Semiautomated detection of cerebral microbleeds in magnetic resonance images
Abstract Cerebral microbleeds (CMBs) are increasingly being recognized as an important biomarker for neurovascular diseases. So far, all attempts to count and quantify them have relied on manual methods that are time-consuming and can be inconsistent. A technique is presented that semiautomatically...
Gespeichert in:
| Veröffentlicht in: | Magnetic resonance imaging 2011-07, Vol.29 (6), p.844-852 |
|---|---|
| Hauptverfasser: | , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 852 |
|---|---|
| container_issue | 6 |
| container_start_page | 844 |
| container_title | Magnetic resonance imaging |
| container_volume | 29 |
| creator | Barnes, Samuel R.S Haacke, E. Mark Ayaz, Muhammad Boikov, Alexander S Kirsch, Wolff Kido, Dan |
| description | Abstract Cerebral microbleeds (CMBs) are increasingly being recognized as an important biomarker for neurovascular diseases. So far, all attempts to count and quantify them have relied on manual methods that are time-consuming and can be inconsistent. A technique is presented that semiautomatically identifies CMBs in susceptibility weighted images (SWI). This will both reduce the processing time and increase the consistency over manual methods. This technique relies on a statistical thresholding algorithm to identify hypointensities within the image. A support vector machine (SVM) supervised learning classifier is then used to separate true CMB from other marked hypointensities. The classifier relies on identifying features such as shape and signal intensity to identify true CMBs. The results from the automated section are then subject to manual review to remove false-positives. This technique is able to achieve a sensitivity of 81.7% compared with the gold standard of manual review and consensus by multiple reviewers. In subjects with many CMBs, this presents a faster alternative to current manual techniques at the cost of some lost sensitivity. |
| doi_str_mv | 10.1016/j.mri.2011.02.028 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_879478877</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>1_s2_0_S0730725X1100097X</els_id><sourcerecordid>873120068</sourcerecordid><originalsourceid>FETCH-LOGICAL-c548t-6890cd77df05045ad1d029f1782126d562e5c1234db288286f94c54839b9c8313</originalsourceid><addsrcrecordid>eNqNkUFr3DAQhUVpabZpf0AuxbeevNVIliURKISQtIWFHpJAbkKWxkFb20olO5B_H5lNeughFAYGhvcezPcIOQG6BQrt1_12TGHLKMCWsjLqDdmAkrwWSjdvyYZKTmvJxO0R-ZDznlIqGBfvyREDIaGRekN2VzgGu8xxtDP6yuOMbg5xqmJfOUzYJTtUY3ApdgOiz1WYqtHeTTgHVyXMcbKTwyqUG-aP5F1vh4yfnvcxubm8uD7_Ue9-ff95frarnWjUXLdKU-el9D0VtBHWg6dM9yAVA9Z60TIUDhhvfMeUYqrtdbM6ue60Uxz4MflyyL1P8c-CeTZjyA6HwU4Yl2yU1I1USsr_UHJglLaqKOGgLK_mnLA396l8lR4NULPSNntTaJuVtqGszOr5_Jy-dCP6v44XvEVwehBgofEQMJnsAhZgPqTC2fgYXo3_9o_bDWEKzg6_8RHzPi5pKpgNmFwM5mqte20boDSt5S1_ApxIo8s</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>873120068</pqid></control><display><type>article</type><title>Semiautomated detection of cerebral microbleeds in magnetic resonance images</title><source>MEDLINE</source><source>Elsevier ScienceDirect Journals Complete</source><creator>Barnes, Samuel R.S ; Haacke, E. Mark ; Ayaz, Muhammad ; Boikov, Alexander S ; Kirsch, Wolff ; Kido, Dan</creator><creatorcontrib>Barnes, Samuel R.S ; Haacke, E. Mark ; Ayaz, Muhammad ; Boikov, Alexander S ; Kirsch, Wolff ; Kido, Dan</creatorcontrib><description>Abstract Cerebral microbleeds (CMBs) are increasingly being recognized as an important biomarker for neurovascular diseases. So far, all attempts to count and quantify them have relied on manual methods that are time-consuming and can be inconsistent. A technique is presented that semiautomatically identifies CMBs in susceptibility weighted