Deep Learning-Based Classification of Inherited Retinal Diseases Using Fundus Autofluorescence
Background. In recent years, deep learning has been increasingly applied to a vast array of ophthalmological diseases. Inherited retinal diseases (IRD) are rare genetic conditions with a distinctive phenotype on fundus autofluorescence imaging (FAF). Our purpose was to automatically classify differe...
Gespeichert in:
Veröffentlicht in: | Journal of clinical medicine 2020-10, Vol.9 (10), p.3303 |
---|---|
Hauptverfasser: | , , , , , , , , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | 10 |
container_start_page | 3303 |
container_title | Journal of clinical medicine |
container_volume | 9 |
creator | Miere, Alexandra Le Meur, Thomas Bitton, Karen Pallone, Carlotta Semoun, Oudy Capuano, Vittorio Colantuono, Donato Taibouni, Kawther Chenoune, Yasmina Astroz, Polina Berlemont, Sylvain Petit, Eric Souied, Eric |
description | Background. In recent years, deep learning has been increasingly applied to a vast array of ophthalmological diseases. Inherited retinal diseases (IRD) are rare genetic conditions with a distinctive phenotype on fundus autofluorescence imaging (FAF). Our purpose was to automatically classify different IRDs by means of FAF images using a deep learning algorithm. Methods. In this study, FAF images of patients with retinitis pigmentosa (RP), Best disease (BD), Stargardt disease (STGD), as well as a healthy comparable group were used to train a multilayer deep convolutional neural network (CNN) to differentiate FAF images between each type of IRD and normal FAF. The CNN was trained and validated with 389 FAF images. Established augmentation techniques were used. An Adam optimizer was used for training. For subsequent testing, the built classifiers were then tested with 94 untrained FAF images. Results. For the inherited retinal disease classifiers, global accuracy was 0.95. The precision-recall area under the curve (PRC-AUC) averaged 0.988 for BD, 0.999 for RP, 0.996 for STGD, and 0.989 for healthy controls. Conclusions. This study describes the use of a deep learning-based algorithm to automatically detect and classify inherited retinal disease in FAF. Hereby, the created classifiers showed excellent results. With further developments, this model may be a diagnostic tool and may give relevant information for future therapeutic approaches. |
doi_str_mv | 10.3390/jcm9103303 |
format | Article |
fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_7602508</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2641139825</sourcerecordid><originalsourceid>FETCH-LOGICAL-c524t-d8fd532c4ab3fb9cef91ea73c51ad05626626bae11d428125e28a535ed8346343</originalsourceid><addsrcrecordid>eNpdkdtKAzEQhoMoWqo3PsGCNyqs5ribvRFqPUJBEL01pNlZm7JNarJb8O1NqXjoMJAh880_mQxCxwRfMFbhy7lZVAQzhtkOGlBcljlmku3-iQ_QUYxznExKTkm5jw4SXiQjA_R2A7DMJqCDs-49v9YR6mzc6hhtY43urHeZb7JHN4Ngu5R7hs463WY3NkKCY_YaU2F217u6j9mo73zT9j5ANOAMHKK9RrcRjr7PIXq9u30ZP-STp_vH8WiSG0F5l9eyqQWjhuspa6aVgaYioEtmBNE1FgUtkk81EFJzKgkVQKUWTEAtGS8YZ0N0tdFd9tMF1Kl3F3SrlsEudPhUXlv1P-PsTL37lSoLTAWWSeBsIzDbKnsYTdT6DnMsOBd8RRJ7-t0s-I8eYqcWNo3bttqB76OiXBApKJE4oSdb6Nz3If1fogpOCKskFYk631Am-BgDND8vIFitt6x-t8y-ALNDmA0</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2641139825</pqid></control><display><type>article</type><title>Deep Learning-Based Classification of Inherited Retinal Diseases Using Fundus Autofluorescence</title><source>PubMed Central Open Access</source><source>MDPI - Multidisciplinary Digital Publishing Institute</source><source>EZB-FREE-00999 freely available EZB journals</source><source>PubMed Central</source><creator>Miere, Alexandra ; Le Meur, Thomas ; Bitton, Karen ; Pallone, Carlotta ; Semoun, Oudy ; Capuano, Vittorio ; Colantuono, Donato ; Taibouni, Kawther ; Chenoune, Yasmina ; Astroz, Polina ; Berlemont, Sylvain ; Petit, Eric ; Souied, Eric</creator><creatorcontrib>Miere, Alexandra ; Le Meur, Thomas ; Bitton, Karen ; Pallone, Carlotta ; Semoun, Oudy ; Capuano, Vittorio ; Colantuono, Donato ; Taibouni, Kawther ; Chenoune, Yasmina ; Astroz, Polina ; Berlemont, Sylvain ; Petit, Eric ; Souied, Eric</creatorcontrib><description>Background. In recent years, deep learning has been increasingly applied to a vast array of ophthalmological