GAEI-UNet: Global Attention and Elastic Interaction U-Net for Vessel Image Segmentation

Vessel image segmentation plays a pivotal role in medical diagnostics, aiding in the early detection and treatment of vascular diseases. While segmentation based on deep learning has shown promising results, effectively segmenting small structures and maintaining connectivity between them remains ch...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Xiao, Ruiqiang, Wan, Zhuoyue
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Xiao, Ruiqiang
Wan, Zhuoyue
description Vessel image segmentation plays a pivotal role in medical diagnostics, aiding in the early detection and treatment of vascular diseases. While segmentation based on deep learning has shown promising results, effectively segmenting small structures and maintaining connectivity between them remains challenging. To address these limitations, we propose GAEI-UNet, a novel model that combines global attention and elastic interaction-based techniques. GAEI-UNet leverages global spatial and channel context information to enhance high-level semantic understanding within the U-Net architecture, enabling precise segmentation of small vessels. Additionally, we adopt an elastic interaction-based loss function to improve connectivity among these fine structures. By capturing the forces generated by misalignment between target and predicted shapes, our model effectively learns to preserve the correct topology of vessel networks. Evaluation on retinal vessel dataset -- DRIVE demonstrates the superior performance of GAEI-UNet in terms of SE and connectivity of small structures, without significantly increasing computational complexity. This research aims to advance the field of vessel image segmentation, providing more accurate and reliable diagnostic tools for the medical community. The implementation code is available on Code.
doi_str_mv 10.48550/arxiv.2308.08345
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2308_08345</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2308_08345</sourcerecordid><originalsourceid>FETCH-LOGICAL-a675-dfdbbd32b19950d4422030ee3551916111cac8762de8a699f33eb92c1138e6903</originalsourceid><addsrcrecordid>eNotj81KxDAUhbNxIaMP4Mq8QGp-mk7irgy1FgZdOKPLcpvcDoW0lTSIvr0z1dWBw3cOfITcCZ7lRmv-APF7-Mqk4ibjRuX6mnzUZdWw4wumR1qHuYNAy5RwSsM8UZg8rQIsaXC0mRJGcGt_ZGee9nOk77gsGGgzwgnpG57G8xIuzA256iEsePufG3J4qg67Z7Z_rZtduWdQbDXzve86r2QnrNXc57mUXHFEpbWwohBCOHBmW0iPBgpre6Wws9IJoQwWlqsNuf-7Xc3azziMEH_ai2G7GqpfedZKNw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>GAEI-UNet: Global Attention and Elastic Interaction U-Net for Vessel Image Segmentation</title><source>arXiv.org</source><creator>Xiao, Ruiqiang ; Wan, Zhuoyue</creator><creatorcontrib>Xiao, Ruiqiang ; Wan, Zhuoyue</creatorcontrib><description>Vessel image segmentation plays a pivotal role in medical diagnostics, aiding in the early detection and treatment of vascular diseases. While segmentation based on deep learning has shown promising results, effectively segmenting small structures and maintaining connectivity between them remains challenging. To address these limitations, we propose GAEI-UNet, a novel model that combines global attention and elastic interaction-based techniques. GAEI-UNet leverages global spatial and channel context information to enhance high-level semantic understanding within the U-Net architecture, enabling precise segmentation of small vessels. Additionally, we adopt an elastic interaction-based loss function to improve connectivity among these fine structures. By capturing the forces generated by misalignment between target and predicted shapes, our model effectively learns to preserve the correct topology of vessel networks. Evaluation on retinal vessel dataset -- DRIVE demonstrates the superior performance of GAEI-UNet in terms of SE and connectivity of small structures, without significantly increasing computational complexity. This research aims to advance the field of vessel image segmentation, providing more accurate and reliable diagnostic tools for the medical community. The implementation code is available on Code.