images (SWI). This will both reduce the processing time and increase the consistency over manual methods. This technique relies on a statistical thresholding algorithm to identify hypointensities within the image. A support vector machine (SVM) supervised learning classifier is then used to separate true CMB from other marked hypointensities. The classifier relies on identifying features such as shape and signal intensity to identify true CMBs. The results from the automated section are then subject to manual review to remove false-positives. This technique is able to achieve a sensitivity of 81.7% compared with the gold standard of manual review and consensus by multiple reviewers. In subjects with many CMBs, this presents a faster alternative to current manual techniques at the cost of some lost sensitivity.</description><identifier>ISSN: 0730-725X</identifier><identifier>EISSN: 1873-5894</identifier><identifier>DOI: 10.1016/j.mri.2011.02.028</identifier><identifier>PMID: 21571479</identifier><language>eng</language><publisher>Netherlands: Elsevier Inc</publisher><subject>Algorithms ; Alzheimer Disease - pathology ; biomarkers ; Cerebral Hemorrhage - diagnosis ; Cerebral microbleed ; Dementia, Vascular - diagnosis ; False Positive Reactions ; Humans ; Image Enhancement - methods ; Image Interpretation, Computer-Assisted - methods ; Learning algorithms ; Longitudinal Studies ; Magnetic Resonance Angiography - methods ; Magnetic resonance imaging ; Pattern Recognition, Automated ; Radiology ; Reviews ; Segmentation ; Sensitivity and Specificity ; Statistics ; Support vector machine ; Susceptibility weighted imaging</subject><ispartof>Magnetic resonance imaging, 2011-07, Vol.29 (6), p.844-852</ispartof><rights>Elsevier Inc.</rights><rights>2011 Elsevier Inc.</rights><rights>Copyright © 2011 Elsevier Inc. All rights reserved.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c548t-6890cd77df05045ad1d029f1782126d562e5c1234db288286f94c54839b9c8313</citedby><cites>FETCH-LOGICAL-c548t-6890cd77df05045ad1d029f1782126d562e5c1234db288286f94c54839b9c8313</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1016/j.mri.2011.02.028$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,780,784,3541,27915,27916,45986</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/21571479$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Barnes, Samuel R.S</creatorcontrib><creatorcontrib>Haacke, E. Mark</creatorcontrib><creatorcontrib>Ayaz, Muhammad</creatorcontrib><creatorcontrib>Boikov, Alexander S</creatorcontrib><creatorcontrib>Kirsch, Wolff</creatorcontrib><creatorcontrib>Kido, Dan</creatorcontrib><title>Semiautomated detection of cerebral microbleeds in magnetic resonance images</title><title>Magnetic resonance imaging</title><addtitle>Magn Reson Imaging</addtitle><description>Abstract Cerebral microbleeds (CMBs) are increasingly being recognized as an important biomarker for neurovascular diseases. So far, all attempts to count and quantify them have relied on manual methods that are time-consuming and can be inconsistent. A technique is presented that semiautomatically identifies CMBs in susceptibility weighted images (SWI). This will both reduce the processing time and increase the consistency over manual methods. This technique relies on a statistical thresholding algorithm to identify hypointensities within the image. A support vector machine (SVM) supervised learning classifier is then used to separate true CMB from other marked hypointensities. The classifier relies on identifying features such as shape and signal intensity to identify true CMBs. The results from the automated section are then subject to manual review to remove false-positives. This technique is able to achieve a sensitivity of 81.7% compared with the gold standard of manual review and consensus by multiple reviewers. In subjects with many CMBs, this presents a faster alternative to current manual techniques at the cost of some lost sensitivity.