diseases. Inherited retinal diseases (IRD) are rare genetic conditions with a distinctive phenotype on fundus autofluorescence imaging (FAF). Our purpose was to automatically classify different IRDs by means of FAF images using a deep learning algorithm. Methods. In this study, FAF images of patients with retinitis pigmentosa (RP), Best disease (BD), Stargardt disease (STGD), as well as a healthy comparable group were used to train a multilayer deep convolutional neural network (CNN) to differentiate FAF images between each type of IRD and normal FAF. The CNN was trained and validated with 389 FAF images. Established augmentation techniques were used. An Adam optimizer was used for training. For subsequent testing, the built classifiers were then tested with 94 untrained FAF images. Results. For the inherited retinal disease classifiers, global accuracy was 0.95. The precision-recall area under the curve (PRC-AUC) averaged 0.988 for BD, 0.999 for RP, 0.996 for STGD, and 0.989 for healthy controls. Conclusions. This study describes the use of a deep learning-based algorithm to automatically detect and classify inherited retinal disease in FAF. Hereby, the created classifiers showed excellent results. With further developments, this model may be a diagnostic tool and may give relevant information for future therapeutic approaches.</description><identifier>ISSN: 2077-0383</identifier><identifier>EISSN: 2077-0383</identifier><identifier>DOI: 10.3390/jcm9103303</identifier><identifier>PMID: 33066661</identifier><language>eng</language><publisher>Basel: MDPI AG</publisher><subject>Atrophy ; Automation ; Classification ; Clinical medicine ; Computer Science ; Datasets ; Deep learning ; Diabetic retinopathy ; Disease ; Neural networks ; Ophthalmology ; Retina</subject><ispartof>Journal of clinical medicine, 2020-10, Vol.9 (10), p.3303</ispartof><rights>2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>Distributed under a Creative Commons Attribution 4.0 International License</rights><rights>2020 by the authors. 2020</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c524t-d8fd532c4ab3fb9cef91ea73c51ad05626626bae11d428125e28a535ed8346343</citedby><cites>FETCH-LOGICAL-c524t-d8fd532c4ab3fb9cef91ea73c51ad05626626bae11d428125e28a535ed8346343</cites><orcidid>0000-0003-4123-8210</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC7602508/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC7602508/$$EHTML$$P50$$Gpubmedcentral$$Hfree_for_read</linktohtml><link.rule.ids>230,314,727,780,784,885,27924,27925,53791,53793</link.rule.ids><backlink>$$Uhttps://hal.u-pec.fr/hal-04054454$$DView record in HAL$$Hfree_for_read</backlink></links><search><creatorcontrib>Miere, Alexandra</creatorcontrib><creatorcontrib>Le Meur, Thomas</creatorcontrib><creatorcontrib>Bitton, Karen</creatorcontrib><creatorcontrib>Pallone, Carlotta</creatorcontrib><creatorcontrib>Semoun, Oudy</creatorcontrib><creatorcontrib>Capuano, Vittorio</creatorcontrib><creatorcontrib>Colantuono, Donato</creatorcontrib><creatorcontrib>Taibouni, Kawther</creatorcontrib><creatorcontrib>Chenoune, Yasmina</creatorcontrib><creatorcontrib>Astroz, Polina</creatorcontrib><creatorcontrib>Berlemont, Sylvain</creatorcontrib><creatorcontrib>Petit, Eric</creatorcontrib><creatorcontrib>Souied, Eric</creatorcontrib><title>Deep Learning-Based Classification of Inherited Retinal Diseases Using Fundus Autofluorescence</title><title>Journal of clinical medicine</title><description>Background. In recent years, deep learning has been increasingly applied to a vast array of ophthalmological diseases. Inherited retinal diseases (IRD) are rare genetic conditions with a distinctive phenotype on fundus autofluorescence imaging (FAF). Our purpose was to automatically classify different IRDs by means of FAF images using a deep learning algorithm. Methods. In this study, FAF images of patients with retinitis pigmentosa (RP), Best disease (BD), Stargardt disease (STGD), as well as a healthy comparable group were used to train a multilayer deep convolutional neural network (CNN) to differentiate FAF images between each type of IRD and normal FAF. The CNN was trained and validated with 389 FAF images. Established augmentation techniques were used. An Adam optimizer was used for