Classification of microcalcifications in digital mammograms using trend-oriented radial basis function neural network
We proposed some novel classification features for the microcalcification of mammograms, and selected the effective combined features using Karhunen–Loeve (KL) transformation followed by the restricted Euclidean distance measure, and finally applied the proposed trend-oriented radial basis function...
Gespeichert in:
| Veröffentlicht in: | Pattern recognition 1999-05, Vol.32 (5), p.891-903 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 903 |
|---|---|
| container_issue | 5 |
| container_start_page | 891 |
| container_title | Pattern recognition |
| container_volume | 32 |
| creator | Tsujii, Osamu Freedman, Matthew T. Mun, Seong K. |
| description | We proposed some novel classification features for the microcalcification of mammograms, and selected the effective combined features using Karhunen–Loeve (KL) transformation followed by the restricted Euclidean distance measure, and finally applied the proposed trend-oriented radial basis function neural network (TRBF-NN) to distinguish the benign group from the malignant group and evaluate the performance with the round-robin method. The two-dimensional KL features were more distinguishable than the raw two-dimensional features. The TRBF-NN was able to define the more generalized distribution than those distributions defined by the conventional RBF-NNs. According to the receiver operating characteristic analysis, the proposed system performed better than two trained radiologists. |
| doi_str_mv | 10.1016/S0031-3203(98)00099-5 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_26887975</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0031320398000995</els_id><sourcerecordid>399904</sourcerecordid><originalsourceid>FETCH-LOGICAL-c445t-ff295d3506ef510cdd166bf480f7b9e8202221cfa5753514fe947fb036525c813</originalsourceid><addsrcrecordid>eNqFkU1rFEEQhhtRcI3-BKEPInoYU90z_TEnkUVNIOAhem56-2NpnemOXTMJ-ff27oZ4zKmg6ql6qfcl5C2DTwyYPL8G6FnXc-g_jPojAIxjJ56RDdOq7wQb-HOyeURekleIvwGYaoMNWbeTRUwxObukkmmJdE6uFmcn99hFmjL1aZ8WO9HZznPZVzsjXTHlPV1qyL4rNYW8BE-r9alhO4sJaVyzO97NYa2tm8NyV-qf1-RFtBOGNw_1jPz69vXn9qK7-vH9cvvlqnPDIJYuRj4K3wuQIQoGznsm5S4OGqLajUFz4JwzF61Qom-PxjAOKu6gl4ILp1l_Rt6f7t7U8ncNuJg5oQvTZHMoKxoutVZjW34SZAMMWsoGihPYPEKsIZqbmmZb7w0Dc0jDHNMwB6vNqM0xDXMQePcgYLF5G6vNLuH_ZaUGqaBhn09YaK7cplANuuarCz7V4BbjS3pC6B8KaaA0</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>21404866</pqid></control><display><type>article</type><title>Classification of microcalcifications in digital mammograms using trend-oriented radial basis function neural network</title><source>Elsevier ScienceDirect Journals Complete</source><creator>Tsujii, Osamu ; Freedman, Matthew T. ; Mun, Seong K.</creator><creatorcontrib>Tsujii, Osamu ; Freedman, Matthew T. ; Mun, Seong K.</creatorcontrib><description>We proposed some novel classification features for the microcalcification of mammograms, and selected the effective combined features using Karhunen–Loeve (KL) transformation followed by the restricted Euclidean distance measure, and finally applied the proposed trend-oriented radial basis function neural network (TRBF-NN) to distinguish the benign group from the malignant group and evaluate the performance with the round-robin method. The two-dimensional KL features were more distinguishable than the raw two-dimensional features. The TRBF-NN was able to define the more generalized distribution than those distributions defined by the conventional RBF-NNs. According to the receiver operating characteristic analysis, the proposed system performed better than two trained radiologists.