An unsupervised coarse-to-fine algorithm for blood vessel segmentation in fundus images
•An unsupervised method to detect blood vessels in fundus images is proposed.•The algorithm effectively tackles image distortions such as central vessel reflex.•The two expert vessel identification images present significant differences.•The average observer plays an important role in defining a neu...
Gespeichert in:
Veröffentlicht in: | Expert systems with applications 2017-07, Vol.78, p.182-192 |
---|---|
Hauptverfasser: | , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 192 |
---|---|
container_issue | |
container_start_page | 182 |
container_title | Expert systems with applications |
container_volume | 78 |
creator | Câmara Neto, Luiz Ramalho, Geraldo L.B. Rocha Neto, Jeová F.S. Veras, Rodrigo M.S. Medeiros, Fátima N.S. |
description | •An unsupervised method to detect blood vessels in fundus images is proposed.•The algorithm effectively tackles image distortions such as central vessel reflex.•The two expert vessel identification images present significant differences.•The average observer plays an important role in defining a neutral standard.•Balanced accuracy is an alternative for performance evaluation of segmentation.
Algorithms for retinal vessel segmentation are powerful tools in automatic tracking systems for early detection of ophthalmological and cardiovascular diseases, and for biometric identification. In order to create more robust and reliable systems, the algorithms need to be accurately evaluated to certify their ability to emulate specific human expertise. The main contribution of this paper is an unsupervised method to detect blood vessels in fundus images using a coarse-to-fine approach. Our methodology combines Gaussian smoothing, a morphological top-hat operator, and vessel contrast enhancement for background homogenization and noise reduction. Here, statistics of spatial dependency and probability are used to coarsely approximate the vessel map with an adaptive local thresholding scheme. The coarse segmentation is then refined through curvature analysis and morphological reconstruction to reduce pixel mislabeling and better estimate the retinal vessel tree. The method was evaluated in terms of its sensitivity, specificity and balanced accuracy. Extensive experiments have been conducted on DRIVE and STARE public retinal images databases. Comparisons with state-of-the-art methods revealed that our method outperformed most recent methods in terms of sensitivity and balanced accuracy with an average of 0.7819 and 0.8702, respectively. Also, the proposed method outperformed state-of-the-art methods when evaluating only pathological images that is a more challenging task. The method achieved for this set of images an average of 0.7842 and 0.8662 for sensitivity and balanced accuracy, respectively. Visual inspection also revealed that the proposed approach effectively addressed main image distortions by reducing mislabeling of central vessel reflex regions and false-positive detection of pathological patterns. These improvements indicate the ability of the method to accurately approximate the vessel tree with reduced visual interference of pathological patterns and vessel-like structures. Therefore, our method has the potential for supporting expert systems in screening, d |
doi_str_mv | 10.1016/j.eswa.2017.02.015 |
format | Article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_1932187853</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0957417417300970</els_id><sourcerecordid>1932187853</sourcerecordid><originalsourceid>FETCH-LOGICAL-c394t-5e98abc7f68061a0e19340c109ccecd523a4f1ea9ab094fe50c238b1d3de37e03</originalsourceid><addsrcrecordid>eNp9kEtLAzEUhYMoWB9_wFXA9Yw3k3mCm1J8QcGN4jJkkpuaYZrUZKbivzelrl3dzfnOPXyE3DDIGbD6bsgxfsu8ANbkUOTAqhOyYG3Ds7rp-ClZQFc1Wcma8pxcxDhACgI0C_KxdHR2cd5h2NuImiovQ8Rs8pmxDqkcNz7Y6XNLjQ-0H73XdI8x4kgjbrboJjlZ76h11MxOz5HardxgvCJnRo4Rr__uJXl_fHhbPWfr16eX1XKdKd6VU1Zh18peNaZuoWYSkHW8BMWgUwqVrgouS8NQdrKHrjRYgSp42zPNNfIGgV-S22PvLvivGeMkBj8Hl16KVFUkBW3FU6o4plTwMQY0YhfSzvAjGIiDQDGIg0BxECigEElggu6PEKb9e4tBRGXRKdQ2oJqE9vY__Be8B3ri</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1932187853</pqid></control><display><type>article</type><title>An unsupervised coarse-to-fine algorithm for blood vessel segmentation in fundus images</title><source>Elsevier ScienceDirect Journals Complete</source><creator>Câmara Neto, Luiz ; Ramalho, Geraldo L.B. ; Rocha Neto, Jeová F.S. ; Veras, Rodrigo M.S. ; Medeiros, Fátima N.S.</creator><creatorcontrib>Câmara Neto, Luiz ; Ramalho, Geraldo L.B. ; Rocha Neto, Jeová F.S. ; Veras, Rodrigo M.S. ; Medeiros, Fátima N.S.</creatorcontrib><description>•An unsupervised method to detect blood vessels in fundus images is proposed.•The algorithm effectively tackles image distortions such as central vessel reflex.•The two expert vessel identification images present significant differences.•The average observer plays an important role in defining a neutral standard.•Balanced accuracy is an alternative for performance evaluation of segmentation.
