Multiclass retinal disease classification and lesion segmentation in OCT B-scan images using cascaded convolutional networks

Disease classification and lesion segmentation of retinal optical coherence tomography images play important roles in ophthalmic computer-aided diagnosis. However, existing methods achieve the two tasks separately, which is insufficient for clinical application and ignores the internal relation of d...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Applied optics (2004) 2020-11, Vol.59 (33), p.10312-10320
Hauptverfasser: Zhong, Pan, Wang, Jianlin, Guo, Yongqi, Fu, Xuesong, Wang, Rutong
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 10320
container_issue 33
container_start_page 10312
container_title Applied optics (2004)
container_volume 59
creator Zhong, Pan
Wang, Jianlin
Guo, Yongqi
Fu, Xuesong
Wang, Rutong
description Disease classification and lesion segmentation of retinal optical coherence tomography images play important roles in ophthalmic computer-aided diagnosis. However, existing methods achieve the two tasks separately, which is insufficient for clinical application and ignores the internal relation of disease and lesion features. In this paper, a framework of cascaded convolutional networks is proposed to jointly classify retinal diseases and segment lesions. First, we adopt an auxiliary binary classification network to identify normal and abnormal images. Then a novel, to the best of our knowledge, U-shaped multi-task network, BDA-Net, combined with a bidirectional decoder and self-attention mechanism, is used to further analyze abnormal images. Experimental results show that the proposed method reaches an accuracy of 0.9913 in classification and achieves an improvement of around 3% in Dice compared to the baseline U-shaped model in segmentation.
doi_str_mv 10.1364/AO.409414
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2473412222</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2474314345</sourcerecordid><originalsourceid>FETCH-LOGICAL-c313t-dc389e5cc7cf8f4be06060ad27455edf08dc7e651660a9d4bd9dc088c15d72853</originalsourceid><addsrcrecordid>eNpdkctOwzAQRS0EoqWw4AeQJTawSIljO49lqXhJRd0UiV3k2pPKJXFKJgEh8fG4TWGBvfD46ujOjC4h5ywcMx6Lm8l8LMJMMHFAhhGTMuAslodk6MssYFH6OiAniOsw5FJkyTEZcM5jlsXRkHw_d2VrdakQaQOtdaqkxiIoBLpTbWG1am3tqHKGloDbEmFVgWt73To6ny7obYBa-V-lVoC0Q-tWVCuvGTBU1-6jLrst7xs4aD_r5g1PyVGhSoSz_TsiL_d3i-ljMJs_PE0ns0BzxtvAaJ5mILVOdJEWYglh7K8yUSKkBFOEqdEJxJLFXs2MWJrM6DBNNZMmiVLJR-Sq99009XsH2OaVRQ1lqRzUHeaRSLhgkT8evfyHruuu8UPvKMGZ4GJreN1TuqkRGyjyTeMXb75yFubbSPLJPO8j8ezF3rFbVmD-yN8M-A8usYfU</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2474314345</pqid></control><display><type>article</type><title>Multiclass retinal disease classification and lesion segmentation in OCT B-scan images using cascaded convolutional networks</title><source>Alma/SFX Local Collection</source><source>Optica Publishing Group Journals</source><creator>Zhong, Pan ; Wang, Jianlin ; Guo, Yongqi ; Fu, Xuesong ; Wang, Rutong</creator><creatorcontrib>Zhong, Pan ; Wang, Jianlin ; Guo, Yongqi ; Fu, Xuesong ; Wang, Rutong</creatorcontrib><description>Disease classification and lesion segmentation of retinal optical coherence tomography images play important roles in ophthalmic computer-aided diagnosis. However, existing methods achieve the two tasks separately, which is insufficient for clinical application and ignores the internal relation of disease and lesion features. In this paper, a framework of cascaded convolutional networks is proposed to jointly classify retinal diseases and segment lesions. First, we adopt an auxiliary binary classification network to identify normal and abnormal images. Then a novel, to the best of our knowledge, U-shaped multi-task network, BDA-Net, combined with a bidirectional decoder and self-attention mechanism, is used to further analyze abnormal images. Experimental results show that the proposed method reaches an accuracy of 0.9913 in classification and achieves an improvement of around 3% in Dice compared to the baseline U-shaped model in segmentation.