The application of competitive Hopfield neural network to medical image segmentation
In this paper, a parallel and unsupervised approach using the competitive Hopfield neural network (CHNN) is proposed for medical image segmentation. It is a kind of Hopfield network which incorporates the winner-takes-all (WTA) learning mechanism. The image segmentation is conceptually formulated as...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on medical imaging 1996-08, Vol.15 (4), p.560-567 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 567 |
|---|---|
| container_issue | 4 |
| container_start_page | 560 |
| container_title | IEEE transactions on medical imaging |
| container_volume | 15 |
| creator | CHENG, K.-S LIN, J.-S MAO, C.-W |
| description | In this paper, a parallel and unsupervised approach using the competitive Hopfield neural network (CHNN) is proposed for medical image segmentation. It is a kind of Hopfield network which incorporates the winner-takes-all (WTA) learning mechanism. The image segmentation is conceptually formulated as a problem of pixel clustering based upon the global information of the gray level distribution. Thus, the energy function for minimization is defined as the mean of the squared distance measures of the gray levels within each class. The proposed network avoids the onerous procedure of determining values for the weighting factors in the energy function. In addition, its training scheme enables the network to learn rapidly and effectively. For an image of n gray levels and c interesting objects, the proposed CHNN would consist of n by c neurons and be independent of the image size. In both simulation studies and practical medical image segmentation, the CHNN method shows promising results in comparison with two well-known methods: the hard and the fuzzy c-means (FCM) methods. |
| doi_str_mv | 10.1109/42.511759 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_proquest_miscellaneous_734246401</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>511759</ieee_id><sourcerecordid>734246401</sourcerecordid><originalsourceid>FETCH-LOGICAL-c392t-370432a5d5af040e6a1c5afedc2bbf066ade3677bdb0f5acf8294b60e7a400573</originalsourceid><addsrcrecordid>eNqF0U1P3DAQBmCrKoJly6HXHpAPCMQh2_FXnBwRKh8SUi9biVvkOOOt2yRO4yyo_76mGy03OI0lP_OONEPIZwYrxqD8KvlKMaZV-YEsmFJFxpV8_EgWwHWRAeT8iBzH-AuASQXlITliBWeqFHpB1uufSM0wtN6ayYeeBkdt6Aac_OSfkN6FwXlsG9rjdjRtKtNzGH_TKdAOm9TUUt-ZDdKImw776X_IJ3LgTBvxZK5L8uPm2_r6Lnv4fnt_ffWQWVHyKRMapOBGNco4kIC5YTY9sbG8rh3kuWlQ5FrXTQ1OGesKXso6B9RGAigtluRilzuM4c8W41R1PlpsW9Nj2MZKC8llLoElef6m5EWewsX7kKWxJVNFgpc7aMcQ44iuGsa0ifFvxaB6uUolebW7SrKnc-i2Tlt7lfMZEjibgYlppW40vfVx7wQrBS9kYl92zCPi_nce8g9yz5x1</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>15739158</pqid></control><display><type>article</type><title>The application of competitive Hopfield neural network to medical image segmentation</title><source>IEEE Electronic Library (IEL)</source><creator>CHENG, K.-S ; LIN, J.-S ; MAO, C.-W</creator><creatorcontrib>CHENG, K.-S ; LIN, J.-S ; MAO, C.-W</creatorcontrib><description>In this paper, a parallel and unsupervised approach using the competitive Hopfield neural network (CHNN) is proposed for medical image segmentation. It is a kind of Hopfield network which incorporates the winner-takes-all (WTA) learning mechanism. The image segmentation is conceptually formulated as a problem of pixel clustering based upon the global information of the gray level distribution. Thus, the energy function for minimization is defined as the mean of the squared distance measures of the gray levels within each class. The proposed network avoids the onerous procedure of determining values for the weighting factors in the energy function. In addition, its training scheme enables the network to learn rapidly and effectively. For an image of n gray levels and c interesting objects, the proposed CHNN would consist of n by c neurons and be independent of the image size. In both simulation studies and practical medical image segmentation, the CHNN method shows promising results in comparison with two well-known methods: the hard and the fuzzy c-means (FCM) methods.