Deep Learning Models for Automated Diagnosis of Retinopathy of Prematurity in Preterm Infants
Retinopathy of prematurity (ROP) is a disease that can cause blindness in premature infants. It is characterized by immature vascular growth of the retinal blood vessels. However, early detection and treatment of ROP can significantly improve the visual acuity of high-risk patients. Thus, early diag...
Gespeichert in:
Veröffentlicht in: | Electronics (Basel) 2020-09, Vol.9 (9), p.1444 |
---|---|
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 | 9 |
container_start_page | 1444 |
container_title | Electronics (Basel) |
container_volume | 9 |
creator | Huang, Yo-Ping Vadloori, Spandana Chu, Hung-Chi Kang, Eugene Yu-Chuan Wu, Wei-Chi Kusaka, Shunji Fukushima, Yoko |
description | Retinopathy of prematurity (ROP) is a disease that can cause blindness in premature infants. It is characterized by immature vascular growth of the retinal blood vessels. However, early detection and treatment of ROP can significantly improve the visual acuity of high-risk patients. Thus, early diagnosis of ROP is crucial in preventing visual impairment. However, several patients refrain from treatment owing to the lack of medical expertise in diagnosing the disease; this is especially problematic considering that the number of ROP cases is on the rise. To this end, we applied transfer learning to five deep neural network architectures for identifying ROP in preterm infants. Our results showed that the VGG19 model outperformed the other models in determining whether a preterm infant has ROP, with 96% accuracy, 96.6% sensitivity, and 95.2% specificity. We also classified the severity of the disease; the VGG19 model showed 98.82% accuracy in predicting the severity of the disease with a sensitivity and specificity of 100% and 98.41%, respectively. We performed 5-fold cross-validation on the datasets to validate the reliability of the VGG19 model and found that the VGG19 model exhibited high accuracy in predicting ROP. These findings could help promote the development of computer-aided diagnosis. |
doi_str_mv | 10.3390/electronics9091444 |
format | Article |
fullrecord | <record><control><sourceid>gale_proqu</sourceid><recordid>TN_cdi_proquest_journals_2441101962</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><galeid>A643043566</galeid><sourcerecordid>A643043566</sourcerecordid><originalsourceid>FETCH-LOGICAL-c413t-29557dc4f37e2f7fe8ad97943813e45ab4887e8ee62952f1155b6b13325aab583</originalsourceid><addsrcrecordid>eNplkF1LwzAYhYsoOHR_wKuA19V8ts3l2PwYTBTRSwlp-2ZmtElN0ov9ezsmKPjenPfAwzlwsuyK4BvGJL6FDpoUvLNNlFgSzvlJNqO4lLmkkp7--c-zeYw7PJ0krGJ4ln2sAAa0AR2cdVv05FvoIjI-oMWYfK8TtGhl9db5aCPyBr1Css4POn3uD_YlwASNwaY9su5gE4QerZ3RLsXL7MzoLsL8Ry-y9_u7t-Vjvnl-WC8Xm7zhhKWcSiHKtuGGlUBNaaDSrSwlZxVhwIWueVWVUAEUE0kNIULURU0Yo0LrWlTsIrs-5g7Bf40Qk9r5MbipUlHOCcFEFvSX2uoOlHXGp6Cb3sZGLQrOMGeiKCaKHqkm-BgDGDUE2-uwVwSrw97q_97sG7kydTU</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2441101962</pqid></control><display><type>article</type><title>Deep Learning Models for Automated Diagnosis of Retinopathy of Prematurity in Preterm Infants</title><source>MDPI - Multidisciplinary Digital Publishing Institute</source><source>EZB-FREE-00999 freely available EZB journals</source><creator>Huang, Yo-Ping ; Vadloori, Spandana ; Chu, Hung-Chi ; Kang, Eugene Yu-Chuan ; Wu, Wei-Chi ; Kusaka, Shunji ; Fukushima, Yoko</creator><creatorcontrib>Huang, Yo-Ping ; Vadloori, Spandana ; Chu, Hung-Chi ; Kang, Eugene Yu-Chuan ; Wu, Wei-Chi ; Kusaka, Shunji ; Fukushima, Yoko</creatorcontrib><description>Retinopathy of prematurity (ROP) is a disease that can cause blindness in premature infants. It is characterized by immature vascular growth of the retinal blood vessels. However, early detection and treatment of ROP can significantly improve the visual acuity of high-risk patients. Thus, early diagnosis of ROP is crucial in preventing visual impairment. However, several patients refrain from treatment owing to the lack of medical expertise in diagnosing the disease; this is especially problematic considering that the number of ROP cases is on the rise. To