Simultaneous Volumetric Segmentation of Vertebral Bodies and Intervertebral Discs on Fat-Water MR Images
Fat-water magnetic resonance (MR) images allow automated noninvasive analysis of morphological properties and fat fractions of vertebral bodies (VBs) and inter-vertebral discs (IVDs) that constitute an important part of human biomechanical systems. In this paper, we propose a fully automated approac...
Gespeichert in:
Veröffentlicht in: | IEEE journal of biomedical and health informatics 2019-07, Vol.23 (4), p.1692-1701 |
---|---|
Hauptverfasser: | , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 1701 |
---|---|
container_issue | 4 |
container_start_page | 1692 |
container_title | IEEE journal of biomedical and health informatics |
container_volume | 23 |
creator | Fallah, Faezeh Walter, Sven Stephan Bamberg, Fabian Yang, Bin |
description | Fat-water magnetic resonance (MR) images allow automated noninvasive analysis of morphological properties and fat fractions of vertebral bodies (VBs) and inter-vertebral discs (IVDs) that constitute an important part of human biomechanical systems. In this paper, we propose a fully automated approach for simultaneously segmenting multiple VBs and IVDs on fat-water MR images without prior localization or geometry estimation. This method involved a hierarchical random forest (HRF) classifier and a hierarchical conditional random field (HCRF) that encoded a multiresolution image pyramid based on a set of multiscale local and contextual features. The HRF classifier employed penalized multivariate linear discriminants and SMOTE Bagging to handle limited and imbalanced training data with large feature dimension. The HCRF estimated optimum labels according to their spatial and hierarchical consistencies by using the layer-wise significant features determined over the trained HRF classifier. To handle variable sample numbers at different resolutions, resolution-specific hyper-parameters were used. This method was trained and evaluated for segmenting 15 thoracic and lumbar VBs and their IVDs on fat-water MR images of a subset of a large cohort data set. It was further evaluated for segmenting seven IVDs of the lower spine on fat-water images of a public grand challenge. These evaluations revealed the comparable accuracy of this method with the state-of-the-art while requiring less computational burden due to a simultaneous localization and segmentation. |
doi_str_mv | 10.1109/JBHI.2018.2872810 |
format | Article |
fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_pubmed_primary_30281501</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>8476176</ieee_id><sourcerecordid>2116122313</sourcerecordid><originalsourceid>FETCH-LOGICAL-c349t-d5c5afa7604e3b10715eeade2994ab383e7aef0ae6dbc0c42a687b40ad734de63</originalsourceid><addsrcrecordid>eNpdkU1P3DAQhi1UBAj4AQipstRLL9l6bMdxjoUW2AqExOfRmiQTGpQPajuV-u_xapc91Bdb8z7vaMYvYycgFgCi_Pbr7Gq5kALsQtpCWhA77ECCsZmUwn76eEOp99lxCK8iHZtKpdlj-0okQy7ggP2-74a5jzjSNAf-NPXzQNF3Nb-nl4HGiLGbRj61_Il8pMpjz8-mpqPAcWz4cozk_26VH12oA0_8BcbsGZPGb-74csAXCkdst8U-0PHmPmSPFz8fzq-y69vL5fn366xWuoxZk9c5tlgYoUlVIArIibAhWZYaK2UVFUitQDJNVYtaSzS2qLTAplC6IaMO2dd13zc__ZkpRDekqajv1ys6CWBASgUqoV_-Q1-n2Y9pOidlrrSBvLSJgjVV-ykET617892A_p8D4VZJuFUSbpWE2ySRPJ83nedqoGbr-Pj3BJyugY6ItrLVhYHCqHdy4YzU</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2253461598</pqid></control><display><type>article</type><title>Simultaneous Volumetric Segmentation of Vertebral Bodies and Intervertebral Discs on Fat-Water MR Images</title><source>IEEE Electronic Library (IEL)</source><creator>Fallah, Faezeh ; Walter, Sven Stephan ; Bamberg, Fabian ; Yang, Bin</creator><creatorcontrib>Fallah, Faezeh ; Walter, Sven Stephan ; Bamberg, Fabian ; Yang, Bin</creatorcontrib><description>Fat-water magnetic resonance (MR) images allow automated noninvasive analysis of morphological properties and