Loading…
Detection of New Vessels on the Optic Disc Using Retinal Photographs
Proliferative diabetic retinopathyis a rare condition likely to lead to severe visual impairment. It is characterized by the development of abnormal new retinal vessels. We describe a method for automatically detecting new vessels on the optic disc using retinal photography. Vessel-like candidate se...
Saved in:
Published in: | IEEE transactions on medical imaging 2011-04, Vol.30 (4), p.972-979 |
---|---|
Main Authors: | , , , , , |
Format: | Article |
Language: | English |
Subjects: | |
Citations: | Items that this one cites Items that cite this one |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | cdi_FETCH-LOGICAL-c318t-fcff3806348602b0835e015a525168d4ab5bd10c413c5a46f1dbb9fdf70191ed3 |
---|---|
cites | cdi_FETCH-LOGICAL-c318t-fcff3806348602b0835e015a525168d4ab5bd10c413c5a46f1dbb9fdf70191ed3 |
container_end_page | 979 |
container_issue | 4 |
container_start_page | 972 |
container_title | IEEE transactions on medical imaging |
container_volume | 30 |
creator | Goatman, K A Fleming, A D Philip, S Williams, G J Olson, J A Sharp, P F |
description | Proliferative diabetic retinopathyis a rare condition likely to lead to severe visual impairment. It is characterized by the development of abnormal new retinal vessels. We describe a method for automatically detecting new vessels on the optic disc using retinal photography. Vessel-like candidate segments are first detected using a method based on watershed lines and ridge strength measurement. Fifteen feature parameters, associated with shape, position, orientation, brightness, contrast and line density are calculated for each candidate segment. Based on these features, each segment is categorized as normal or abnormal using a support vector machine (SVM) classifier. The system was trained and tested by cross-validation using 38 images with new vessels and 71 normal images from two diabetic retinal screening centers and one hospital eye clinic. The discrimination performance of the fifteen features was tested against a clinical reference standard. Fourteen features were found to be effective and used in the final test. The area under the receiver operator characteristic curve was 0.911 for detecting images with new vessels on the disc. This accuracy may be sufficient for it to play a useful clinical role in an automated retinopathy analysis system. |
doi_str_mv | 10.1109/TMI.2010.2099236 |
format | article |
fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmed_primary_21156389</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>5667059</ieee_id><sourcerecordid>861204155</sourcerecordid><originalsourceid>FETCH-LOGICAL-c318t-fcff3806348602b0835e015a525168d4ab5bd10c413c5a46f1dbb9fdf70191ed3</originalsourceid><addsrcrecordid>eNo9kE1Lw0AQhhdRbK3eBUH25il1Zje73RzF-lGoVqQVbyEfs20kTWJ2i_jvTWntaZiZ5x2Gh7FLhCEiRLfzl8lQQNcJiCIh9RHro1ImECr8PGZ9ECMTAGjRY2fOfQFgqCA6ZT2BqLQ0UZ-Nx-Qp80Vd8dryV_rhH-QclY53E78iPmt8kfFx4TK-cEW15O_kiyop-duq9vWyTZqVO2cnNikdXezrgC0eH-b3z8F09jS5v5sGmUTjA5tZKw1oGRoNIgUjFQGqRAmF2uRhkqo0R8hClJlKQm0xT9PI5nYEGCHlcsBudnebtv7ekPPxuvuLyjKpqN642GgUEHYGOhJ2ZNbWzrVk46Yt1kn7GyPEW3Vxpy7eqov36rrI9f74Jl1Tfgj8u-qAqx1QENFhrbQegYrkHynqcRc</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>861204155</pqid></control><display><type>article</type><title>Detection of New Vessels on the Optic Disc Using Retinal Photographs</title><source>IEEE Electronic Library (IEL) Journals</source><creator>Goatman, K A ; Fleming, A D ; Philip, S ; Williams, G J ; Olson, J A ; Sharp, P F</creator><creatorcontrib>Goatman, K A ; Fleming, A D ; Philip, S ; Williams, G J ; Olson, J A ; Sharp, P F</creatorcontrib><description>Proliferative diabetic retinopathyis a rare condition likely to lead to severe visual impairment. It is characterized by the development of abnormal new retinal vessels. We describe a method for automatically detecting new vessels on the optic disc using retinal photography. Vessel-like candidate segments are first detected using a method based on watershed lines and ridge strength measurement. Fifteen feature parameters, associated with shape, position, orientation, brightness, contrast and line density are calculated for each candidate segment. Based on these features, each segment is categorized as normal or abnormal using a support vector machine (SVM) classifier. The system was trained and tested by cross-validation using 38 images with new vessels and 71 normal images from two diabetic retinal screening centers and one hospital eye clinic. The discrimination performance of the fifteen features was tested against a clinical reference standard. Fourteen features were found to be effective and used in the final test. The area under the receiver operator characteristic curve was 0.911 for detecting images with new vessels on the disc. This accuracy may be sufficient for it to play a useful clinical role in an automated retinopathy analysis system.