Automated detection of diabetic retinopathy lesions on ultrawidefield pseudocolour images
Purpose We examined the sensitivity and specificity of an automated algorithm for detecting referral‐warranted diabetic retinopathy (DR) on Optos ultrawidefield (UWF) pseudocolour images. Methods Patients with diabetes were recruited for UWF imaging. A total of 383 subjects (754 eyes) were enrolled....
Gespeichert in:
| Veröffentlicht in: | Acta ophthalmologica (Oxford, England) England), 2018-03, Vol.96 (2), p.e168-e173 |
|---|---|
| Hauptverfasser: | , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | e173 |
|---|---|
| container_issue | 2 |
| container_start_page | e168 |
| container_title | Acta ophthalmologica (Oxford, England) |
| container_volume | 96 |
| creator | Wang, Kang Jayadev, Chaitra Nittala, Muneeswar G. Velaga, Swetha B. Ramachandra, Chaithanya A. Bhaskaranand, Malavika Bhat, Sandeep Solanki, Kaushal Sadda, SriniVas R. |
| description | Purpose
We examined the sensitivity and specificity of an automated algorithm for detecting referral‐warranted diabetic retinopathy (DR) on Optos ultrawidefield (UWF) pseudocolour images.
Methods
Patients with diabetes were recruited for UWF imaging. A total of 383 subjects (754 eyes) were enrolled. Nonproliferative DR graded to be moderate or higher on the 5‐level International Clinical Diabetic Retinopathy (ICDR) severity scale was considered as grounds for referral. The software automatically detected DR lesions using the previously trained classifiers and classified each image in the test set as referral‐warranted or not warranted. Sensitivity, specificity and the area under the receiver operating curve (AUROC) of the algorithm were computed.
Results
The automated algorithm achieved a 91.7%/90.3% sensitivity (95% CI 90.1–93.9/80.4–89.4) with a 50.0%/53.6% specificity (95% CI 31.7–72.8/36.5–71.4) for detecting referral‐warranted retinopathy at the patient/eye levels, respectively; the AUROC was 0.873/0.851 (95% CI 0.819–0.922/0.804–0.894).
Conclusion
Diabetic retinopathy (DR) lesions were detected from Optos pseudocolour UWF images using an automated algorithm. Images were classified as referral‐warranted DR with a high degree of sensitivity and moderate specificity. Automated analysis of UWF images could be of value in DR screening programmes and could allow for more complete and accurate disease staging. |
| doi_str_mv | 10.1111/aos.13528 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_1940598661</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2001909132</sourcerecordid><originalsourceid>FETCH-LOGICAL-c3888-b2563373376cf2c427c4079a82fee1cd9c4df45b658921f4545d3c2b023143253</originalsourceid><addsrcrecordid>eNp1kF1LwzAYhYMobk4v_ANS8EYvuuWjSZvLMfwCYRcq6FVIk7fa0TazaRn790Y7dyH4Et4cyMPh5CB0TvCUhJlp56eEcZodoDFJOY9ZKrLDveavI3Ti_QpjQYRIjtGIZpIKIuUYvc37ztW6AxtZ6MB0pWsiV0S21Dl0pYnasBu31t3HNqrAh2cfBaSvulZvSgtFCZWN1h5664yrXN9GZa3fwZ-io0JXHs529wS93N48L-7jx-Xdw2L-GBuWZVmcUy4YS8MRpqAmoalJcCp1RgsAYqw0iS0SngseMpOgEm6ZoTmmjCSMcjZBV4PvunWfPfhO1aU3UFW6Add7RWSCucyEIAG9_IOuQt4mpFMUYyKxJIwG6nqgTOu8b6FQ6zZ8qd0qgtV33yr0rX76DuzFzrHPa7B78rfgAMwGYFNWsP3fSc2XT4PlF34iiZs</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2001909132</pqid></control><display><type>article</type><title>Automated detection of diabetic retinopathy lesions on ultrawidefield pseudocolour images</title><source>MEDLINE</source><source>Wiley Free Content</source><source>Wiley Online Library All Journals</source><creator>Wang, Kang ; Jayadev, Chaitra ; Nittala, Muneeswar G. ; Velaga, Swetha B. ; Ramachandra, Chaithanya A. ; Bhaskaranand, Malavika ; Bhat, Sandeep ; Solanki, Kaushal ; Sadda, SriniVas R.</creator><creatorcontrib>Wang, Kang ; Jayadev, Chaitra ; Nittala, Muneeswar G. ; Velaga, Swetha B. ; Ramachandra, Chaithanya A. ; Bhaskaranand, Malavika ; Bhat, Sandeep ; Solanki, Kaushal ; Sadda, SriniVas R.</creatorcontrib><description>Purpose
We examined the sensitivity and specificity of an automated algorithm for detecting referral‐warranted diabetic retinopathy (DR) on Optos ultrawidefield (UWF) pseudocolour images.