fat fractions of vertebral bodies (VBs) and inter-vertebral discs (IVDs) that constitute an important part of human biomechanical systems. In this paper, we propose a fully automated approach for simultaneously segmenting multiple VBs and IVDs on fat-water MR images without prior localization or geometry estimation. This method involved a hierarchical random forest (HRF) classifier and a hierarchical conditional random field (HCRF) that encoded a multiresolution image pyramid based on a set of multiscale local and contextual features. The HRF classifier employed penalized multivariate linear discriminants and SMOTE Bagging to handle limited and imbalanced training data with large feature dimension. The HCRF estimated optimum labels according to their spatial and hierarchical consistencies by using the layer-wise significant features determined over the trained HRF classifier. To handle variable sample numbers at different resolutions, resolution-specific hyper-parameters were used. This method was trained and evaluated for segmenting 15 thoracic and lumbar VBs and their IVDs on fat-water MR images of a subset of a large cohort data set. It was further evaluated for segmenting seven IVDs of the lower spine on fat-water images of a public grand challenge. These evaluations revealed the comparable accuracy of this method with the state-of-the-art while requiring less computational burden due to a simultaneous localization and segmentation.</description><identifier>ISSN: 2168-2194</identifier><identifier>EISSN: 2168-2208</identifier><identifier>DOI: 10.1109/JBHI.2018.2872810</identifier><identifier>PMID: 30281501</identifier><identifier>CODEN: IJBHA9</identifier><language>eng</language><publisher>United States: IEEE</publisher><subject>Adipose Tissue - diagnostic imaging ; Adult ; Algorithms ; Automation ; Biomechanics ; Body Water - diagnostic imaging ; Classifiers ; Coding ; Computer applications ; Conditional random fields ; Fats ; Feature extraction ; Female ; Hierarchical conditional random field ; hierarchical random forest ; Humans ; Image processing ; Image Processing, Computer-Assisted - methods ; Image segmentation ; Intervertebral Disc - diagnostic imaging ; Intervertebral discs ; Localization ; Lumbar Vertebrae - diagnostic imaging ; Magnetic properties ; Magnetic resonance imaging ; Magnetic Resonance Imaging - methods ; Male ; Middle Aged ; penalized multivariate linear discriminant ; Spatial resolution ; Spine ; Spine (lumbar) ; Thorax ; Training ; Training data ; Vertebrae ; vertebral bodies</subject><ispartof>IEEE journal of biomedical and health informatics, 2019-07, Vol.23 (4), p.1692-1701</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c349t-d5c5afa7604e3b10715eeade2994ab383e7aef0ae6dbc0c42a687b40ad734de63</citedby><cites>FETCH-LOGICAL-c349t-d5c5afa7604e3b10715eeade2994ab383e7aef0ae6dbc0c42a687b40ad734de63</cites><orcidid>0000-0002-2870-825X ; 0000-0002-7115-9161 ; 0000-0002-8322-117X</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/8476176$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/8476176$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/30281501$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Fallah, Faezeh</creatorcontrib><creatorcontrib>Walter, Sven Stephan</creatorcontrib><creatorcontrib>Bamberg, Fabian</creatorcontrib><creatorcontrib>Yang, Bin</creatorcontrib><title>Simultaneous Volumetric Segmentation of Vertebral Bodies and Intervertebral Discs on Fat-Water MR Images</title><title>IEEE journal of biomedical and health informatics</title><addtitle>JBHI</addtitle><addtitle>IEEE J Biomed Health Inform</addtitle><description>Fat-water magnetic resonance (MR) images allow automated noninvasive analysis of morphological properties and fat fractions of vertebral bodies (VBs) and inter-vertebral discs (IVDs) that constitute an important part of human biomechanical