</description><subject>Algorithms</subject><subject>Alzheimer Disease - pathology</subject><subject>biomarkers</subject><subject>Cerebral Hemorrhage - diagnosis</subject><subject>Cerebral microbleed</subject><subject>Dementia, Vascular - diagnosis</subject><subject>False Positive Reactions</subject><subject>Humans</subject><subject>Image Enhancement - methods</subject><subject>Image Interpretation, Computer-Assisted - methods</subject><subject>Learning algorithms</subject><subject>Longitudinal Studies</subject><subject>Magnetic Resonance Angiography - methods</subject><subject>Magnetic resonance imaging</subject><subject>Pattern Recognition, Automated</subject><subject>Radiology</subject><subject>Reviews</subject><subject>Segmentation</subject><subject>Sensitivity and Specificity</subject><subject>Statistics</subject><subject>Support vector machine</subject><subject>Susceptibility weighted imaging</subject><issn>0730-725X</issn><issn>1873-5894</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2011</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNqNkUFr3DAQhUVpabZpf0AuxbeevNVIliURKISQtIWFHpJAbkKWxkFb20olO5B_H5lNeughFAYGhvcezPcIOQG6BQrt1_12TGHLKMCWsjLqDdmAkrwWSjdvyYZKTmvJxO0R-ZDznlIqGBfvyREDIaGRekN2VzgGu8xxtDP6yuOMbg5xqmJfOUzYJTtUY3ApdgOiz1WYqtHeTTgHVyXMcbKTwyqUG-aP5F1vh4yfnvcxubm8uD7_Ue9-ff95frarnWjUXLdKU-el9D0VtBHWg6dM9yAVA9Z60TIUDhhvfMeUYqrtdbM6ue60Uxz4MflyyL1P8c-CeTZjyA6HwU4Yl2yU1I1USsr_UHJglLaqKOGgLK_mnLA396l8lR4NULPSNntTaJuVtqGszOr5_Jy-dCP6v44XvEVwehBgofEQMJnsAhZgPqTC2fgYXo3_9o_bDWEKzg6_8RHzPi5pKpgNmFwM5mqte20boDSt5S1_ApxIo8s</recordid><startdate>20110701</startdate><enddate>20110701</enddate><creator>Barnes, Samuel R.S</creator><creator>Haacke, E. Mark</creator><creator>Ayaz, Muhammad</creator><creator>Boikov, Alexander S</creator><creator>Kirsch, Wolff</creator><creator>Kido, Dan</creator><general>Elsevier 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>7X8</scope><scope>7QO</scope><scope>7TK</scope><scope>8FD</scope><scope>FR3</scope><scope>P64</scope></search><sort><creationdate>20110701</creationdate><title>Semiautomated detection of cerebral microbleeds in magnetic resonance images</title><author>Barnes, Samuel R.S ; Haacke, E. Mark ; Ayaz, Muhammad ; Boikov, Alexander S ; Kirsch, Wolff ; Kido, Dan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c548t-6890cd77df05045ad1d029f1782126d562e5c1234db288286f94c54839b9c8313</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2011</creationdate><topic>Algorithms</topic><topic>Alzheimer Disease - pathology</topic><topic>biomarkers</topic><topic>Cerebral Hemorrhage - diagnosis</topic><topic>Cerebral microbleed</topic><topic>Dementia, Vascular - diagnosis</topic><topic>False Positive Reactions</topic><topic>Humans</topic><topic>Image Enhancement - methods</topic><topic>Image Interpretation, Computer-Assisted - methods</topic><topic>Learning algorithms</topic><topic>Longitudinal Studies</topic><topic>Magnetic Resonance Angiography - methods</topic><topic>Magnetic resonance imaging</topic><topic>Pattern Recognition, Automated</topic><topic>Radiology</topic><topic>Reviews</topic><topic>Segmentation</topic><topic>Sensitivity and Specificity</topic><topic>Statistics</topic><topic>Support vector machine</topic><topic>Susceptibility weighted imaging</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Barnes, Samuel R.S</creatorcontrib><creatorcontrib>Haacke, E. Mark</creatorcontrib><creatorcontrib>Ayaz, Muhammad</creatorcontrib><creatorcontrib>Boikov, Alexander