</description><identifier>ISSN: 0278-0062</identifier><identifier>EISSN: 1558-254X</identifier><identifier>DOI: 10.1109/42.511759</identifier><identifier>PMID: 18215937</identifier><identifier>CODEN: ITMID4</identifier><language>eng</language><publisher>New York, NY: IEEE</publisher><subject>Anatomical structure ; Biological and medical sciences ; Biomedical imaging ; Brain ; Computerized, statistical medical data processing and models in biomedicine ; Hopfield neural networks ; Image segmentation ; Learning systems ; Medical computing and teaching ; Medical diagnostic imaging ; Medical sciences ; Medical simulation ; Multi-layer neural network ; Pixel</subject><ispartof>IEEE transactions on medical imaging, 1996-08, Vol.15 (4), p.560-567</ispartof><rights>1996 INIST-CNRS</rights><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c392t-370432a5d5af040e6a1c5afedc2bbf066ade3677bdb0f5acf8294b60e7a400573</citedby><cites>FETCH-LOGICAL-c392t-370432a5d5af040e6a1c5afedc2bbf066ade3677bdb0f5acf8294b60e7a400573</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/511759$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/511759$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=3193284$$DView record in Pascal Francis$$Hfree_for_read</backlink><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/18215937$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>CHENG, K.-S</creatorcontrib><creatorcontrib>LIN, J.-S</creatorcontrib><creatorcontrib>MAO, C.-W</creatorcontrib><title>The application of competitive Hopfield neural network to medical image segmentation</title><title>IEEE transactions on medical imaging</title><addtitle>TMI</addtitle><addtitle>IEEE Trans Med Imaging</addtitle><description>In this paper, a parallel and unsupervised approach using the competitive Hopfield neural network (CHNN) is proposed for medical image segmentation. It is a kind of Hopfield network which incorporates the winner-takes-all (WTA) learning mechanism. The image segmentation is conceptually formulated as a problem of pixel clustering based upon the global information of the gray level distribution. Thus, the energy function for minimization is defined as the mean of the squared distance measures of the gray levels within each class. The proposed network avoids the onerous procedure of determining values for the weighting factors in the energy function. In addition, its training scheme enables the network to learn rapidly and effectively. For an image of n gray levels and c interesting objects, the proposed CHNN would consist of n by c neurons and be independent of the image size. In both simulation studies and practical medical image segmentation, the CHNN method shows promising results in comparison with two well-known methods: the hard and the fuzzy c-means (FCM) methods.</description><subject>Anatomical structure</subject><subject>Biological and medical sciences</subject><subject>Biomedical imaging</subject><subject>Brain</subject><subject>Computerized, statistical medical data processing and models in biomedicine</subject><subject>Hopfield neural networks</subject><subject>Image segmentation</subject><subject>Learning systems</subject><subject>Medical computing and teaching</subject><subject>Medical diagnostic imaging</subject><subject>Medical sciences</subject><subject>Medical simulation</subject><subject>Multi-layer neural network</subject><subject>Pixel</subject><issn>0278-0062</issn><issn>1558-254X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>1996</creationdate><recordtype>article</recordtype><recordid>eNqF0U1P3DAQBmCrKoJly6HXHpAPCMQh2_FXnBwRKh8SUi9biVvkOOOt2yRO4yyo_76mGy03OI0lP_OONEPIZwYrxqD8KvlKMaZV-YEsmFJFxpV8_EgWwHWRAeT8iBzH-AuASQXlITliBWeqFHpB1uufSM0wtN6ayYeeBkdt6Aac_OSfkN6FwXlsG9rjdjRtKtNzGH_TKdAOm9TUUt-ZDdKImw776X_IJ3LgTBvxZK5L8uPm2_r6Lnv4fnt_ffWQWVHyKRMapOBGNco4kIC5YTY9sbG8rh3kuWlQ5FrXTQ1OGesKXso6B9RGAigtluRilzuM4c8W41R1PlpsW9Nj2MZKC8llLoElef6m5EWewsX7kKWxJVNFgpc7aMcQ44iuGsa0ifFvxaB6uUolebW7SrKnc-i2Tlt7lfMZEjibgYlppW40vfVx7wQrBS9kYl92zCPi_nce8g9yz5x1</recordid><startdate>19960801</startdate><enddate>19960801</enddate><creator>CHENG, K.-S</creator><creator>LIN, J.-S</creator><creator>MAO, C.-W</creator><general>IEEE</general><general>Institute of Electrical and Electronics Engineers</general><scope>IQODW</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7QO</scope><scope>8FD</scope><scope>FR3</scope><scope>P64</scope><scope>7SC</scope><scope>7U5</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>7X8</scope></search><sort><creationdate>19960801</creationdate><title>The application of competitive Hopfield neural network to medical image segmentation</title><author>CHENG, K.-S ; LIN, J.-S ; MAO, C.