U-net Based Method for Automatic Hard Exudates Segmentation in Fundus Images Using Inception Module and Residual Connection
Diabetic retinopathy (DR) is an eye abnormality caused by chronic diabetes that affected patients worldwide. Hard exudate is an important and observable sign of DR and can be used for early diagnosis. In this paper, an automatic hard exudates segmentation method is proposed in order to aid ophthalmo...
Gespeichert in:
| Veröffentlicht in: | IEEE access 2020, Vol.8, p.167225-167235 |
|---|---|
| Hauptverfasser: | , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 167235 |
|---|---|
| container_issue | |
| container_start_page | 167225 |
| container_title | IEEE access |
| container_volume | 8 |
| creator | Zong, Yongshuo Chen, Jinling Yang, Lvqing Tao, Siyi Aoma, Cieryouzhen Zhao, Jiangsheng Wang, Shuihua |
| description | Diabetic retinopathy (DR) is an eye abnormality caused by chronic diabetes that affected patients worldwide. Hard exudate is an important and observable sign of DR and can be used for early diagnosis. In this paper, an automatic hard exudates segmentation method is proposed in order to aid ophthalmologists to diagnose DR in the early stage. We utilized the SLIC superpixel algorithm to generate sample patches, thus overcoming the difficulty of the limited and imbalanced dataset. Furthermore, a U-net based network architecture with inception modules and residual connections is proposed to conduct end-to-end hard exudate segmentation, and focal loss is utilized as the loss function. Extensive experiments have been conducted on the IDRiD dataset to evaluate the performance of the proposed method. The reported sensitivity, specificity, and accuracy achieve 96.38%, 97.14%, and 97.95% respectively, which demonstrates the effectiveness and superiority of our method. The achieved segmentation results prove the potential of the method for clinical diagnosis. |
| doi_str_mv | 10.1109/ACCESS.2020.3023273 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2454678472</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9194249</ieee_id><doaj_id>oai_doaj_org_article_11af494d5ec74a838a21b10749a4247c</doaj_id><sourcerecordid>2454678472</sourcerecordid><originalsourceid>FETCH-LOGICAL-c408t-d182be5512f058d521c9d45e79709e34bdd29b3c3a2fc8e444cb9cd46267afa83</originalsourceid><addsrcrecordid>eNpNUd1r2zAQN2OFlbZ_QV8EfXamL1vWY2bSNdAyWJpncZbOqUMiZZING_3nq9SlTC8n7vdxd_yK4pbRBWNUf1-27WqzWXDK6UJQLrgSX4pLzmpdikrUX__7fytuUtrT_JrcqtRl8botPY7kByR05AnHl-BIHyJZTmM4wjhY8gDRkdXfycGIiWxwd0Q_ZiR4MnhyP3k3JbI-wi6j2zT4HVl7i6d3wlNw0wEJeEd-YxrcBAfSBu_RnuHr4qKHQ8Kbj3pVbO9Xz-1D-fjr57pdPpZW0mYsHWt4h1XFeE-rxlWcWe1khUorqlHIzjmuO2EF8N42KKW0nbZO1rxW0EMjror17OsC7M0pDkeI_0yAwbw3QtwZiPnUAxrGoJdaugqtklnaAGcdo0pqkFwqm73uZq9TDH8mTKPZhyn6vL7hspK1aqTimSVmlo0hpYj951RGzTk0M4dmzqGZj9Cy6nZWDYj4qdBM59FavAFsb5LG</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2454678472</pqid></control><display><type>article</type><title>U-net Based Method for Automatic Hard Exudates Segmentation in Fundus Images Using Inception Module and Residual Connection</title><source>DOAJ Directory of Open Access Journals</source><source>IEEE Xplore Open Access Journals</source><source>EZB Electronic Journals Library</source><creator>Zong, Yongshuo ; Chen, Jinling ; Yang, Lvqing ; Tao, Siyi ; Aoma, Cieryouzhen ; Zhao, Jiangsheng ; Wang, Shuihua</creator><creatorcontrib>Zong, Yongshuo ; Chen, Jinling ; Yang, Lvqing ; Tao, Siyi ; Aoma, Cieryouzhen ; Zhao, Jiangsheng ; Wang, Shuihua</creatorcontrib><description>Diabetic retinopathy (DR) is an eye abnormality caused by chronic diabetes that affected patients worldwide. Hard exudate is an important and observable sign of DR and can be used for early diagnosis. In this paper, an automatic hard exudates segmentation method is proposed in order to aid ophthalmologists to diagnose DR in the early stage. We utilized the SLIC superpixel algorithm to generate sample patches, thus overcoming the difficulty of the limited and imbalanced dataset. Furthermore, a U-net based network architecture with inception modules and residual connections is proposed to conduct end-to-end hard exudate segmentation, and focal loss is utilized as the loss function. Extensive experiments have been conducted on the IDRiD dataset to evaluate the performance of the proposed method. The reported sensitivity, specificity, and accuracy achieve 96.38%, 97.14%, and 97.95% respectively, which demonstrates the effectiveness and superiority of our method. The achieved segmentation results prove the potential of the method for clinical diagnosis.</description><identifier>ISSN: 2169-3536</identifier><identifier>EISSN: 2169-3536</identifier><identifier>DOI: 10.1109/ACCESS.2020.3023273</identifier><identifier>CODEN: IAECCG</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Algorithms ; Biomedical imaging ; Classification algorithms ; Computer architecture ; Datasets ; Deep learning ; Diabetes ; Diabetic retinopathy ; Diagnosis ; exudates segmentation ; Exudation ; Feature extraction ; Image color analysis ; Image segmentation ; Machine learning ; Modules ; superpixel ; U-net</subject><ispartof>IEEE access, 2020, Vol.8, p.167225-167235</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c408t-d182be5512f058d521c9d45e79709e34bdd29b3c3a2fc8e444cb9cd46267afa83</citedby><cites>FETCH-LOGICAL-c408t-d182be5512f058d521c9d45e79709e34bdd29b3c3a2fc8e444cb9cd46267afa83</cites><orcidid>0000-0003-2238-6808 ; 0000-0002-3267-753X ; 0000-0002-3245-2613</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9194249$$EHTML$$P50$$Gieee$$Hfree_for_read</linktohtml><link.rule.ids>314,777,781,861,2096,4010,27614,27904,27905,27906,54914</link.rule.ids></links><search><creatorcontrib>Zong, Yongshuo</creatorcontrib><creatorcontrib>Chen, Jinling</creatorcontrib><creatorcontrib>Yang, Lvqing</creatorcontrib><creatorcontrib>Tao, Siyi</creatorcontrib><creatorcontrib>Aoma, Cieryouzhen</creatorcontrib><creatorcontrib>Zhao, Jiangsheng</creatorcontrib><creatorcontrib>Wang, Shuihua</creatorcontrib><title>U-net Based Method for Automatic Hard Exudates Segmentation in Fundus Images Using Inception Module and Residual Connection</title><title>IEEE access</title><addtitle>Access</addtitle><description>Diabetic retinopathy (DR) is an eye abnormality caused by chronic diabetes that affected patients worldwide. Hard exudate is an important and observable sign of DR and can be used for early diagnosis. In this paper, an automatic hard exudates segmentation method is proposed in order to aid ophthalmologists to diagnose DR in the early stage. We utilized the SLIC superpixel algorithm to generate sample patches, thus overcoming the difficulty of the limited and imbalanced dataset. Furthermore, a U-net based network architecture with inception modules and residual connections is proposed to conduct end-to-end hard exudate segmentation, and focal loss is utilized as the loss function. Extensive experiments have been conducted on the IDRiD dataset to evaluate the performance of the proposed method. The reported sensitivity, specificity, and accuracy achieve 96.38%, 97.14%, and 97.95% respectively, which demonstrates the effectiveness and superiority of our method. The achieved segmentation results prove the potential of the method for clinical diagnosis.