</description><identifier>ISSN: 0278-0062</identifier><identifier>EISSN: 1558-254X</identifier><identifier>DOI: 10.1109/TMI.2010.2099236</identifier><identifier>PMID: 21156389</identifier><identifier>CODEN: ITMID4</identifier><language>eng</language><publisher>United States: IEEE</publisher><subject>Diabetes ; Diabetic Retinopathy - pathology ; Diagnostic Techniques, Ophthalmological ; Humans ; Image Processing, Computer-Assisted - methods ; Image segmentation ; Neovascularization, Pathologic - pathology ; Optic Disk - anatomy & histology ; Optic Disk - blood supply ; Optical imaging ; Photography - methods ; Pixel ; Retina ; Retinal Vessels - anatomy & histology ; Retinal Vessels - pathology ; Retinopathy ; ROC Curve ; Support vector machines</subject><ispartof>IEEE transactions on medical imaging, 2011-04, Vol.30 (4), p.972-979</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c318t-fcff3806348602b0835e015a525168d4ab5bd10c413c5a46f1dbb9fdf70191ed3</citedby><cites>FETCH-LOGICAL-c318t-fcff3806348602b0835e015a525168d4ab5bd10c413c5a46f1dbb9fdf70191ed3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/5667059$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,27923,27924,54795</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/21156389$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Goatman, K A</creatorcontrib><creatorcontrib>Fleming, A D</creatorcontrib><creatorcontrib>Philip, S</creatorcontrib><creatorcontrib>Williams, G J</creatorcontrib><creatorcontrib>Olson, J A</creatorcontrib><creatorcontrib>Sharp, P F</creatorcontrib><title>Detection of New Vessels on the Optic Disc Using Retinal Photographs</title><title>IEEE transactions on medical imaging</title><addtitle>TMI</addtitle><addtitle>IEEE Trans Med Imaging</addtitle><description>Proliferative diabetic retinopathyis a rare condition likely to lead to severe visual impairment. It is characterized by the development of abnormal new retinal vessels. We describe a method for automatically detecting new vessels on the optic disc using retinal photography. Vessel-like candidate segments are first detected using a method based on watershed lines and ridge strength measurement. Fifteen feature parameters, associated with shape, position, orientation, brightness, contrast and line density are calculated for each candidate segment. Based on these features, each segment is categorized as normal or abnormal using a support vector machine (SVM) classifier. The system was trained and tested by cross-validation using 38 images with new vessels and 71 normal images from two diabetic retinal screening centers and one hospital eye clinic. The discrimination performance of the fifteen features was tested against a clinical reference standard. Fourteen features were found to be effective and used in the final test. The area under the receiver operator characteristic curve was 0.911 for detecting images with new vessels on the disc. This accuracy may be sufficient for it to play a useful clinical role in an automated retinopathy analysis system.</description><subject>Diabetes</subject><subject>Diabetic Retinopathy - pathology</subject><subject>Diagnostic Techniques, Ophthalmological</subject><subject>Humans</subject><subject>Image Processing, Computer-Assisted - methods</subject><subject>Image segmentation</subject><subject>Neovascularization, Pathologic - pathology</subject><subject>Optic Disk - anatomy & histology</subject><subject>Optic Disk - blood supply</subject><subject>Optical imaging</subject><subject>Photography - methods</subject><subject>Pixel</subject><subject>Retina</subject><subject>Retinal Vessels - anatomy & histology</subject><subject>Retinal Vessels - pathology</subject><subject>Retinopathy</subject><subject>ROC Curve</subject><subject>Support vector machines</subject><issn>0278-0062</issn><issn>1558-254X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2011</creationdate><recordtype>article</recordtype><recordid>eNo9kE1Lw0AQhhdRbK3eBUH25il1Zje73RzF-lGoVqQVbyEfs20kTWJ2i_jvTWntaZiZ5x2Gh7FLhCEiRLfzl8lQQNcJiCIh9RHro1ImECr8PGZ9ECMTAGjRY2fOfQFgqCA6ZT2BqLQ0UZ-Nx-Qp80Vd8dryV_rhH-QclY53E78iPmt8kfFx4TK-cEW15O_kiyop-duq9vWyTZqVO2cnNikdXezrgC0eH-b3z8F09jS5v5sGmUTjA5tZKw1oGRoNIgUjFQGqRAmF2uRhkqo0R8hClJlKQm0xT9PI5nYEGCHlcsBudnebtv7ekPPxuvuLyjKpqN642GgUEHYGOhJ2ZNbWzrVk46Yt1kn7GyPEW3Vxpy7eqov36rrI9f74Jl1Tfgj8u-qAqx1QENFhrbQegYrkHynqcRc</recordid><startdate>201104</startdate><enddate>201104</enddate><creator>Goatman, K A</creator><creator>Fleming, A D</creator><creator>Philip, S</creator><creator>Williams, G J</creator><creator>Olson, J A</creator><creator>Sharp, P F</creator><general>IEEE</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><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>7X8</scope></search><sort><creationdate>201104</creationdate><title>Detection of New Vessels on the Optic Disc Using Retinal Photographs</title><author>Goatman, K A ; Fleming, A D ; Philip, S ; Williams, G J ; Olson, J