-W</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c392t-370432a5d5af040e6a1c5afedc2bbf066ade3677bdb0f5acf8294b60e7a400573</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>1996</creationdate><topic>Anatomical structure</topic><topic>Biological and medical sciences</topic><topic>Biomedical imaging</topic><topic>Brain</topic><topic>Computerized, statistical medical data processing and models in biomedicine</topic><topic>Hopfield neural networks</topic><topic>Image segmentation</topic><topic>Learning systems</topic><topic>Medical computing and teaching</topic><topic>Medical diagnostic imaging</topic><topic>Medical sciences</topic><topic>Medical simulation</topic><topic>Multi-layer neural network</topic><topic>Pixel</topic><toplevel>online_resources</toplevel><creatorcontrib>CHENG, K.-S</creatorcontrib><creatorcontrib>LIN, J.-S</creatorcontrib><creatorcontrib>MAO, C.-W</creatorcontrib><collection>Pascal-Francis</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Biotechnology Research Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>Biotechnology and BioEngineering Abstracts</collection><collection>Computer and Information Systems Abstracts</collection><collection>Solid State and Superconductivity Abstracts</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><collection>MEDLINE - Academic</collection><jtitle>IEEE transactions on medical imaging</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>CHENG, K.-S</au><au>LIN, J.-S</au><au>MAO, C.-W</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>The application of competitive Hopfield neural network to medical image segmentation</atitle><jtitle>IEEE transactions on medical imaging</jtitle><stitle>TMI</stitle><addtitle>IEEE Trans Med Imaging</addtitle><date>1996-08-01</date><risdate>1996</risdate><volume>15</volume><issue>4</issue><spage>560</spage><epage>567</epage><pages>560-567</pages><issn>0278-0062</issn><eissn>1558-254X</eissn><coden>ITMID4</coden><abstract>In this paper, a parallel and unsupervised approach using the competitive Hopfield neural network (CHNN) is proposed for medical image segmentation. It is a kind of Hopfield network which incorporates the winner-takes-all (WTA) learning mechanism. The image segmentation is conceptually formulated as a problem of pixel clustering based upon the global information of the gray level distribution. Thus, the energy function for minimization is defined as the mean of the squared distance measures of the gray levels within each class. The proposed network avoids the onerous procedure of determining values for the weighting factors in the energy function. In addition, its training scheme enables the network to learn rapidly and effectively. For an image of n gray levels and c interesting objects, the proposed CHNN would consist of n by c neurons and be independent of the image size. In both simulation studies and practical medical image segmentation, the CHNN method shows promising results in comparison with two well-known methods: the hard and the fuzzy c-means (FCM) methods.</abstract><cop>New York, NY</cop><pub>IEEE</pub><pmid>18215937</pmid><doi>10.1109/42.511759</doi><tpages>8</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 0278-0062 |
| ispartof | IEEE transactions on medical imaging, 1996-08, Vol.15 (4), p.560-567 |
| issn | 0278-0062 1558-254X |
| language | eng |
| recordid | cdi_proquest_miscellaneous_734246401 |
| source | IEEE Electronic Library (IEL) |
| subjects | Anatomical structure Biological and medical sciences Biomedical imaging Brain Computerized, statistical medical data processing and models in biomedicine Hopfield neural networks Image segmentation Learning systems Medical computing and teaching Medical diagnostic imaging Medical sciences Medical simulation Multi-layer neural network Pixel |
| title | The application of competitive Hopfield neural network to medical image segmentation |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T20%3A47%3A19IST&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=The%20application%20of%20competitive%20Hopfield%20neural%20network%20to%20medical%20image%20segmentation&rft.jtitle=IEEE%20transactions%20on%20medical%20imaging&rft.au=CHENG,%20K.-S&rft.date=1996-08-01&rft.volume=15&rft.issue=4&rft.spage=560&rft.epage=567&rft.pages=560-567&rft.issn=0278-0062&rft.eissn=1558-254X&rft.coden=ITMID4&rft_id=info:doi/10.1109/42.511759&rft_dat=%3Cproquest_RIE%3E734246401%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=15739158&rft_id=info:pmid/18215937&rft_ieee_id=511759&rfr_iscdi=true |