Loading…

ResD-Unet Research and Application for Pulmonary Artery Segmentation

In the three-dimensional reconstruction of the pulmonary artery and the identification of pulmonary embolism, experts find it difficult to accurately estimate the severity of the embolism in the pulmonary artery, due to its irregular shape and complex adjacent tissues. In effect, segmenting the pulm...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2021, Vol.9, p.67504-67511
Main Authors: Yuan, Hongfang, Liu, Zhenhong, Shao, Yajun, Liu, Min
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c408t-d1e2a6ef42e8dbd0d090fa87bbf9c9f867b0a2d50a3e2dc74398456b46e9ce9b3
cites cdi_FETCH-LOGICAL-c408t-d1e2a6ef42e8dbd0d090fa87bbf9c9f867b0a2d50a3e2dc74398456b46e9ce9b3
container_end_page 67511
container_issue
container_start_page 67504
container_title IEEE access
container_volume 9
creator Yuan, Hongfang
Liu, Zhenhong
Shao, Yajun
Liu, Min
description In the three-dimensional reconstruction of the pulmonary artery and the identification of pulmonary embolism, experts find it difficult to accurately estimate the severity of the embolism in the pulmonary artery, due to its irregular shape and complex adjacent tissues. In effect, segmenting the pulmonary artery accurately is the basis for assessing the severity of pulmonary embolism, and it is also a challengeable task. To solve this problem, this study proposes a ResD-Unet architecture for pulmonary artery segmentation. To begin with, the U-Net network is used as the basic structure, which allows efficient information flow and good performance in the absence of a sufficiently large dataset. In what follows, novel Residual-Dense blocks are introduced in the ResD-Unet architecture to refine image segmentation and build a deeper network while improving the gradient circulation of the network. Finally, a novel hybrid loss function is utilized to make full use of the advantages of the binary cross entropy loss, Dice loss and SSIM loss. Equipped with the hybrid loss, the proposed architecture is able to effectively segment the object areas and accurately predict the structures with clear boundaries. The experimental results show that the proposed framework can achieve high segmentation accuracy and efficiency, and the segmentation results are comparable to that of manual segmentation.
doi_str_mv 10.1109/ACCESS.2021.3073051
format article
fullrecord <record><control><sourceid>proquest_ieee_</sourceid><recordid>TN_cdi_ieee_primary_9408588</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9408588</ieee_id><doaj_id>oai_doaj_org_article_1d46915b268f4340a4b942427fb461a5</doaj_id><sourcerecordid>2525833344</sourcerecordid><originalsourceid>FETCH-LOGICAL-c408t-d1e2a6ef42e8dbd0d090fa87bbf9c9f867b0a2d50a3e2dc74398456b46e9ce9b3</originalsourceid><addsrcrecordid>eNpNkE9Lw0AQxYMoWGo_QS8Bz6n7N9k9hrRqoaBYe1422dmakmbjJj347d02UpzLDMN7b4ZfFM0xWmCM5FNeFKvtdkEQwQuKMoo4vokmBKcyoZymt__m-2jW9wcUSoQVzybR8gP6ZbJrYYjDBNpXX7FuTZx3XVNXeqhdG1vn4_dTc3St9j9x7gcIbQv7I7TDRfEQ3Vnd9DD769No97z6LF6TzdvLusg3ScWQGBKDgegULCMgTGmQQRJZLbKytLKSVqRZiTQxHGkKxFQZo1IwnpYsBVmBLOk0Wo-5xumD6nx9DA8pp2t1WTi_V9oPddWAwoalEvOSpMIyypBmpWSEkcyGOKx5yHocszrvvk_QD-rgTr4N7yvCCReUUsaCio6qyru-92CvVzFSZ_pqpK_O9NUf_eCaj64aAK4OGSBwIegvaQR_dA</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2525833344</pqid></control><display><type>article</type><title>ResD-Unet Research and Application for Pulmonary Artery Segmentation</title><source>IEEE Xplore Open Access Journals</source><creator>Yuan, Hongfang ; Liu, Zhenhong ; Shao, Yajun ; Liu, Min</creator><creatorcontrib>Yuan, Hongfang ; Liu, Zhenhong ; Shao, Yajun ; Liu, Min</creatorcontrib><description>In the three-dimensional reconstruction of the pulmonary artery and the identification of pulmonary embolism, experts find it difficult to accurately estimate the severity of the embolism in the pulmonary artery, due to its irregular shape and complex adjacent tissues. In effect, segmenting the pulmonary artery accurately is the basis for assessing the severity of pulmonary embolism, and it is also a challengeable task. To solve this problem, this study proposes a ResD-Unet architecture for pulmonary artery segmentation. To begin with, the U-Net network is used as the basic structure, which allows efficient information flow and good performance in the absence of a sufficiently large dataset. In what follows, novel Residual-Dense blocks are introduced in the ResD-Unet architecture to refine image segmentation and build a deeper network while improving the gradient circulation of the network. Finally, a novel hybrid loss function is utilized to make full use of the advantages of the binary cross entropy loss, Dice loss and SSIM loss. Equipped with the hybrid loss, the proposed architecture is able to effectively segment the object areas and accurately predict the structures with clear boundaries. The experimental results show that the proposed framework can achieve high segmentation accuracy and efficiency, and the segmentation results are comparable to that of manual segmentation.