systems. In this paper, we propose a fully automated approach for simultaneously segmenting multiple VBs and IVDs on fat-water MR images without prior localization or geometry estimation. This method involved a hierarchical random forest (HRF) classifier and a hierarchical conditional random field (HCRF) that encoded a multiresolution image pyramid based on a set of multiscale local and contextual features. The HRF classifier employed penalized multivariate linear discriminants and SMOTE Bagging to handle limited and imbalanced training data with large feature dimension. The HCRF estimated optimum labels according to their spatial and hierarchical consistencies by using the layer-wise significant features determined over the trained HRF classifier. To handle variable sample numbers at different resolutions, resolution-specific hyper-parameters were used. This method was trained and evaluated for segmenting 15 thoracic and lumbar VBs and their IVDs on fat-water MR images of a subset of a large cohort data set. It was further evaluated for segmenting seven IVDs of the lower spine on fat-water images of a public grand challenge. These evaluations revealed the comparable accuracy of this method with the state-of-the-art while requiring less computational burden due to a simultaneous localization and segmentation.</description><subject>Adipose Tissue - diagnostic imaging</subject><subject>Adult</subject><subject>Algorithms</subject><subject>Automation</subject><subject>Biomechanics</subject><subject>Body Water - diagnostic imaging</subject><subject>Classifiers</subject><subject>Coding</subject><subject>Computer applications</subject><subject>Conditional random fields</subject><subject>Fats</subject><subject>Feature extraction</subject><subject>Female</subject><subject>Hierarchical conditional random field</subject><subject>hierarchical random forest</subject><subject>Humans</subject><subject>Image processing</subject><subject>Image Processing, Computer-Assisted - methods</subject><subject>Image segmentation</subject><subject>Intervertebral Disc - diagnostic imaging</subject><subject>Intervertebral discs</subject><subject>Localization</subject><subject>Lumbar Vertebrae - diagnostic imaging</subject><subject>Magnetic properties</subject><subject>Magnetic resonance imaging</subject><subject>Magnetic Resonance Imaging - methods</subject><subject>Male</subject><subject>Middle Aged</subject><subject>penalized multivariate linear discriminant</subject><subject>Spatial resolution</subject><subject>Spine</subject><subject>Spine (lumbar)</subject><subject>Thorax</subject><subject>Training</subject><subject>Training data</subject><subject>Vertebrae</subject><subject>vertebral bodies</subject><issn>2168-2194</issn><issn>2168-2208</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><sourceid>EIF</sourceid><recordid>eNpdkU1P3DAQhi1UBAj4AQipstRLL9l6bMdxjoUW2AqExOfRmiQTGpQPajuV-u_xapc91Bdb8z7vaMYvYycgFgCi_Pbr7Gq5kALsQtpCWhA77ECCsZmUwn76eEOp99lxCK8iHZtKpdlj-0okQy7ggP2-74a5jzjSNAf-NPXzQNF3Nb-nl4HGiLGbRj61_Il8pMpjz8-mpqPAcWz4cozk_26VH12oA0_8BcbsGZPGb-74csAXCkdst8U-0PHmPmSPFz8fzq-y69vL5fn366xWuoxZk9c5tlgYoUlVIArIibAhWZYaK2UVFUitQDJNVYtaSzS2qLTAplC6IaMO2dd13zc__ZkpRDekqajv1ys6CWBASgUqoV_-Q1-n2Y9pOidlrrSBvLSJgjVV-ykET617892A_p8D4VZJuFUSbpWE2ySRPJ83nedqoGbr-Pj3BJyugY6ItrLVhYHCqHdy4YzU</recordid><startdate>201907</startdate><enddate>201907</enddate><creator>Fallah, Faezeh</creator><creator>Walter, Sven Stephan</creator><creator>Bamberg, Fabian</creator><creator>Yang, Bin</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (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>7QF</scope><scope>7QO</scope><scope>7QQ</scope><scope>7SC</scope><scope>7SE</scope><scope>7SP</scope><scope>7SR</scope><scope>7TA</scope><scope>7TB</scope><scope>7U5</scope><scope>8BQ</scope><scope>8FD</scope><scope>F28</scope><scope>FR3</scope><scope>H8D</scope><scope>JG9</scope><scope>JQ2</scope><scope>K9.