</description><identifier>ISSN: 1559-128X</identifier><identifier>EISSN: 2155-3165</identifier><identifier>EISSN: 1539-4522</identifier><identifier>DOI: 10.1364/AO.409414</identifier><identifier>PMID: 33361962</identifier><language>eng</language><publisher>United States: Optical Society of America</publisher><subject>Classification ; Disease ; Image classification ; Image segmentation ; Medical imaging</subject><ispartof>Applied optics (2004), 2020-11, Vol.59 (33), p.10312-10320</ispartof><rights>Copyright Optical Society of America Nov 20, 2020</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c313t-dc389e5cc7cf8f4be06060ad27455edf08dc7e651660a9d4bd9dc088c15d72853</citedby><cites>FETCH-LOGICAL-c313t-dc389e5cc7cf8f4be06060ad27455edf08dc7e651660a9d4bd9dc088c15d72853</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780,3245,27901,27902</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/33361962$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Zhong, Pan</creatorcontrib><creatorcontrib>Wang, Jianlin</creatorcontrib><creatorcontrib>Guo, Yongqi</creatorcontrib><creatorcontrib>Fu, Xuesong</creatorcontrib><creatorcontrib>Wang, Rutong</creatorcontrib><title>Multiclass retinal disease classification and lesion segmentation in OCT B-scan images using cascaded convolutional networks</title><title>Applied optics (2004)</title><addtitle>Appl Opt</addtitle><description>Disease classification and lesion segmentation of retinal optical coherence tomography images play important roles in ophthalmic computer-aided diagnosis. However, existing methods achieve the two tasks separately, which is insufficient for clinical application and ignores the internal relation of disease and lesion features. In this paper, a framework of cascaded convolutional networks is proposed to jointly classify retinal diseases and segment lesions. First, we adopt an auxiliary binary classification network to identify normal and abnormal images. Then a novel, to the best of our knowledge, U-shaped multi-task network, BDA-Net, combined with a bidirectional decoder and self-attention mechanism, is used to further analyze abnormal images. Experimental results show that the proposed method reaches an accuracy of 0.9913 in classification and achieves an improvement of around 3% in Dice compared to the baseline U-shaped model in segmentation.</description><subject>Classification</subject><subject>Disease</subject><subject>Image classification</subject><subject>Image segmentation</subject><subject>Medical imaging</subject><issn>1559-128X</issn><issn>2155-3165</issn><issn>1539-4522</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><recordid>eNpdkctOwzAQRS0EoqWw4AeQJTawSIljO49lqXhJRd0UiV3k2pPKJXFKJgEh8fG4TWGBvfD46ujOjC4h5ywcMx6Lm8l8LMJMMHFAhhGTMuAslodk6MssYFH6OiAniOsw5FJkyTEZcM5jlsXRkHw_d2VrdakQaQOtdaqkxiIoBLpTbWG1am3tqHKGloDbEmFVgWt73To6ny7obYBa-V-lVoC0Q-tWVCuvGTBU1-6jLrst7xs4aD_r5g1PyVGhSoSz_TsiL_d3i-ljMJs_PE0ns0BzxtvAaJ5mILVOdJEWYglh7K8yUSKkBFOEqdEJxJLFXs2MWJrM6DBNNZMmiVLJR-Sq99009XsH2OaVRQ1lqRzUHeaRSLhgkT8evfyHruuu8UPvKMGZ4GJreN1TuqkRGyjyTeMXb75yFubbSPLJPO8j8ezF3rFbVmD-yN8M-A8usYfU</recordid><startdate>20201120</startdate><enddate>20201120</enddate><creator>Zhong, Pan</creator><creator>Wang, Jianlin</creator><creator>Guo, Yongqi</creator><creator>Fu, Xuesong</creator><creator>Wang, Rutong</creator><general>Optical Society of America</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>7U5</scope><scope>8FD</scope><scope>H8D</scope><scope>L7M</scope><scope>7X8</scope></search><sort><creationdate>20201120</creationdate><title>Multiclass retinal disease classification and lesion segmentation in OCT B-scan images using