Methods
Patients with diabetes were recruited for UWF imaging. A total of 383 subjects (754 eyes) were enrolled. Nonproliferative DR graded to be moderate or higher on the 5‐level International Clinical Diabetic Retinopathy (ICDR) severity scale was considered as grounds for referral. The software automatically detected DR lesions using the previously trained classifiers and classified each image in the test set as referral‐warranted or not warranted. Sensitivity, specificity and the area under the receiver operating curve (AUROC) of the algorithm were computed.
Results
The automated algorithm achieved a 91.7%/90.3% sensitivity (95% CI 90.1–93.9/80.4–89.4) with a 50.0%/53.6% specificity (95% CI 31.7–72.8/36.5–71.4) for detecting referral‐warranted retinopathy at the patient/eye levels, respectively; the AUROC was 0.873/0.851 (95% CI 0.819–0.922/0.804–0.894).
Conclusion
Diabetic retinopathy (DR) lesions were detected from Optos pseudocolour UWF images using an automated algorithm. Images were classified as referral‐warranted DR with a high degree of sensitivity and moderate specificity. Automated analysis of UWF images could be of value in DR screening programmes and could allow for more complete and accurate disease staging.</description><identifier>ISSN: 1755-375X</identifier><identifier>EISSN: 1755-3768</identifier><identifier>DOI: 10.1111/aos.13528</identifier><identifier>PMID: 28926199</identifier><language>eng</language><publisher>England: Wiley Subscription Services, Inc</publisher><subject>Adult ; Aged ; Algorithms ; Area Under Curve ; automated ; Automation ; Diabetes ; Diabetes mellitus ; Diabetic retinopathy ; Diabetic Retinopathy - diagnosis ; Diagnostic Techniques, Ophthalmological ; Female ; Humans ; Image detection ; Image Processing, Computer-Assisted - methods ; Lesions ; Male ; Middle Aged ; Photography - methods ; pseudocolour ; Retina ; Retinopathy ; ROC Curve ; Sensitivity ; Sensitivity and Specificity ; Software ; ultrawidefield</subject><ispartof>Acta ophthalmologica (Oxford, England), 2018-03, Vol.96 (2), p.e168-e173</ispartof><rights>2017 Acta Ophthalmologica Scandinavica Foundation. Published by John Wiley & Sons Ltd</rights><rights>2017 Acta Ophthalmologica Scandinavica Foundation. Published by John Wiley & Sons Ltd.</rights><rights>Copyright © 2018 Acta Ophthalmologica Scandinavica Foundation</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c3888-b2563373376cf2c427c4079a82fee1cd9c4df45b658921f4545d3c2b023143253</citedby><cites>FETCH-LOGICAL-c3888-b2563373376cf2c427c4079a82fee1cd9c4df45b658921f4545d3c2b023143253</cites><orcidid>0000-0002-3802-6594</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://onlinelibrary.wiley.com/doi/pdf/10.1111%2Faos.13528$$EPDF$$P50$$Gwiley$$H</linktopdf><linktohtml>$$Uhttps://onlinelibrary.wiley.com/doi/full/10.1111%2Faos.13528$$EHTML$$P50$$Gwiley$$H</linktohtml><link.rule.ids>314,780,784,1416,1432,27923,27924,45573,45574,46408,46832</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/28926199$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Wang, Kang</creatorcontrib><creatorcontrib>Jayadev, Chaitra</creatorcontrib><creatorcontrib>Nittala, Muneeswar G.</creatorcontrib><creatorcontrib>Velaga, Swetha B.</creatorcontrib><creatorcontrib>Ramachandra, Chaithanya A.</creatorcontrib><creatorcontrib>Bhaskaranand, Malavika</creatorcontrib><creatorcontrib>Bhat, Sandeep</creatorcontrib><creatorcontrib>Solanki, Kaushal</creatorcontrib><creatorcontrib>Sadda, SriniVas R.</creatorcontrib><title>Automated detection of diabetic retinopathy lesions on ultrawidefield pseudocolour images</title><title>Acta ophthalmologica (Oxford, England)</title><addtitle>Acta Ophthalmol</addtitle><description>Purpose
We examined the sensitivity and specificity of an automated algorithm for detecting referral‐warranted diabetic retinopathy (DR) on Optos ultrawidefield (UWF) pseudocolour images.
Methods
Patients with diabetes were recruited for UWF imaging. A total of 383 subjects (754 eyes) were enrolled. Nonproliferative DR graded to be moderate or higher on the 5‐level International Clinical Diabetic Retinopathy (ICDR) severity scale was considered as grounds for referral. The software automatically detected DR lesions using the previously trained classifiers and classified each image in the test set as referral‐warranted or not warranted. Sensitivity, specificity and the area under the receiver operating curve (AUROC) of the algorithm were computed.