</scope><scope>KR7</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>NAPCQ</scope><scope>P64</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0002-2870-825X</orcidid><orcidid>https://orcid.org/0000-0002-7115-9161</orcidid><orcidid>https://orcid.org/0000-0002-8322-117X</orcidid></search><sort><creationdate>201907</creationdate><title>Simultaneous Volumetric Segmentation of Vertebral Bodies and Intervertebral Discs on Fat-Water MR Images</title><author>Fallah, Faezeh ; Walter, Sven Stephan ; Bamberg, Fabian ; Yang, Bin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c349t-d5c5afa7604e3b10715eeade2994ab383e7aef0ae6dbc0c42a687b40ad734de63</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Adipose Tissue - diagnostic imaging</topic><topic>Adult</topic><topic>Algorithms</topic><topic>Automation</topic><topic>Biomechanics</topic><topic>Body Water - diagnostic imaging</topic><topic>Classifiers</topic><topic>Coding</topic><topic>Computer applications</topic><topic>Conditional random fields</topic><topic>Fats</topic><topic>Feature extraction</topic><topic>Female</topic><topic>Hierarchical conditional random field</topic><topic>hierarchical random forest</topic><topic>Humans</topic><topic>Image processing</topic><topic>Image Processing, Computer-Assisted - methods</topic><topic>Image segmentation</topic><topic>Intervertebral Disc - diagnostic imaging</topic><topic>Intervertebral discs</topic><topic>Localization</topic><topic>Lumbar Vertebrae - diagnostic imaging</topic><topic>Magnetic properties</topic><topic>Magnetic resonance imaging</topic><topic>Magnetic Resonance Imaging - methods</topic><topic>Male</topic><topic>Middle Aged</topic><topic>penalized multivariate linear discriminant</topic><topic>Spatial resolution</topic><topic>Spine</topic><topic>Spine (lumbar)</topic><topic>Thorax</topic><topic>Training</topic><topic>Training data</topic><topic>Vertebrae</topic><topic>vertebral bodies</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Fallah, Faezeh</creatorcontrib><creatorcontrib>Walter, Sven Stephan</creatorcontrib><creatorcontrib>Bamberg, Fabian</creatorcontrib><creatorcontrib>Yang, Bin</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE 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>Aluminium Industry Abstracts</collection><collection>Biotechnology Research Abstracts</collection><collection>Ceramic Abstracts</collection><collection>Computer and Information Systems Abstracts</collection><collection>Corrosion Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Engineered Materials Abstracts</collection><collection>Materials Business File</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Solid State and Superconductivity Abstracts</collection><collection>METADEX</collection><collection>Technology Research Database</collection><collection>ANTE: Abstracts in New Technology & Engineering</collection><collection>Engineering Research Database</collection><collection>Aerospace Database</collection><collection>Materials Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Civil Engineering Abstracts</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>Nursing & Allied Health Premium</collection><collection>Biotechnology and BioEngineering Abstracts</collection><collection>MEDLINE - Academic</collection><jtitle>IEEE journal of biomedical and health informatics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Fallah, Faezeh</au><au>Walter, Sven Stephan</au><au>Bamberg, Fabian</au><au>Yang, Bin</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Simultaneous Volumetric Segmentation of Vertebral Bodies and Intervertebral Discs on Fat-Water MR Images</atitle><jtitle>IEEE journal of biomedical and health informatics</jtitle><stitle>JBHI</stitle><addtitle>IEEE J Biomed Health