cascaded convolutional networks</title><author>Zhong, Pan ; Wang, Jianlin ; Guo, Yongqi ; Fu, Xuesong ; Wang, Rutong</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c313t-dc389e5cc7cf8f4be06060ad27455edf08dc7e651660a9d4bd9dc088c15d72853</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Classification</topic><topic>Disease</topic><topic>Image classification</topic><topic>Image segmentation</topic><topic>Medical imaging</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zhong, Pan</creatorcontrib><creatorcontrib>Wang, Jianlin</creatorcontrib><creatorcontrib>Guo, Yongqi</creatorcontrib><creatorcontrib>Fu, Xuesong</creatorcontrib><creatorcontrib>Wang, Rutong</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Solid State and Superconductivity Abstracts</collection><collection>Technology Research Database</collection><collection>Aerospace Database</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>MEDLINE - Academic</collection><jtitle>Applied optics (2004)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zhong, Pan</au><au>Wang, Jianlin</au><au>Guo, Yongqi</au><au>Fu, Xuesong</au><au>Wang, Rutong</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Multiclass retinal disease classification and lesion segmentation in OCT B-scan images using cascaded convolutional networks</atitle><jtitle>Applied optics (2004)</jtitle><addtitle>Appl Opt</addtitle><date>2020-11-20</date><risdate>2020</risdate><volume>59</volume><issue>33</issue><spage>10312</spage><epage>10320</epage><pages>10312-10320</pages><issn>1559-128X</issn><eissn>2155-3165</eissn><eissn>1539-4522</eissn><abstract>Disease classification and lesion segmentation of retinal optical coherence tomography images play important roles in ophthalmic computer-aided diagnosis. However, existing methods achieve the two tasks separately, which is insufficient for clinical application and ignores the internal relation of disease and lesion features. In this paper, a framework of cascaded convolutional networks is proposed to jointly classify retinal diseases and segment lesions. First, we adopt an auxiliary binary classification network to identify normal and abnormal images. Then a novel, to the best of our knowledge, U-shaped multi-task network, BDA-Net, combined with a bidirectional decoder and self-attention mechanism, is used to further analyze abnormal images. Experimental results show that the proposed method reaches an accuracy of 0.9913 in classification and achieves an improvement of around 3% in Dice compared to the baseline U-shaped model in segmentation.</abstract><cop>United States</cop><pub>Optical Society of America</pub><pmid>33361962</pmid><doi>10.1364/AO.409414</doi><tpages>9</tpages></addata></record>
fulltext fulltext
identifier ISSN: 1559-128X
ispartof Applied optics (2004), 2020-11, Vol.59 (33), p.10312-10320
issn 1559-128X
2155-3165
1539-4522
language eng
recordid cdi_proquest_miscellaneous_2473412222
source Alma/SFX Local Collection; Optica Publishing Group Journals
subjects Classification
Disease
Image classification
Image segmentation
Medical imaging
title Multiclass retinal disease classification and lesion segmentation in OCT B-scan images using cascaded convolutional networks
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-10T14%3A58%3A40IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Multiclass%20retinal%20disease%20classification%20and%20lesion%20segmentation%20in%20OCT%20B-scan%20images%20using%20cascaded%20convolutional%20networks&rft.jtitle=Applied%20optics%20(2004)&rft.au=Zhong,%20Pan&rft.date=2020-11-20&rft.volume=59&rft.issue=33&rft.spage=10312&rft.epage=10320&rft.pages=10312-10320&rft.issn=1559-128X&rft.eissn=2155-3165&rft_id=info:doi/10.1364/AO.409414&rft_dat=%3Cproquest_cross%3E2474314345%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2474314345&rft_id=info:pmid/33361962&rfr_iscdi=true