</description><identifier>ISSN: 2169-3536</identifier><identifier>EISSN: 2169-3536</identifier><identifier>DOI: 10.1109/ACCESS.2021.3073051</identifier><identifier>CODEN: IAECCG</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Arteries ; Computed tomography ; Computer architecture ; Convergence ; Convolution ; deep learning ; Embolisms ; Image segmentation ; Information flow ; Neural network ; Pulmonary arteries ; Pulmonary embolisms ; ResD-Unet ; Residual-dense block ; Training</subject><ispartof>IEEE access, 2021, Vol.9, p.67504-67511</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c408t-d1e2a6ef42e8dbd0d090fa87bbf9c9f867b0a2d50a3e2dc74398456b46e9ce9b3</citedby><cites>FETCH-LOGICAL-c408t-d1e2a6ef42e8dbd0d090fa87bbf9c9f867b0a2d50a3e2dc74398456b46e9ce9b3</cites><orcidid>0000-0002-8026-9629</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9408588$$EHTML$$P50$$Gieee$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,4024,27633,27923,27924,27925,54933</link.rule.ids></links><search><creatorcontrib>Yuan, Hongfang</creatorcontrib><creatorcontrib>Liu, Zhenhong</creatorcontrib><creatorcontrib>Shao, Yajun</creatorcontrib><creatorcontrib>Liu, Min</creatorcontrib><title>ResD-Unet Research and Application for Pulmonary Artery Segmentation</title><title>IEEE access</title><addtitle>Access</addtitle><description>In the three-dimensional reconstruction of the pulmonary artery and the identification of pulmonary embolism, experts find it difficult to accurately estimate the severity of the embolism in the pulmonary artery, due to its irregular shape and complex adjacent tissues. In effect, segmenting the pulmonary artery accurately is the basis for assessing the severity of pulmonary embolism, and it is also a challengeable task. To solve this problem, this study proposes a ResD-Unet architecture for pulmonary artery segmentation. To begin with, the U-Net network is used as the basic structure, which allows efficient information flow and good performance in the absence of a sufficiently large dataset. In what follows, novel Residual-Dense blocks are introduced in the ResD-Unet architecture to refine image segmentation and build a deeper network while improving the gradient circulation of the network. Finally, a novel hybrid loss function is utilized to make full use of the advantages of the binary cross entropy loss, Dice loss and SSIM loss. Equipped with the hybrid loss, the proposed architecture is able to effectively segment the object areas and accurately predict the structures with clear boundaries. The experimental results show that the proposed framework can achieve high segmentation accuracy and efficiency, and the segmentation results are comparable to that of manual segmentation.</description><subject>Arteries</subject><subject>Computed tomography</subject><subject>Computer architecture</subject><subject>Convergence</subject><subject>Convolution</subject><subject>deep learning</subject><subject>Embolisms</subject><subject>Image segmentation</subject><subject>Information flow</subject><subject>Neural network</subject><subject>Pulmonary arteries</subject><subject>Pulmonary embolisms</subject><subject>ResD-Unet</subject><subject>Residual-dense block</subject><subject>Training</subject><issn>2169-3536</issn><issn>2169-3536</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>ESBDL</sourceid><sourceid>DOA</sourceid><recordid>eNpNkE9Lw0AQxYMoWGo_QS8Bz6n7N9k9hrRqoaBYe1422dmakmbjJj347d02UpzLDMN7b4ZfFM0xWmCM5FNeFKvtdkEQwQuKMoo4vokmBKcyoZymt__m-2jW9wcUSoQVzybR8gP6ZbJrYYjDBNpXX7FuTZx3XVNXeqhdG1vn4_dTc3St9j9x7gcIbQv7I7TDRfEQ3Vnd9DD769No97z6LF6TzdvLusg3ScWQGBKDgegULCMgTGmQQRJZLbKytLKSVqRZiTQxHGkKxFQZo1IwnpYsBVmBLOk0Wo-5xumD6nx9DA8pp2t1WTi_V9oPddWAwoalEvOSpMIyypBmpWSEkcyGOKx5yHocszrvvk_QD-rgTr4N7yvCCReUUsaCio6qyru-92CvVzFSZ_pqpK_O9NUf_eCaj64aAK4OGSBwIegvaQR_dA</recordid><startdate>2021</startdate><enddate>2021</enddate><creator>Yuan, Hongfang</creator><creator>Liu, Zhenhong</creator><creator>Shao, Yajun</creator><creator>Liu, Min</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>ESBDL</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>7SR</scope><scope>8BQ</scope><scope>8FD</scope><scope>JG9</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0002-8026-9629</orcidid></search><sort><creationdate>2021</creationdate><title>ResD-Unet Research and Application for Pulmonary Artery Segmentation</title><author>Yuan, Hongfang ; Liu, Zhenhong ; Shao, Yajun ; Liu, Min</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c408t-d1e2a6ef42e8dbd0d090fa87bbf9c9f867b0a2d50a3e2dc74398456b46e9ce9b3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Arteries</topic><topic>Computed tomography</topic><topic>Computer architecture</topic><topic>Convergence</topic><topic>Convolution</topic><topic>deep learning</topic><topic>Embolisms</topic><topic>Image segmentation</topic><topic>Information flow</topic><topic>Neural network</topic><topic>Pulmonary arteries</topic><topic>Pulmonary embolisms</topic><topic>ResD-Unet</topic><topic>Residual-dense block</topic><topic>Training</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Yuan, Hongfang</creatorcontrib><creatorcontrib>Liu, Zhenhong</creatorcontrib><creatorcontrib>Shao, Yajun</creatorcontrib><creatorcontrib>Liu, Min</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005–Present</collection><collection>IEEE Xplore Open Access Journals</collection><collection>IEEE All-Society Periodicals Package (ASPP) Online</collection><collection>IEEE Electronic Library Online</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Engineered Materials Abstracts</collection><collection>METADEX</collection><collection>Technology Research Database</collection><collection>Materials Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>IEEE access</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Yuan, Hongfang</au><au>Liu, Zhenhong</au><au>Shao, Yajun</au><au>Liu, Min</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>ResD-Unet Research and Application for Pulmonary Artery Segmentation</atitle><jtitle>IEEE access</jtitle><stitle>Access</stitle><date>2021</date><risdate>2021</risdate><volume>9</volume><spage>67504</spage><epage>67511</epage><pages>67504-67511</pages><issn>2169-3536</issn><eissn>2169-3536</eissn><coden>IAECCG</coden><abstract>In the three-dimensional reconstruction of the pulmonary artery and the identification of pulmonary embolism, experts find it difficult to accurately estimate the severity of the embolism in the pulmonary artery, due to its irregular shape and complex adjacent tissues. In effect, segmenting the pulmonary artery accurately is the basis for assessing the severity of pulmonary embolism, and it is also a challengeable task. To solve this problem, this study proposes a ResD-Unet architecture for pulmonary artery segmentation. To begin with, the U-Net network is used as the basic structure, which allows efficient information flow and good performance in the absence of a sufficiently large dataset. In what follows, novel Residual-Dense blocks are introduced in the ResD-Unet architecture to refine image segmentation and build a deeper network while improving the gradient circulation of the network. Finally, a novel hybrid loss function is utilized to make full use of the advantages of the binary cross entropy loss, Dice loss and SSIM loss. Equipped with the hybrid loss, the proposed architecture is able to effectively segment the object areas and accurately predict the structures with clear boundaries. The experimental results show that the proposed framework can achieve high segmentation accuracy and efficiency, and the segmentation results are comparable to that of manual segmentation.</abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/ACCESS.2021.3073051</doi><tpages>8</tpages><orcidid>https://orcid.org/0000-0002-8026-9629</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 2169-3536
ispartof IEEE access, 2021, Vol.9, p.67504-67511
issn 2169-3536
2169-3536
language eng
recordid cdi_ieee_primary_9408588
source IEEE Xplore Open Access Journals
subjects Arteries
Computed tomography
Computer architecture
Convergence
Convolution
deep learning
Embolisms
Image segmentation
Information flow
Neural network
Pulmonary arteries
Pulmonary embolisms
ResD-Unet
Residual-dense block
Training
title ResD-Unet Research and Application for Pulmonary Artery Segmentation
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T23%3A56%3A46IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_ieee_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=ResD-Unet%20Research%20and%20Application%20for%20Pulmonary%20Artery%20Segmentation&rft.jtitle=IEEE%20access&rft.au=Yuan,%20Hongfang&rft.date=2021&rft.volume=9&rft.spage=67504&rft.epage=67511&rft.pages=67504-67511&rft.issn=2169-3536&rft.eissn=2169-3536&rft.coden=IAECCG&rft_id=info:doi/10.1109/ACCESS.2021.3073051&rft_dat=%3Cproquest_ieee_%3E2525833344%3C/proquest_ieee_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c408t-d1e2a6ef42e8dbd0d090fa87bbf9c9f867b0a2d50a3e2dc74398456b46e9ce9b3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2525833344&rft_id=info:pmid/&rft_ieee_id=9408588&rfr_iscdi=true