Results
The automated algorithm achieved a 91.7%/90.3% sensitivity (95% CI 90.1–93.9/80.4–89.4) with a 50.0%/53.6% specificity (95% CI 31.7–72.8/36.5–71.4) for detecting referral‐warranted retinopathy at the patient/eye levels, respectively; the AUROC was 0.873/0.851 (95% CI 0.819–0.922/0.804–0.894).
Conclusion
Diabetic retinopathy (DR) lesions were detected from Optos pseudocolour UWF images using an automated algorithm. Images were classified as referral‐warranted DR with a high degree of sensitivity and moderate specificity. Automated analysis of UWF images could be of value in DR screening programmes and could allow for more complete and accurate disease staging.</description><subject>Adult</subject><subject>Aged</subject><subject>Algorithms</subject><subject>Area Under Curve</subject><subject>automated</subject><subject>Automation</subject><subject>Diabetes</subject><subject>Diabetes mellitus</subject><subject>Diabetic retinopathy</subject><subject>Diabetic Retinopathy - diagnosis</subject><subject>Diagnostic Techniques, Ophthalmological</subject><subject>Female</subject><subject>Humans</subject><subject>Image detection</subject><subject>Image Processing, Computer-Assisted - methods</subject><subject>Lesions</subject><subject>Male</subject><subject>Middle Aged</subject><subject>Photography - methods</subject><subject>pseudocolour</subject><subject>Retina</subject><subject>Retinopathy</subject><subject>ROC Curve</subject><subject>Sensitivity</subject><subject>Sensitivity and Specificity</subject><subject>Software</subject><subject>ultrawidefield</subject><issn>1755-375X</issn><issn>1755-3768</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNp1kF1LwzAYhYMobk4v_ANS8EYvuuWjSZvLMfwCYRcq6FVIk7fa0TazaRn790Y7dyH4Et4cyMPh5CB0TvCUhJlp56eEcZodoDFJOY9ZKrLDveavI3Ti_QpjQYRIjtGIZpIKIuUYvc37ztW6AxtZ6MB0pWsiV0S21Dl0pYnasBu31t3HNqrAh2cfBaSvulZvSgtFCZWN1h5664yrXN9GZa3fwZ-io0JXHs529wS93N48L-7jx-Xdw2L-GBuWZVmcUy4YS8MRpqAmoalJcCp1RgsAYqw0iS0SngseMpOgEm6ZoTmmjCSMcjZBV4PvunWfPfhO1aU3UFW6Add7RWSCucyEIAG9_IOuQt4mpFMUYyKxJIwG6nqgTOu8b6FQ6zZ8qd0qgtV33yr0rX76DuzFzrHPa7B78rfgAMwGYFNWsP3fSc2XT4PlF34iiZs</recordid><startdate>201803</startdate><enddate>201803</enddate><creator>Wang, Kang</creator><creator>Jayadev, Chaitra</creator><creator>Nittala, Muneeswar G.</creator><creator>Velaga, Swetha B.</creator><creator>Ramachandra, Chaithanya A.</creator><creator>Bhaskaranand, Malavika</creator><creator>Bhat, Sandeep</creator><creator>Solanki, Kaushal</creator><creator>Sadda, SriniVas R.</creator><general>Wiley Subscription Services, Inc</general><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7TK</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0002-3802-6594</orcidid></search><sort><creationdate>201803</creationdate><title>Automated detection of diabetic retinopathy lesions on ultrawidefield pseudocolour images</title><author>Wang, Kang ; Jayadev, Chaitra ; Nittala, Muneeswar G. ; Velaga, Swetha B. ; Ramachandra, Chaithanya A. ; Bhaskaranand, Malavika ; Bhat, Sandeep ; Solanki, Kaushal ; Sadda, SriniVas R.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c3888-b2563373376cf2c427c4079a82fee1cd9c4df45b658921f4545d3c2b023143253</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Adult</topic><topic>Aged</topic><topic>Algorithms</topic><topic>Area Under Curve</topic><topic>automated</topic><topic>Automation</topic><topic>Diabetes</topic><topic>Diabetes mellitus</topic><topic>Diabetic retinopathy</topic><topic>Diabetic Retinopathy - diagnosis</topic><topic>Diagnostic Techniques, Ophthalmological</topic><topic>Female</topic><topic>Humans</topic><topic>Image detection</topic><topic>Image Processing, Computer-Assisted - methods</topic><topic>Lesions</topic><topic>Male</topic><topic>Middle Aged</topic><topic>Photography - methods</topic><topic>pseudocolour</topic><topic>Retina</topic><topic>Retinopathy</topic><topic>ROC Curve</topic><topic>Sensitivity</topic><topic>Sensitivity and Specificity</topic><topic>Software</topic><topic>ultrawidefield</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Wang, Kang</creatorcontrib><creatorcontrib>Jayadev, Chaitra</creatorcontrib><creatorcontrib>Nittala, Muneeswar G.</creatorcontrib><creatorcontrib>Velaga, Swetha B.