Algorithms for retinal vessel segmentation are powerful tools in automatic tracking systems for early detection of ophthalmological and cardiovascular diseases, and for biometric identification. In order to create more robust and reliable systems, the algorithms need to be accurately evaluated to certify their ability to emulate specific human expertise. The main contribution of this paper is an unsupervised method to detect blood vessels in fundus images using a coarse-to-fine approach. Our methodology combines Gaussian smoothing, a morphological top-hat operator, and vessel contrast enhancement for background homogenization and noise reduction. Here, statistics of spatial dependency and probability are used to coarsely approximate the vessel map with an adaptive local thresholding scheme. The coarse segmentation is then refined through curvature analysis and morphological reconstruction to reduce pixel mislabeling and better estimate the retinal vessel tree. The method was evaluated in terms of its sensitivity, specificity and balanced accuracy. Extensive experiments have been conducted on DRIVE and STARE public retinal images databases. Comparisons with state-of-the-art methods revealed that our method outperformed most recent methods in terms of sensitivity and balanced accuracy with an average of 0.7819 and 0.8702, respectively. Also, the proposed method outperformed state-of-the-art methods when evaluating only pathological images that is a more challenging task. The method achieved for this set of images an average of 0.7842 and 0.8662 for sensitivity and balanced accuracy, respectively. Visual inspection also revealed that the proposed approach effectively addressed main image distortions by reducing mislabeling of central vessel reflex regions and false-positive detection of pathological patterns. These improvements indicate the ability of the method to accurately approximate the vessel tree with reduced visual interference of pathological patterns and vessel-like structures. Therefore, our method has the potential for supporting expert systems in screening, diagnosis and treatment of ophthalmological diseases, and furthermore for personal recognition based on retinal profile matching.</description><identifier>ISSN: 0957-4174</identifier><identifier>EISSN: 1873-6793</identifier><identifier>DOI: 10.1016/j.eswa.2017.02.015</identifier><language>eng</language><publisher>New York: Elsevier Ltd</publisher><subject>Algorithms ; Background noise ; Balanced accuracy ; Blood vessels ; Curvature ; Expert systems ; Heart diseases ; Homogenization ; Image detection ; Image processing ; Image segmentation ; Local coarse segmentation ; Noise reduction ; Probability ; Retinal images ; Retinal vasculature ; Sensitivity analysis ; Smoothing ; State of the art ; Tracking systems ; Vessel refinement</subject><ispartof>Expert systems with applications, 2017-07, Vol.78, p.182-192</ispartof><rights>2017 Elsevier Ltd</rights><rights>Copyright Elsevier BV Jul 15, 2017</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c394t-5e98abc7f68061a0e19340c109ccecd523a4f1ea9ab094fe50c238b1d3de37e03</citedby><cites>FETCH-LOGICAL-c394t-5e98abc7f68061a0e19340c109ccecd523a4f1ea9ab094fe50c238b1d3de37e03</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1016/j.eswa.2017.02.015$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,780,784,3550,27924,27925,45995</link.rule.ids></links><search><creatorcontrib>Câmara Neto, Luiz</creatorcontrib><creatorcontrib>Ramalho, Geraldo L.B.</creatorcontrib><creatorcontrib>Rocha Neto, Jeová F.S.</creatorcontrib><creatorcontrib>Veras, Rodrigo M.S.</creatorcontrib><creatorcontrib>Medeiros, Fátima N.S.</creatorcontrib><title>An unsupervised coarse-to-fine algorithm for blood vessel segmentation in fundus images</title><title>Expert systems with applications</title><description>•An unsupervised method to detect blood vessels in fundus images is proposed.•The algorithm effectively tackles image distortions such as central vessel reflex.•The two expert vessel identification images present significant differences.•The average observer plays an important role in defining a neutral standard.•Balanced accuracy is an alternative for performance evaluation of segmentation.