training. For subsequent testing, the built classifiers were then tested with 94 untrained FAF images. Results. For the inherited retinal disease classifiers, global accuracy was 0.95. The precision-recall area under the curve (PRC-AUC) averaged 0.988 for BD, 0.999 for RP, 0.996 for STGD, and 0.989 for healthy controls. Conclusions. This study describes the use of a deep learning-based algorithm to automatically detect and classify inherited retinal disease in FAF. Hereby, the created classifiers showed excellent results. With further developments, this model may be a diagnostic tool and may give relevant information for future therapeutic approaches.</description><subject>Atrophy</subject><subject>Automation</subject><subject>Classification</subject><subject>Clinical medicine</subject><subject>Computer Science</subject><subject>Datasets</subject><subject>Deep learning</subject><subject>Diabetic retinopathy</subject><subject>Disease</subject><subject>Neural networks</subject><subject>Ophthalmology</subject><subject>Retina</subject><issn>2077-0383</issn><issn>2077-0383</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNpdkdtKAzEQhoMoWqo3PsGCNyqs5ribvRFqPUJBEL01pNlZm7JNarJb8O1NqXjoMJAh880_mQxCxwRfMFbhy7lZVAQzhtkOGlBcljlmku3-iQ_QUYxznExKTkm5jw4SXiQjA_R2A7DMJqCDs-49v9YR6mzc6hhtY43urHeZb7JHN4Ngu5R7hs463WY3NkKCY_YaU2F217u6j9mo73zT9j5ANOAMHKK9RrcRjr7PIXq9u30ZP-STp_vH8WiSG0F5l9eyqQWjhuspa6aVgaYioEtmBNE1FgUtkk81EFJzKgkVQKUWTEAtGS8YZ0N0tdFd9tMF1Kl3F3SrlsEudPhUXlv1P-PsTL37lSoLTAWWSeBsIzDbKnsYTdT6DnMsOBd8RRJ7-t0s-I8eYqcWNo3bttqB76OiXBApKJE4oSdb6Nz3If1fogpOCKskFYk631Am-BgDND8vIFitt6x-t8y-ALNDmA0</recordid><startdate>20201014</startdate><enddate>20201014</enddate><creator>Miere, Alexandra</creator><creator>Le Meur, Thomas</creator><creator>Bitton, Karen</creator><creator>Pallone, Carlotta</creator><creator>Semoun, Oudy</creator><creator>Capuano, Vittorio</creator><creator>Colantuono, Donato</creator><creator>Taibouni, Kawther</creator><creator>Chenoune, Yasmina</creator><creator>Astroz, Polina</creator><creator>Berlemont, Sylvain</creator><creator>Petit, Eric</creator><creator>Souied, Eric</creator><general>MDPI AG</general><general>MDPI</general><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7X7</scope><scope>7XB</scope><scope>8FI</scope><scope>8FJ</scope><scope>8FK</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FYUFA</scope><scope>GHDGH</scope><scope>K9.</scope><scope>M0S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>7X8</scope><scope>1XC</scope><scope>VOOES</scope><scope>5PM</scope><orcidid>https://orcid.org/0000-0003-4123-8210</orcidid></search><sort><creationdate>20201014</creationdate><title>Deep Learning-Based Classification of Inherited Retinal Diseases Using Fundus Autofluorescence</title><author>Miere, Alexandra ; Le Meur, Thomas ; Bitton, Karen ; Pallone, Carlotta ; Semoun, Oudy ; Capuano, Vittorio ; Colantuono, Donato ; Taibouni, Kawther ; Chenoune, Yasmina ; Astroz, Polina ; Berlemont, Sylvain ; Petit, Eric ; Souied, Eric</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c524t-d8fd532c4ab3fb9cef91ea73c51ad05626626bae11d428125e28a535ed8346343</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Atrophy</topic><topic>Automation</topic><topic>Classification</topic><topic>Clinical medicine</topic><topic>Computer Science</topic><topic>Datasets</topic><topic>Deep learning</topic><topic>Diabetic retinopathy</topic><topic>Disease</topic><topic>Neural networks</topic><topic>Ophthalmology</topic><topic>Retina</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Miere, Alexandra</creatorcontrib><creatorcontrib>Le Meur, Thomas</creatorcontrib><creatorcontrib>Bitton, Karen</creatorcontrib><creatorcontrib>Pallone, Carlotta</creatorcontrib><creatorcontrib>Semoun, Oudy</creatorcontrib><creatorcontrib>Capuano, Vittorio</creatorcontrib><creatorcontrib>Colantuono, Donato</creatorcontrib><creatorcontrib>Taibouni, Kawther</creatorcontrib><creatorcontrib>Chenoune, Yasmina</creatorcontrib><creatorcontrib>Astroz, Polina</creatorcontrib><creatorcontrib>Berlemont, Sylvain</creatorcontrib><creatorcontrib>Petit, Eric</creatorcontrib><creatorcontrib>Souied, Eric</creatorcontrib><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>Health & Medical Collection</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Hospital