</description><subject>Algorithms</subject><subject>Biomedical imaging</subject><subject>Classification algorithms</subject><subject>Computer architecture</subject><subject>Datasets</subject><subject>Deep learning</subject><subject>Diabetes</subject><subject>Diabetic retinopathy</subject><subject>Diagnosis</subject><subject>exudates segmentation</subject><subject>Exudation</subject><subject>Feature extraction</subject><subject>Image color analysis</subject><subject>Image segmentation</subject><subject>Machine learning</subject><subject>Modules</subject><subject>superpixel</subject><subject>U-net</subject><issn>2169-3536</issn><issn>2169-3536</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>ESBDL</sourceid><sourceid>RIE</sourceid><sourceid>DOA</sourceid><recordid>eNpNUd1r2zAQN2OFlbZ_QV8EfXamL1vWY2bSNdAyWJpncZbOqUMiZZING_3nq9SlTC8n7vdxd_yK4pbRBWNUf1-27WqzWXDK6UJQLrgSX4pLzmpdikrUX__7fytuUtrT_JrcqtRl8botPY7kByR05AnHl-BIHyJZTmM4wjhY8gDRkdXfycGIiWxwd0Q_ZiR4MnhyP3k3JbI-wi6j2zT4HVl7i6d3wlNw0wEJeEd-YxrcBAfSBu_RnuHr4qKHQ8Kbj3pVbO9Xz-1D-fjr57pdPpZW0mYsHWt4h1XFeE-rxlWcWe1khUorqlHIzjmuO2EF8N42KKW0nbZO1rxW0EMjror17OsC7M0pDkeI_0yAwbw3QtwZiPnUAxrGoJdaugqtklnaAGcdo0pqkFwqm73uZq9TDH8mTKPZhyn6vL7hspK1aqTimSVmlo0hpYj951RGzTk0M4dmzqGZj9Cy6nZWDYj4qdBM59FavAFsb5LG</recordid><startdate>2020</startdate><enddate>2020</enddate><creator>Zong, Yongshuo</creator><creator>Chen, Jinling</creator><creator>Yang, Lvqing</creator><creator>Tao, Siyi</creator><creator>Aoma, Cieryouzhen</creator><creator>Zhao, Jiangsheng</creator><creator>Wang, Shuihua</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/0000-0003-2238-6808</orcidid><orcidid>https://orcid.org/0000-0002-3267-753X</orcidid><orcidid>https://orcid.org/0000-0002-3245-2613</orcidid></search><sort><creationdate>2020</creationdate><title>U-net Based Method for Automatic Hard Exudates Segmentation in Fundus Images Using Inception Module and Residual Connection</title><author>Zong, Yongshuo ; Chen, Jinling ; Yang, Lvqing ; Tao, Siyi ; Aoma, Cieryouzhen ; Zhao, Jiangsheng ; Wang, Shuihua</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c408t-d182be5512f058d521c9d45e79709e34bdd29b3c3a2fc8e444cb9cd46267afa83</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Algorithms</topic><topic>Biomedical imaging</topic><topic>Classification algorithms</topic><topic>Computer architecture</topic><topic>Datasets</topic><topic>Deep learning</topic><topic>Diabetes</topic><topic>Diabetic retinopathy</topic><topic>Diagnosis</topic><topic>exudates segmentation</topic><topic>Exudation</topic><topic>Feature extraction</topic><topic>Image color analysis</topic><topic>Image segmentation</topic><topic>Machine learning</topic><topic>Modules</topic><topic>superpixel</topic><topic>U-net</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zong, Yongshuo</creatorcontrib><creatorcontrib>Chen, Jinling</creatorcontrib><creatorcontrib>Yang, Lvqing</creatorcontrib><creatorcontrib>Tao, Siyi</creatorcontrib><creatorcontrib>Aoma, Cieryouzhen</creatorcontrib><creatorcontrib>Zhao, Jiangsheng</creatorcontrib><creatorcontrib>Wang, Shuihua</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) 1998-Present</collection><collection>IEEE