this end, we applied transfer learning to five deep neural network architectures for identifying ROP in preterm infants. Our results showed that the VGG19 model outperformed the other models in determining whether a preterm infant has ROP, with 96% accuracy, 96.6% sensitivity, and 95.2% specificity. We also classified the severity of the disease; the VGG19 model showed 98.82% accuracy in predicting the severity of the disease with a sensitivity and specificity of 100% and 98.41%, respectively. We performed 5-fold cross-validation on the datasets to validate the reliability of the VGG19 model and found that the VGG19 model exhibited high accuracy in predicting ROP. These findings could help promote the development of computer-aided diagnosis.</description><identifier>ISSN: 2079-9292</identifier><identifier>EISSN: 2079-9292</identifier><identifier>DOI: 10.3390/electronics9091444</identifier><language>eng</language><publisher>Basel: MDPI AG</publisher><subject>Applied research ; Artificial intelligence ; Artificial neural networks ; Automation ; Blindness ; Blood vessels ; Brain cancer ; Classification ; Computer aided medical diagnosis ; Computer architecture ; Datasets ; Deep learning ; Diabetic retinopathy ; Diagnosis ; Diagnostic imaging ; Eye diseases ; Glaucoma ; Health services ; Infants ; Machine learning ; Medical personnel ; Methods ; Model accuracy ; Neural networks ; Newborn babies ; Premature birth ; Retinal detachment ; Retinopathy of prematurity ; Sensitivity ; Telemedicine ; Visual acuity ; Visual impairment</subject><ispartof>Electronics (Basel), 2020-09, Vol.9 (9), p.1444</ispartof><rights>COPYRIGHT 2020 MDPI AG</rights><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><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c413t-29557dc4f37e2f7fe8ad97943813e45ab4887e8ee62952f1155b6b13325aab583</citedby><cites>FETCH-LOGICAL-c413t-29557dc4f37e2f7fe8ad97943813e45ab4887e8ee62952f1155b6b13325aab583</cites><orcidid>0000-0003-0429-2007 ; 0000-0001-6814-6530 ; 0000-0002-1732-981X</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Huang, Yo-Ping</creatorcontrib><creatorcontrib>Vadloori, Spandana</creatorcontrib><creatorcontrib>Chu, Hung-Chi</creatorcontrib><creatorcontrib>Kang, Eugene Yu-Chuan</creatorcontrib><creatorcontrib>Wu, Wei-Chi</creatorcontrib><creatorcontrib>Kusaka, Shunji</creatorcontrib><creatorcontrib>Fukushima, Yoko</creatorcontrib><title>Deep Learning Models for Automated Diagnosis of Retinopathy of Prematurity in Preterm Infants</title><title>Electronics (Basel)</title><description>Retinopathy of prematurity (ROP) is a disease that can cause blindness in premature infants. It is characterized by immature vascular growth of the retinal blood vessels. However, early detection and treatment of ROP can significantly improve the visual acuity of high-risk patients. Thus, early diagnosis of ROP is crucial in preventing visual impairment. However, several patients refrain from treatment owing to the lack of medical expertise in diagnosing the disease; this is especially problematic considering that the number of ROP cases is on the rise. To this end, we applied transfer learning to five deep neural network architectures for identifying ROP in preterm infants. Our results showed that the VGG19 model outperformed the other models in determining whether a preterm infant has ROP, with 96% accuracy, 96.6% sensitivity, and 95.2% specificity. We also classified the severity of the disease; the VGG19 model showed 98.82% accuracy in predicting the severity of the disease with a sensitivity and specificity of 100% and 98.41%, respectively. We performed 5-fold cross-validation on the datasets to validate the reliability of the VGG19 model and found that the VGG19 model exhibited high accuracy in predicting ROP. These findings could help promote the development of computer-aided diagnosis.