</creatorcontrib><creatorcontrib>Ramachandra, Chaithanya A.</creatorcontrib><creatorcontrib>Bhaskaranand, Malavika</creatorcontrib><creatorcontrib>Bhat, Sandeep</creatorcontrib><creatorcontrib>Solanki, Kaushal</creatorcontrib><creatorcontrib>Sadda, SriniVas R.</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Neurosciences Abstracts</collection><collection>MEDLINE - Academic</collection><jtitle>Acta ophthalmologica (Oxford, England)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Wang, Kang</au><au>Jayadev, Chaitra</au><au>Nittala, Muneeswar G.</au><au>Velaga, Swetha B.</au><au>Ramachandra, Chaithanya A.</au><au>Bhaskaranand, Malavika</au><au>Bhat, Sandeep</au><au>Solanki, Kaushal</au><au>Sadda, SriniVas R.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Automated detection of diabetic retinopathy lesions on ultrawidefield pseudocolour images</atitle><jtitle>Acta ophthalmologica (Oxford, England)</jtitle><addtitle>Acta Ophthalmol</addtitle><date>2018-03</date><risdate>2018</risdate><volume>96</volume><issue>2</issue><spage>e168</spage><epage>e173</epage><pages>e168-e173</pages><issn>1755-375X</issn><eissn>1755-3768</eissn><abstract>Purpose
We examined the sensitivity and specificity of an automated algorithm for detecting referral‐warranted diabetic retinopathy (DR) on Optos ultrawidefield (UWF) pseudocolour images.
Methods
Patients with diabetes were recruited for UWF imaging. A total of 383 subjects (754 eyes) were enrolled. Nonproliferative DR graded to be moderate or higher on the 5‐level International Clinical Diabetic Retinopathy (ICDR) severity scale was considered as grounds for referral. The software automatically detected DR lesions using the previously trained classifiers and classified each image in the test set as referral‐warranted or not warranted. Sensitivity, specificity and the area under the receiver operating curve (AUROC) of the algorithm were computed.
Results
The automated algorithm achieved a 91.7%/90.3% sensitivity (95% CI 90.1–93.9/80.4–89.4) with a 50.0%/53.6% specificity (95% CI 31.7–72.8/36.5–71.4) for detecting referral‐warranted retinopathy at the patient/eye levels, respectively; the AUROC was 0.873/0.851 (95% CI 0.819–0.922/0.804–0.894).
Conclusion
Diabetic retinopathy (DR) lesions were detected from Optos pseudocolour UWF images using an automated algorithm. Images were classified as referral‐warranted DR with a high degree of sensitivity and moderate specificity. Automated analysis of UWF images could be of value in DR screening programmes and could allow for more complete and accurate disease staging.</abstract><cop>England</cop><pub>Wiley Subscription Services, Inc</pub><pmid>28926199</pmid><doi>10.1111/aos.13528</doi><tpages>6</tpages><orcidid>https://orcid.org/0000-0002-3802-6594</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1755-375X |
| ispartof | Acta ophthalmologica (Oxford, England), 2018-03, Vol.96 (2), p.e168-e173 |
| issn | 1755-375X 1755-3768 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_1940598661 |
| source | MEDLINE; Wiley Free Content; Wiley Online Library All Journals |
| subjects | Adult Aged Algorithms Area Under Curve automated Automation Diabetes Diabetes mellitus Diabetic retinopathy Diabetic Retinopathy - diagnosis Diagnostic Techniques, Ophthalmological Female Humans Image detection Image Processing, Computer-Assisted - methods Lesions Male Middle Aged Photography - methods pseudocolour Retina Retinopathy ROC Curve Sensitivity Sensitivity and Specificity Software ultrawidefield |
| title | Automated detection of diabetic retinopathy lesions on ultrawidefield pseudocolour images |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-11T12%3A21%3A28IST&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=Automated%20detection%20of%20diabetic%20retinopathy%20lesions%20on%20ultrawidefield%20pseudocolour%20images&rft.jtitle=Acta%20ophthalmologica%20(Oxford,%20England)&rft.au=Wang,%20Kang&rft.date=2018-03&rft.volume=96&rft.issue=2&rft.spage=e168&rft.epage=e173&rft.pages=e168-e173&rft.issn=1755-375X&rft.eissn=1755-3768&rft_id=info:doi/10.1111/aos.13528&rft_dat=%3Cproquest_cross%3E2001909132%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=2001909132&rft_id=info:pmid/28926199&rfr_iscdi=true |