</description><identifier>DOI: 10.48550/arxiv.2308.08345</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition</subject><creationdate>2023-08</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2308.08345$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2308.08345$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Xiao, Ruiqiang</creatorcontrib><creatorcontrib>Wan, Zhuoyue</creatorcontrib><title>GAEI-UNet: Global Attention and Elastic Interaction U-Net for Vessel Image Segmentation</title><description>Vessel image segmentation plays a pivotal role in medical diagnostics, aiding in the early detection and treatment of vascular diseases. While segmentation based on deep learning has shown promising results, effectively segmenting small structures and maintaining connectivity between them remains challenging. To address these limitations, we propose GAEI-UNet, a novel model that combines global attention and elastic interaction-based techniques. GAEI-UNet leverages global spatial and channel context information to enhance high-level semantic understanding within the U-Net architecture, enabling precise segmentation of small vessels. Additionally, we adopt an elastic interaction-based loss function to improve connectivity among these fine structures. By capturing the forces generated by misalignment between target and predicted shapes, our model effectively learns to preserve the correct topology of vessel networks. Evaluation on retinal vessel dataset -- DRIVE demonstrates the superior performance of GAEI-UNet in terms of SE and connectivity of small structures, without significantly increasing computational complexity. This research aims to advance the field of vessel image segmentation, providing more accurate and reliable diagnostic tools for the medical community. The implementation code is available on Code.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj81KxDAUhbNxIaMP4Mq8QGp-mk7irgy1FgZdOKPLcpvcDoW0lTSIvr0z1dWBw3cOfITcCZ7lRmv-APF7-Mqk4ibjRuX6mnzUZdWw4wumR1qHuYNAy5RwSsM8UZg8rQIsaXC0mRJGcGt_ZGee9nOk77gsGGgzwgnpG57G8xIuzA256iEsePufG3J4qg67Z7Z_rZtduWdQbDXzve86r2QnrNXc57mUXHFEpbWwohBCOHBmW0iPBgpre6Wws9IJoQwWlqsNuf-7Xc3azziMEH_ai2G7GqpfedZKNw</recordid><startdate>20230816</startdate><enddate>20230816</enddate><creator>Xiao, Ruiqiang</creator><creator>Wan, Zhuoyue</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20230816</creationdate><title>GAEI-UNet: Global Attention and Elastic Interaction U-Net for Vessel Image Segmentation</title><author>Xiao, Ruiqiang ; Wan, Zhuoyue</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a675-dfdbbd32b19950d4422030ee3551916111cac8762de8a699f33eb92c1138e6903</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Xiao, Ruiqiang</creatorcontrib><creatorcontrib>Wan, Zhuoyue</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Xiao, Ruiqiang</au><au>Wan, Zhuoyue</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>GAEI-UNet: Global Attention and Elastic Interaction U-Net for Vessel Image Segmentation</atitle><date>2023-08-16</date><risdate>2023</risdate><abstract>Vessel image segmentation plays a pivotal role in medical diagnostics, aiding in the early detection and treatment of vascular diseases. While segmentation based on deep learning has shown promising results, effectively segmenting small structures and maintaining connectivity between them remains challenging. To address these limitations, we propose GAEI-UNet, a novel model that combines global attention and elastic interaction-based techniques. GAEI-UNet leverages global spatial and channel context information to enhance high-level semantic understanding within the U-Net architecture, enabling precise segmentation of small vessels. Additionally, we adopt an elastic interaction-based loss function to improve connectivity among these fine structures. By capturing the forces generated by misalignment between target and predicted shapes, our model effectively learns to preserve the correct topology of vessel networks. Evaluation on retinal vessel dataset -- DRIVE demonstrates the superior performance of GAEI-UNet in terms of SE and connectivity of small structures, without significantly increasing computational complexity. This research aims to advance the field of vessel image segmentation, providing more accurate and reliable diagnostic tools for the medical community. The implementation code is available on Code.</abstract><doi>10.48550/arxiv.2308.08345</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2308.08345
ispartof
issn
language eng
recordid cdi_arxiv_primary_2308_08345
source arXiv.org
subjects Computer Science - Computer Vision and Pattern Recognition
title GAEI-UNet: Global Attention and Elastic Interaction U-Net for Vessel Image Segmentation
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-19T22%3A11%3A44IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=GAEI-UNet:%20Global%20Attention%20and%20Elastic%20Interaction%20U-Net%20for%20Vessel%20Image%20Segmentation&rft.au=Xiao,%20Ruiqiang&rft.date=2023-08-16&rft_id=info:doi/10.48550/arxiv.2308.08345&rft_dat=%3Carxiv_GOX%3E2308_08345%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true