</description><subject>Applied research</subject><subject>Artificial intelligence</subject><subject>Artificial neural networks</subject><subject>Automation</subject><subject>Blindness</subject><subject>Blood vessels</subject><subject>Brain cancer</subject><subject>Classification</subject><subject>Computer aided medical diagnosis</subject><subject>Computer architecture</subject><subject>Datasets</subject><subject>Deep learning</subject><subject>Diabetic retinopathy</subject><subject>Diagnosis</subject><subject>Diagnostic imaging</subject><subject>Eye diseases</subject><subject>Glaucoma</subject><subject>Health services</subject><subject>Infants</subject><subject>Machine learning</subject><subject>Medical personnel</subject><subject>Methods</subject><subject>Model accuracy</subject><subject>Neural networks</subject><subject>Newborn babies</subject><subject>Premature birth</subject><subject>Retinal detachment</subject><subject>Retinopathy of prematurity</subject><subject>Sensitivity</subject><subject>Telemedicine</subject><subject>Visual acuity</subject><subject>Visual impairment</subject><issn>2079-9292</issn><issn>2079-9292</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>eNplkF1LwzAYhYsoOHR_wKuA19V8ts3l2PwYTBTRSwlp-2ZmtElN0ov9ezsmKPjenPfAwzlwsuyK4BvGJL6FDpoUvLNNlFgSzvlJNqO4lLmkkp7--c-zeYw7PJ0krGJ4ln2sAAa0AR2cdVv05FvoIjI-oMWYfK8TtGhl9db5aCPyBr1Css4POn3uD_YlwASNwaY9su5gE4QerZ3RLsXL7MzoLsL8Ry-y9_u7t-Vjvnl-WC8Xm7zhhKWcSiHKtuGGlUBNaaDSrSwlZxVhwIWueVWVUAEUE0kNIULURU0Yo0LrWlTsIrs-5g7Bf40Qk9r5MbipUlHOCcFEFvSX2uoOlHXGp6Cb3sZGLQrOMGeiKCaKHqkm-BgDGDUE2-uwVwSrw97q_97sG7kydTU</recordid><startdate>20200901</startdate><enddate>20200901</enddate><creator>Huang, Yo-Ping</creator><creator>Vadloori, Spandana</creator><creator>Chu, Hung-Chi</creator><creator>Kang, Eugene Yu-Chuan</creator><creator>Wu, Wei-Chi</creator><creator>Kusaka, Shunji</creator><creator>Fukushima, Yoko</creator><general>MDPI AG</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>8FD</scope><scope>8FE</scope><scope>8FG</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>ARAPS</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>COVID</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L7M</scope><scope>P5Z</scope><scope>P62</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><orcidid>https://orcid.org/0000-0003-0429-2007</orcidid><orcidid>https://orcid.org/0000-0001-6814-6530</orcidid><orcidid>https://orcid.org/0000-0002-1732-981X</orcidid></search><sort><creationdate>20200901</creationdate><title>Deep Learning Models for Automated Diagnosis of Retinopathy of Prematurity in Preterm Infants</title><author>Huang, Yo-Ping ; Vadloori, Spandana ; Chu, Hung-Chi ; Kang, Eugene Yu-Chuan ; Wu, Wei-Chi ; Kusaka, Shunji ; Fukushima, Yoko</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c413t-29557dc4f37e2f7fe8ad97943813e45ab4887e8ee62952f1155b6b13325aab583</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Applied research</topic><topic>Artificial intelligence</topic><topic>Artificial neural networks</topic><topic>Automation</topic><topic>Blindness</topic><topic>Blood vessels</topic><topic>Brain cancer</topic><topic>Classification</topic><topic>Computer aided medical diagnosis</topic><topic>Computer architecture</topic><topic>Datasets</topic><topic>Deep learning</topic><topic>Diabetic retinopathy</topic><topic>Diagnosis</topic><topic>Diagnostic imaging</topic><topic>Eye diseases</topic><topic>Glaucoma</topic><topic>Health services</topic><topic>Infants</topic><topic>Machine learning</topic><topic>Medical personnel</topic><topic>Methods</topic><topic>Model accuracy</topic><topic>Neural networks</topic><topic>Newborn babies</topic><topic>Premature birth</topic><topic>Retinal detachment</topic><topic>Retinopathy of prematurity</topic><topic>Sensitivity</topic><topic>Telemedicine</topic><topic>Visual acuity</topic><topic>Visual impairment</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Huang, Yo-Ping</creatorcontrib><creatorcontrib>Vadloori, Spandana</creatorcontrib><creatorcontrib>Chu, Hung-Chi</creatorcontrib><creatorcontrib>Kang, Eugene Yu-Chuan</creatorcontrib><creatorcontrib>Wu, Wei-Chi</creatorcontrib><creatorcontrib>Kusaka, Shunji</creatorcontrib><creatorcontrib>Fukushima, Yoko</creatorcontrib><collection>CrossRef</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>Advanced Technologies & Aerospace Collection</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection (ProQuest)</collection><collection>ProQuest One Community College</collection><collection>Coronavirus Research Database</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Advanced Technologies & Aerospace Database</collection><collection>ProQuest Advanced Technologies & Aerospace Collection</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><jtitle>Electronics (Basel)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Huang, Yo-Ping</au><au>Vadloori, Spandana</au><au>Chu, Hung-Chi</au><au>Kang, Eugene Yu-Chuan</au><au>Wu, Wei-Chi</au><au>Kusaka, Shunji</au><au>Fukushima, Yoko</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Deep Learning Models for Automated Diagnosis of Retinopathy of Prematurity in Preterm Infants</atitle><jtitle>Electronics (Basel)</jtitle><date>2020-09-01</date><risdate>2020</risdate><volume>9</volume><issue>9</issue><spage>1444</spage><pages>1444-</pages><issn>2079-9292</issn><eissn>2079-9292</eissn><abstract>Retinopathy of prematurity (ROP) is a disease that can cause blindness in premature infants. It is characterized by immature vascular growth of the retinal blood vessels. However, early detection and treatment of ROP can significantly improve the visual acuity of high-risk patients. Thus, early diagnosis of ROP is crucial in preventing visual impairment. However, several patients refrain from treatment owing to the lack of medical expertise in diagnosing the disease; this is especially problematic considering that the number of ROP cases is on the rise. To this end, we applied transfer learning to five deep neural network architectures for identifying ROP in preterm infants. Our results showed that the VGG19 model outperformed the other models in determining whether a preterm infant has ROP, with 96% accuracy, 96.6% sensitivity, and 95.2% specificity. We also classified the severity of the disease; the VGG19 model showed 98.82% accuracy in predicting the severity of the disease with a sensitivity and specificity of 100% and 98.41%, respectively. We performed 5-fold cross-validation on the datasets to validate the reliability of the VGG19 model and found that the VGG19 model exhibited high accuracy in predicting ROP. These findings could help promote the development of computer-aided diagnosis.</abstract><cop>Basel</cop><pub>MDPI AG</pub><doi>10.3390/electronics9091444</doi><orcidid>https://orcid.org/0000-0003-0429-2007</orcidid><orcidid>https://orcid.org/0000-0001-6814-6530</orcidid><orcidid>https://orcid.org/0000-0002-1732-981X</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 2079-9292 |
ispartof | Electronics (Basel), 2020-09, Vol.9 (9), p.1444 |
issn | 2079-9292 2079-9292 |
language | eng |
recordid | cdi_proquest_journals_2441101962 |
source | MDPI - Multidisciplinary Digital Publishing Institute; EZB-FREE-00999 freely available EZB journals |
subjects | Applied research Artificial intelligence Artificial neural networks Automation Blindness Blood vessels Brain cancer Classification Computer aided medical diagnosis Computer architecture Datasets Deep learning Diabetic retinopathy Diagnosis Diagnostic imaging Eye diseases Glaucoma Health services Infants Machine learning Medical personnel Methods Model accuracy Neural networks Newborn babies Premature birth Retinal detachment Retinopathy of prematurity Sensitivity Telemedicine Visual acuity Visual impairment |
title | Deep Learning Models for Automated Diagnosis of Retinopathy of Prematurity in Preterm Infants |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-06T12%3A34%3A48IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-gale_proqu&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Deep%20Learning%20Models%20for%20Automated%20Diagnosis%20of%20Retinopathy%20of%20Prematurity%20in%20Preterm%20Infants&rft.jtitle=Electronics%20(Basel)&rft.au=Huang,%20Yo-Ping&rft.date=2020-09-01&rft.volume=9&rft.issue=9&rft.spage=1444&rft.pages=1444-&rft.issn=2079-9292&rft.eissn=2079-9292&rft_id=info:doi/10.3390/electronics9091444&rft_dat=%3Cgale_proqu%3EA643043566%3C/gale_proqu%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2441101962&rft_id=info:pmid/&rft_galeid=A643043566&rfr_iscdi=true |