUNet: A deep learning approach for carotid artery segmentation in transverse view images for non-invasive stenosis diagnosis
title_full_unstemmed Bi-attention DoubleUNet: A deep learning approach for carotid artery segmentation in transverse view images for non-invasive stenosis diagnosis
title_short Bi-attention DoubleUNet: A deep learning approach for carotid artery segmentation in transverse view images for non-invasive stenosis diagnosis
title_sort Bi-attention DoubleUNet: A deep learning approach for carotid artery segmentation in transverse view images for non-invasive stenosis diagnosis
topic Carotid artery segmentation
Transverse mode
Attention network
DoubleUnet
Bottleneck attention module
url http://dx.doi.org/10.1016/j.bspc.2024.106350
https://www.sciencedirect.com/science/article/pii/S1746809424004087
http://hdl.handle.net/10576/55190