S</creatorcontrib><creatorcontrib>Kirsch, Wolff</creatorcontrib><creatorcontrib>Kido, Dan</creatorcontrib><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><collection>Biotechnology Research Abstracts</collection><collection>Neurosciences Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>Biotechnology and BioEngineering Abstracts</collection><jtitle>Magnetic resonance imaging</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Barnes, Samuel R.S</au><au>Haacke, E. Mark</au><au>Ayaz, Muhammad</au><au>Boikov, Alexander S</au><au>Kirsch, Wolff</au><au>Kido, Dan</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Semiautomated detection of cerebral microbleeds in magnetic resonance images</atitle><jtitle>Magnetic resonance imaging</jtitle><addtitle>Magn Reson Imaging</addtitle><date>2011-07-01</date><risdate>2011</risdate><volume>29</volume><issue>6</issue><spage>844</spage><epage>852</epage><pages>844-852</pages><issn>0730-725X</issn><eissn>1873-5894</eissn><abstract>Abstract Cerebral microbleeds (CMBs) are increasingly being recognized as an important biomarker for neurovascular diseases. So far, all attempts to count and quantify them have relied on manual methods that are time-consuming and can be inconsistent. A technique is presented that semiautomatically identifies CMBs in susceptibility weighted images (SWI). This will both reduce the processing time and increase the consistency over manual methods. This technique relies on a statistical thresholding algorithm to identify hypointensities within the image. A support vector machine (SVM) supervised learning classifier is then used to separate true CMB from other marked hypointensities. The classifier relies on identifying features such as shape and signal intensity to identify true CMBs. The results from the automated section are then subject to manual review to remove false-positives. This technique is able to achieve a sensitivity of 81.7% compared with the gold standard of manual review and consensus by multiple reviewers. In subjects with many CMBs, this presents a faster alternative to current manual techniques at the cost of some lost sensitivity.</abstract><cop>Netherlands</cop><pub>Elsevier Inc</pub><pmid>21571479</pmid><doi>10.1016/j.mri.2011.02.028</doi><tpages>9</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0730-725X |
| ispartof | Magnetic resonance imaging, 2011-07, Vol.29 (6), p.844-852 |
| issn | 0730-725X 1873-5894 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_879478877 |
| source | MEDLINE; Elsevier ScienceDirect Journals Complete |
| subjects | Algorithms Alzheimer Disease - pathology biomarkers Cerebral Hemorrhage - diagnosis Cerebral microbleed Dementia, Vascular - diagnosis False Positive Reactions Humans Image Enhancement - methods Image Interpretation, Computer-Assisted - methods Learning algorithms Longitudinal Studies Magnetic Resonance Angiography - methods Magnetic resonance imaging Pattern Recognition, Automated Radiology Reviews Segmentation Sensitivity and Specificity Statistics Support vector machine Susceptibility weighted imaging |
| title | Semiautomated detection of cerebral microbleeds in magnetic resonance images |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-14T19%3A55%3A38IST&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=Semiautomated%20detection%20of%20cerebral%20microbleeds%20in%20magnetic%20resonance%20images&rft.jtitle=Magnetic%20resonance%20imaging&rft.au=Barnes,%20Samuel%20R.S&rft.date=2011-07-01&rft.volume=29&rft.issue=6&rft.spage=844&rft.epage=852&rft.pages=844-852&rft.issn=0730-725X&rft.eissn=1873-5894&rft_id=info:doi/10.1016/j.mri.2011.02.028&rft_dat=%3Cproquest_cross%3E873120068%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=873120068&rft_id=info:pmid/21571479&rft_els_id=1_s2_0_S0730725X1100097X&rfr_iscdi=true |