A ; Sharp, P F</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c318t-fcff3806348602b0835e015a525168d4ab5bd10c413c5a46f1dbb9fdf70191ed3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2011</creationdate><topic>Diabetes</topic><topic>Diabetic Retinopathy - pathology</topic><topic>Diagnostic Techniques, Ophthalmological</topic><topic>Humans</topic><topic>Image Processing, Computer-Assisted - methods</topic><topic>Image segmentation</topic><topic>Neovascularization, Pathologic - pathology</topic><topic>Optic Disk - anatomy & histology</topic><topic>Optic Disk - blood supply</topic><topic>Optical imaging</topic><topic>Photography - methods</topic><topic>Pixel</topic><topic>Retina</topic><topic>Retinal Vessels - anatomy & histology</topic><topic>Retinal Vessels - pathology</topic><topic>Retinopathy</topic><topic>ROC Curve</topic><topic>Support vector machines</topic><toplevel>online_resources</toplevel><creatorcontrib>Goatman, K A</creatorcontrib><creatorcontrib>Fleming, A D</creatorcontrib><creatorcontrib>Philip, S</creatorcontrib><creatorcontrib>Williams, G J</creatorcontrib><creatorcontrib>Olson, J A</creatorcontrib><creatorcontrib>Sharp, P F</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE/IET Electronic Library (IEL)</collection><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>IEEE transactions on medical imaging</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Goatman, K A</au><au>Fleming, A D</au><au>Philip, S</au><au>Williams, G J</au><au>Olson, J A</au><au>Sharp, P F</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Detection of New Vessels on the Optic Disc Using Retinal Photographs</atitle><jtitle>IEEE transactions on medical imaging</jtitle><stitle>TMI</stitle><addtitle>IEEE Trans Med Imaging</addtitle><date>2011-04</date><risdate>2011</risdate><volume>30</volume><issue>4</issue><spage>972</spage><epage>979</epage><pages>972-979</pages><issn>0278-0062</issn><eissn>1558-254X</eissn><coden>ITMID4</coden><abstract>Proliferative diabetic retinopathyis a rare condition likely to lead to severe visual impairment. It is characterized by the development of abnormal new retinal vessels. We describe a method for automatically detecting new vessels on the optic disc using retinal photography. Vessel-like candidate segments are first detected using a method based on watershed lines and ridge strength measurement. Fifteen feature parameters, associated with shape, position, orientation, brightness, contrast and line density are calculated for each candidate segment. Based on these features, each segment is categorized as normal or abnormal using a support vector machine (SVM) classifier. The system was trained and tested by cross-validation using 38 images with new vessels and 71 normal images from two diabetic retinal screening centers and one hospital eye clinic. The discrimination performance of the fifteen features was tested against a clinical reference standard. Fourteen features were found to be effective and used in the final test. The area under the receiver operator characteristic curve was 0.911 for detecting images with new vessels on the disc. This accuracy may be sufficient for it to play a useful clinical role in an automated retinopathy analysis system.</abstract><cop>United States</cop><pub>IEEE</pub><pmid>21156389</pmid><doi>10.1109/TMI.2010.2099236</doi><tpages>8</tpages></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0278-0062 |
ispartof | IEEE transactions on medical imaging, 2011-04, Vol.30 (4), p.972-979 |
issn | 0278-0062 1558-254X |
language | eng |
recordid | cdi_pubmed_primary_21156389 |
source | IEEE Electronic Library (IEL) Journals |
subjects | Diabetes Diabetic Retinopathy - pathology Diagnostic Techniques, Ophthalmological Humans Image Processing, Computer-Assisted - methods Image segmentation Neovascularization, Pathologic - pathology Optic Disk - anatomy & histology Optic Disk - blood supply Optical imaging Photography - methods Pixel Retina Retinal Vessels - anatomy & histology Retinal Vessels - pathology Retinopathy ROC Curve Support vector machines |
title | Detection of New Vessels on the Optic Disc Using Retinal Photographs |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-11T18%3A24%3A00IST&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=Detection%20of%20New%20Vessels%20on%20the%20Optic%20Disc%20Using%20Retinal%20Photographs&rft.jtitle=IEEE%20transactions%20on%20medical%20imaging&rft.au=Goatman,%20K%20A&rft.date=2011-04&rft.volume=30&rft.issue=4&rft.spage=972&rft.epage=979&rft.pages=972-979&rft.issn=0278-0062&rft.eissn=1558-254X&rft.coden=ITMID4&rft_id=info:doi/10.1109/TMI.2010.2099236&rft_dat=%3Cproquest_pubme%3E861204155%3C/proquest_pubme%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c318t-fcff3806348602b0835e015a525168d4ab5bd10c413c5a46f1dbb9fdf70191ed3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=861204155&rft_id=info:pmid/21156389&rft_ieee_id=5667059&rfr_iscdi=true |