Algorithms for retinal vessel segmentation are powerful tools in automatic tracking systems for early detection of ophthalmological and cardiovascular diseases, and for biometric identification. In order to create more robust and reliable systems, the algorithms need to be accurately evaluated to certify their ability to emulate specific human expertise. The main contribution of this paper is an unsupervised method to detect blood vessels in fundus images using a coarse-to-fine approach. Our methodology combines Gaussian smoothing, a morphological top-hat operator, and vessel contrast enhancement for background homogenization and noise reduction. Here, statistics of spatial dependency and probability are used to coarsely approximate the vessel map with an adaptive local thresholding scheme. The coarse segmentation is then refined through curvature analysis and morphological reconstruction to reduce pixel mislabeling and better estimate the retinal vessel tree. The method was evaluated in terms of its sensitivity, specificity and balanced accuracy. Extensive experiments have been conducted on DRIVE and STARE public retinal images databases. Comparisons with state-of-the-art methods revealed that our method outperformed most recent methods in terms of sensitivity and balanced accuracy with an average of 0.7819 and 0.8702, respectively. Also, the proposed method outperformed state-of-the-art methods when evaluating only pathological images that is a more challenging task. The method achieved for this set of images an average of 0.7842 and 0.8662 for sensitivity and balanced accuracy, respectively. Visual inspection also revealed that the proposed approach effectively addressed main image distortions by reducing mislabeling of central vessel reflex regions and false-positive detection of pathological patterns. These improvements indicate the ability of the method to accurately approximate the vessel tree with reduced visual interference of pathological patterns and vessel-like structures. Therefore, our method has the potential for supporting expert systems in screening, diagnosis and treatment of ophthalmological diseases, and furthermore for personal recognition based on retinal profile matching.</description><subject>Algorithms</subject><subject>Background noise</subject><subject>Balanced accuracy</subject><subject>Blood vessels</subject><subject>Curvature</subject><subject>Expert systems</subject><subject>Heart diseases</subject><subject>Homogenization</subject><subject>Image detection</subject><subject>Image processing</subject><subject>Image segmentation</subject><subject>Local coarse segmentation</subject><subject>Noise reduction</subject><subject>Probability</subject><subject>Retinal images</subject><subject>Retinal vasculature</subject><subject>Sensitivity analysis</subject><subject>Smoothing</subject><subject>State of the art</subject><subject>Tracking systems</subject><subject>Vessel refinement</subject><issn>0957-4174</issn><issn>1873-6793</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2017</creationdate><recordtype>article</recordtype><recordid>eNp9kEtLAzEUhYMoWB9_wFXA9Yw3k3mCm1J8QcGN4jJkkpuaYZrUZKbivzelrl3dzfnOPXyE3DDIGbD6bsgxfsu8ANbkUOTAqhOyYG3Ds7rp-ClZQFc1Wcma8pxcxDhACgI0C_KxdHR2cd5h2NuImiovQ8Rs8pmxDqkcNz7Y6XNLjQ-0H73XdI8x4kgjbrboJjlZ76h11MxOz5HardxgvCJnRo4Rr__uJXl_fHhbPWfr16eX1XKdKd6VU1Zh18peNaZuoWYSkHW8BMWgUwqVrgouS8NQdrKHrjRYgSp42zPNNfIGgV-S22PvLvivGeMkBj8Hl16KVFUkBW3FU6o4plTwMQY0YhfSzvAjGIiDQDGIg0BxECigEElggu6PEKb9e4tBRGXRKdQ2oJqE9vY__Be8B3ri</recordid><startdate>20170715</startdate><enddate>20170715</enddate><creator>Câmara Neto, Luiz</creator><creator>Ramalho, Geraldo L.B.</creator><creator>Rocha Neto, Jeová F.S.</creator><creator>Veras, Rodrigo M.S.</creator><creator>Medeiros, Fátima N.S.</creator><general>Elsevier Ltd</general><general>Elsevier BV</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>20170715</creationdate><title>An unsupervised coarse-to-fine algorithm for blood vessel segmentation in fundus images</title><author>Câmara Neto, Luiz ; Ramalho, Geraldo L.B. ; Rocha Neto, Jeová F.S. ; Veras, Rodrigo M.S. ; Medeiros, Fátima N.S.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c394t-5e98abc7f68061a0e19340c109ccecd523a4f1ea9ab094fe50c238b1d3de37e03</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2017</creationdate><topic>Algorithms</topic><topic>Background noise</topic><topic>Balanced accuracy</topic><topic>Blood vessels</topic><topic>Curvature</topic><topic>Expert systems</topic><topic>Heart diseases</topic><topic>Homogenization</topic><topic>Image detection</topic><topic>Image processing</topic><topic>Image segmentation</topic><topic>Local coarse segmentation</topic><topic>Noise reduction</topic><topic>Probability</topic><topic>Retinal images</topic><topic>Retinal vasculature</topic><topic>Sensitivity analysis</topic><topic>Smoothing</topic><topic>State of the art</topic><topic>Tracking systems</topic><topic>Vessel refinement</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Câmara Neto, Luiz</creatorcontrib><creatorcontrib>Ramalho, Geraldo L.B.</creatorcontrib><creatorcontrib>Rocha Neto, Jeová F.S.</creatorcontrib><creatorcontrib>Veras, Rodrigo M.S.</creatorcontrib><creatorcontrib>Medeiros, Fátima N.S.</creatorcontrib><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Technology 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><jtitle>Expert systems with applications</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Câmara Neto, Luiz</au><au>Ramalho, Geraldo L.B.</au><au>Rocha Neto, Jeová F.S.</au><au>Veras, Rodrigo M.S.</au><au>Medeiros, Fátima N.S.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>An unsupervised coarse-to-fine algorithm for blood vessel segmentation in fundus images</atitle><jtitle>Expert systems with applications</jtitle><date>2017-07-15</date><risdate>2017</risdate><volume>78</volume><spage>182</spage><epage>192</epage><pages>182-192</pages><issn>0957-4174</issn><eissn>1873-6793</eissn><abstract>•An unsupervised method to detect blood vessels in fundus images is proposed.•The algorithm effectively tackles image distortions such as central vessel reflex.•The two expert vessel identification images present significant differences.•The average observer plays an important role in defining a neutral standard.•Balanced accuracy is an alternative for performance evaluation of segmentation.