Premium Collection</collection><collection>Hospital Premium Collection (Alumni Edition)</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>Health Research Premium Collection</collection><collection>Health Research Premium Collection (Alumni)</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Health & Medical Collection (Alumni Edition)</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>MEDLINE - Academic</collection><collection>Hyper Article en Ligne (HAL)</collection><collection>Hyper Article en Ligne (HAL) (Open Access)</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Journal of clinical medicine</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Miere, Alexandra</au><au>Le Meur, Thomas</au><au>Bitton, Karen</au><au>Pallone, Carlotta</au><au>Semoun, Oudy</au><au>Capuano, Vittorio</au><au>Colantuono, Donato</au><au>Taibouni, Kawther</au><au>Chenoune, Yasmina</au><au>Astroz, Polina</au><au>Berlemont, Sylvain</au><au>Petit, Eric</au><au>Souied, Eric</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Deep Learning-Based Classification of Inherited Retinal Diseases Using Fundus Autofluorescence</atitle><jtitle>Journal of clinical medicine</jtitle><date>2020-10-14</date><risdate>2020</risdate><volume>9</volume><issue>10</issue><spage>3303</spage><pages>3303-</pages><issn>2077-0383</issn><eissn>2077-0383</eissn><abstract>Background. In recent years, deep learning has been increasingly applied to a vast array of ophthalmological diseases. Inherited retinal diseases (IRD) are rare genetic conditions with a distinctive phenotype on fundus autofluorescence imaging (FAF). Our purpose was to automatically classify different IRDs by means of FAF images using a deep learning algorithm. Methods. In this study, FAF images of patients with retinitis pigmentosa (RP), Best disease (BD), Stargardt disease (STGD), as well as a healthy comparable group were used to train a multilayer deep convolutional neural network (CNN) to differentiate FAF images between each type of IRD and normal FAF. The CNN was trained and validated with 389 FAF images. Established augmentation techniques were used. An Adam optimizer was used for training. For subsequent testing, the built classifiers were then tested with 94 untrained FAF images. Results. For the inherited retinal disease classifiers, global accuracy was 0.95. The precision-recall area under the curve (PRC-AUC) averaged 0.988 for BD, 0.999 for RP, 0.996 for STGD, and 0.989 for healthy controls. Conclusions. This study describes the use of a deep learning-based algorithm to automatically detect and classify inherited retinal disease in FAF. Hereby, the created classifiers showed excellent results. With further developments, this model may be a diagnostic tool and may give relevant information for future therapeutic approaches.</abstract><cop>Basel</cop><pub>MDPI AG</pub><pmid>33066661</pmid><doi>10.3390/jcm9103303</doi><orcidid>https://orcid.org/0000-0003-4123-8210</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 2077-0383 |
ispartof | Journal of clinical medicine, 2020-10, Vol.9 (10), p.3303 |
issn | 2077-0383 2077-0383 |
language | eng |
recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_7602508 |
source | PubMed Central Open Access; MDPI - Multidisciplinary Digital Publishing Institute; EZB-FREE-00999 freely available EZB journals; PubMed Central |
subjects | Atrophy Automation Classification Clinical medicine Computer Science Datasets Deep learning Diabetic retinopathy Disease Neural networks Ophthalmology Retina |
title | Deep Learning-Based Classification of Inherited Retinal Diseases Using Fundus Autofluorescence |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T20%3A45%3A29IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Deep%20Learning-Based%20Classification%20of%20Inherited%20Retinal%20Diseases%20Using%20Fundus%20Autofluorescence&rft.jtitle=Journal%20of%20clinical%20medicine&rft.au=Miere,%20Alexandra&rft.date=2020-10-14&rft.volume=9&rft.issue=10&rft.spage=3303&rft.pages=3303-&rft.issn=2077-0383&rft.eissn=2077-0383&rft_id=info:doi/10.3390/jcm9103303&rft_dat=%3Cproquest_pubme%3E2641139825%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2641139825&rft_id=info:pmid/33066661&rfr_iscdi=true |