Inform</addtitle><date>2019-07</date><risdate>2019</risdate><volume>23</volume><issue>4</issue><spage>1692</spage><epage>1701</epage><pages>1692-1701</pages><issn>2168-2194</issn><eissn>2168-2208</eissn><coden>IJBHA9</coden><abstract>Fat-water magnetic resonance (MR) images allow automated noninvasive analysis of morphological properties and fat fractions of vertebral bodies (VBs) and inter-vertebral discs (IVDs) that constitute an important part of human biomechanical systems. In this paper, we propose a fully automated approach for simultaneously segmenting multiple VBs and IVDs on fat-water MR images without prior localization or geometry estimation. This method involved a hierarchical random forest (HRF) classifier and a hierarchical conditional random field (HCRF) that encoded a multiresolution image pyramid based on a set of multiscale local and contextual features. The HRF classifier employed penalized multivariate linear discriminants and SMOTE Bagging to handle limited and imbalanced training data with large feature dimension. The HCRF estimated optimum labels according to their spatial and hierarchical consistencies by using the layer-wise significant features determined over the trained HRF classifier. To handle variable sample numbers at different resolutions, resolution-specific hyper-parameters were used. This method was trained and evaluated for segmenting 15 thoracic and lumbar VBs and their IVDs on fat-water MR images of a subset of a large cohort data set. It was further evaluated for segmenting seven IVDs of the lower spine on fat-water images of a public grand challenge. These evaluations revealed the comparable accuracy of this method with the state-of-the-art while requiring less computational burden due to a simultaneous localization and segmentation.</abstract><cop>United States</cop><pub>IEEE</pub><pmid>30281501</pmid><doi>10.1109/JBHI.2018.2872810</doi><tpages>10</tpages><orcidid>https://orcid.org/0000-0002-2870-825X</orcidid><orcidid>https://orcid.org/0000-0002-7115-9161</orcidid><orcidid>https://orcid.org/0000-0002-8322-117X</orcidid></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | ISSN: 2168-2194 |
ispartof | IEEE journal of biomedical and health informatics, 2019-07, Vol.23 (4), p.1692-1701 |
issn | 2168-2194 2168-2208 |
language | eng |
recordid | cdi_pubmed_primary_30281501 |
source | IEEE Electronic Library (IEL) |
subjects | Adipose Tissue - diagnostic imaging Adult Algorithms Automation Biomechanics Body Water - diagnostic imaging Classifiers Coding Computer applications Conditional random fields Fats Feature extraction Female Hierarchical conditional random field hierarchical random forest Humans Image processing Image Processing, Computer-Assisted - methods Image segmentation Intervertebral Disc - diagnostic imaging Intervertebral discs Localization Lumbar Vertebrae - diagnostic imaging Magnetic properties Magnetic resonance imaging Magnetic Resonance Imaging - methods Male Middle Aged penalized multivariate linear discriminant Spatial resolution Spine Spine (lumbar) Thorax Training Training data Vertebrae vertebral bodies |
title | Simultaneous Volumetric Segmentation of Vertebral Bodies and Intervertebral Discs on Fat-Water MR Images |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-27T20%3A33%3A54IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Simultaneous%20Volumetric%20Segmentation%20of%20Vertebral%20Bodies%20and%20Intervertebral%20Discs%20on%20Fat-Water%20MR%20Images&rft.jtitle=IEEE%20journal%20of%20biomedical%20and%20health%20informatics&rft.au=Fallah,%20Faezeh&rft.date=2019-07&rft.volume=23&rft.issue=4&rft.spage=1692&rft.epage=1701&rft.pages=1692-1701&rft.issn=2168-2194&rft.eissn=2168-2208&rft.coden=IJBHA9&rft_id=info:doi/10.1109/JBHI.2018.2872810&rft_dat=%3Cproquest_RIE%3E2116122313%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2253461598&rft_id=info:pmid/30281501&rft_ieee_id=8476176&rfr_iscdi=true |