Algorithms for retinal vessel segmentation are powerful tools in automatic tracking systems for early detection of ophthalmological and cardiovascular diseases, and for biometric identification. In order to create more robust and reliable systems, the algorithms need to be accurately evaluated to certify their ability to emulate specific human expertise. The main contribution of this paper is an unsupervised method to detect blood vessels in fundus images using a coarse-to-fine approach. Our methodology combines Gaussian smoothing, a morphological top-hat operator, and vessel contrast enhancement for background homogenization and noise reduction. Here, statistics of spatial dependency and probability are used to coarsely approximate the vessel map with an adaptive local thresholding scheme. The coarse segmentation is then refined through curvature analysis and morphological reconstruction to reduce pixel mislabeling and better estimate the retinal vessel tree. The method was evaluated in terms of its sensitivity, specificity and balanced accuracy. Extensive experiments have been conducted on DRIVE and STARE public retinal images databases. Comparisons with state-of-the-art methods revealed that our method outperformed most recent methods in terms of sensitivity and balanced accuracy with an average of 0.7819 and 0.8702, respectively. Also, the proposed method outperformed state-of-the-art methods when evaluating only pathological images that is a more challenging task. The method achieved for this set of images an average of 0.7842 and 0.8662 for sensitivity and balanced accuracy, respectively. Visual inspection also revealed that the proposed approach effectively addressed main image distortions by reducing mislabeling of central vessel reflex regions and false-positive detection of pathological patterns. These improvements indicate the ability of the method to accurately approximate the vessel tree with reduced visual interference of pathological patterns and vessel-like structures. Therefore, our method has the potential for supporting expert systems in screening, diagnosis and treatment of ophthalmological diseases, and furthermore for personal recognition based on retinal profile matching.</abstract><cop>New York</cop><pub>Elsevier Ltd</pub><doi>10.1016/j.eswa.2017.02.015</doi><tpages>11</tpages></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0957-4174 |
ispartof | Expert systems with applications, 2017-07, Vol.78, p.182-192 |
issn | 0957-4174 1873-6793 |
language | eng |
recordid | cdi_proquest_journals_1932187853 |
source | Elsevier ScienceDirect Journals Complete |
subjects | Algorithms Background noise Balanced accuracy Blood vessels Curvature Expert systems Heart diseases Homogenization Image detection Image processing Image segmentation Local coarse segmentation Noise reduction Probability Retinal images Retinal vasculature Sensitivity analysis Smoothing State of the art Tracking systems Vessel refinement |
title | An unsupervised coarse-to-fine algorithm for blood vessel segmentation in fundus images |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T19%3A04%3A58IST&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=An%20unsupervised%20coarse-to-fine%20algorithm%20for%20blood%20vessel%20segmentation%20in%20fundus%20images&rft.jtitle=Expert%20systems%20with%20applications&rft.au=C%C3%A2mara%20Neto,%20Luiz&rft.date=2017-07-15&rft.volume=78&rft.spage=182&rft.epage=192&rft.pages=182-192&rft.issn=0957-4174&rft.eissn=1873-6793&rft_id=info:doi/10.1016/j.eswa.2017.02.015&rft_dat=%3Cproquest_cross%3E1932187853%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=1932187853&rft_id=info:pmid/&rft_els_id=S0957417417300970&rfr_iscdi=true |