Xplore</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & 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>Zong, Yongshuo</au><au>Chen, Jinling</au><au>Yang, Lvqing</au><au>Tao, Siyi</au><au>Aoma, Cieryouzhen</au><au>Zhao, Jiangsheng</au><au>Wang, Shuihua</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>U-net Based Method for Automatic Hard Exudates Segmentation in Fundus Images Using Inception Module and Residual Connection</atitle><jtitle>IEEE access</jtitle><stitle>Access</stitle><date>2020</date><risdate>2020</risdate><volume>8</volume><spage>167225</spage><epage>167235</epage><pages>167225-167235</pages><issn>2169-3536</issn><eissn>2169-3536</eissn><coden>IAECCG</coden><abstract>Diabetic retinopathy (DR) is an eye abnormality caused by chronic diabetes that affected patients worldwide. Hard exudate is an important and observable sign of DR and can be used for early diagnosis. In this paper, an automatic hard exudates segmentation method is proposed in order to aid ophthalmologists to diagnose DR in the early stage. We utilized the SLIC superpixel algorithm to generate sample patches, thus overcoming the difficulty of the limited and imbalanced dataset. Furthermore, a U-net based network architecture with inception modules and residual connections is proposed to conduct end-to-end hard exudate segmentation, and focal loss is utilized as the loss function. Extensive experiments have been conducted on the IDRiD dataset to evaluate the performance of the proposed method. The reported sensitivity, specificity, and accuracy achieve 96.38%, 97.14%, and 97.95% respectively, which demonstrates the effectiveness and superiority of our method. The achieved segmentation results prove the potential of the method for clinical diagnosis.</abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/ACCESS.2020.3023273</doi><tpages>11</tpages><orcidid>https://orcid.org/0000-0003-2238-6808</orcidid><orcidid>https://orcid.org/0000-0002-3267-753X</orcidid><orcidid>https://orcid.org/0000-0002-3245-2613</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 2169-3536 |
| ispartof | IEEE access, 2020, Vol.8, p.167225-167235 |
| issn | 2169-3536 2169-3536 |
| language | eng |
| recordid | cdi_proquest_journals_2454678472 |
| source | DOAJ Directory of Open Access Journals; IEEE Xplore Open Access Journals; EZB Electronic Journals Library |
| subjects | Algorithms Biomedical imaging Classification algorithms Computer architecture Datasets Deep learning Diabetes Diabetic retinopathy Diagnosis exudates segmentation Exudation Feature extraction Image color analysis Image segmentation Machine learning Modules superpixel U-net |
| title | U-net Based Method for Automatic Hard Exudates Segmentation in Fundus Images Using Inception Module and Residual Connection |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-17T18%3A22%3A22IST&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=U-net%20Based%20Method%20for%20Automatic%20Hard%20Exudates%20Segmentation%20in%20Fundus%20Images%20Using%20Inception%20Module%20and%20Residual%20Connection&rft.jtitle=IEEE%20access&rft.au=Zong,%20Yongshuo&rft.date=2020&rft.volume=8&rft.spage=167225&rft.epage=167235&rft.pages=167225-167235&rft.issn=2169-3536&rft.eissn=2169-3536&rft.coden=IAECCG&rft_id=info:doi/10.1109/ACCESS.2020.3023273&rft_dat=%3Cproquest_cross%3E2454678472%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=2454678472&rft_id=info:pmid/&rft_ieee_id=9194249&rft_doaj_id=oai_doaj_org_article_11af494d5ec74a838a21b10749a4247c&rfr_iscdi=true |