</description><identifier>ISSN: 0031-3203</identifier><identifier>EISSN: 1873-5142</identifier><identifier>DOI: 10.1016/S0031-3203(98)00099-5</identifier><identifier>CODEN: PTNRA8</identifier><language>eng</language><publisher>Oxford: Elsevier Ltd</publisher><subject>Applied sciences ; Artificial intelligence ; Biological and medical sciences ; Calcification (biochemistry) ; Classification ; Computer science; control theory; systems ; Computerized, statistical medical data processing and models in biomedicine ; Connectionism. Neural networks ; Euclidean distance measure ; Exact sciences and technology ; Feature selection ; Karhunen–Loeve transformation ; Mammograms ; Mammography ; Mathematical transformations ; Medical management aid. Diagnosis aid ; Medical sciences ; Microcalcification ; Neural network ; Neural networks ; Pattern recognition. Digital image processing. Computational geometry ; Radial basis function ; Receiver operating characteristic ; Round-robin method ; Two dimensional</subject><ispartof>Pattern recognition, 1999-05, Vol.32 (5), p.891-903</ispartof><rights>1999 Pattern Recognition Society</rights><rights>1999 INIST-CNRS</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c445t-ff295d3506ef510cdd166bf480f7b9e8202221cfa5753514fe947fb036525c813</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.sciencedirect.com/science/article/pii/S0031320398000995$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,776,780,3537,27901,27902,65534</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=1774670$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><creatorcontrib>Tsujii, Osamu</creatorcontrib><creatorcontrib>Freedman, Matthew T.</creatorcontrib><creatorcontrib>Mun, Seong K.</creatorcontrib><title>Classification of microcalcifications in digital mammograms using trend-oriented radial basis function neural network</title><title>Pattern recognition</title><description>We proposed some novel classification features for the microcalcification of mammograms, and selected the effective combined features using Karhunen–Loeve (KL) transformation followed by the restricted Euclidean distance measure, and finally applied the proposed trend-oriented radial basis function neural network (TRBF-NN) to distinguish the benign group from the malignant group and evaluate the performance with the round-robin method. The two-dimensional KL features were more distinguishable than the raw two-dimensional features. The TRBF-NN was able to define the more generalized distribution than those distributions defined by the conventional RBF-NNs. According to the receiver operating characteristic analysis, the proposed system performed better than two trained radiologists.</description><subject>Applied sciences</subject><subject>Artificial intelligence</subject><subject>Biological and medical sciences</subject><subject>Calcification (biochemistry)</subject><subject>Classification</subject><subject>Computer science; control theory; systems</subject><subject>Computerized, statistical medical data processing and models in biomedicine</subject><subject>Connectionism. Neural networks</subject><subject>Euclidean distance measure</subject><subject>Exact sciences and technology</subject><subject>Feature selection</subject><subject>Karhunen–Loeve transformation</subject><subject>Mammograms</subject><subject>Mammography</subject><subject>Mathematical transformations</subject><subject>Medical management aid. Diagnosis aid</subject><subject>Medical sciences</subject><subject>Microcalcification</subject><subject>Neural network</subject><subject>Neural networks</subject><subject>Pattern recognition. Digital image processing. Computational geometry</subject><subject>Radial basis function</subject><subject>Receiver operating characteristic</subject><subject>Round-robin method</subject><subject>Two dimensional</subject><issn>0031-3203</issn><issn>1873-5142</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>1999</creationdate><recordtype>article</recordtype><recordid>eNqFkU1rFEEQhhtRcI3-BKEPInoYU90z_TEnkUVNIOAhem56-2NpnemOXTMJ-ff27oZ4zKmg6ql6qfcl5C2DTwyYPL8G6FnXc-g_jPojAIxjJ56RDdOq7wQb-HOyeURekleIvwGYaoMNWbeTRUwxObukkmmJdE6uFmcn99hFmjL1aZ8WO9HZznPZVzsjXTHlPV1qyL4rNYW8BE-r9alhO4sJaVyzO97NYa2tm8NyV-qf1-RFtBOGNw_1jPz69vXn9qK7-vH9cvvlqnPDIJYuRj4K3wuQIQoGznsm5S4OGqLajUFz4JwzF61Qom-PxjAOKu6gl4ILp1l_Rt6f7t7U8ncNuJg5oQvTZHMoKxoutVZjW34SZAMMWsoGihPYPEKsIZqbmmZb7w0Dc0jDHNMwB6vNqM0xDXMQePcgYLF5G6vNLuH_ZaUGqaBhn09YaK7cplANuuarCz7V4BbjS3pC6B8KaaA0</recordid><startdate>19990501</startdate><enddate>19990501</enddate><creator>Tsujii, Osamu</creator><creator>Freedman, Matthew T.</creator><creator>Mun, Seong K.</creator><general>Elsevier Ltd</general><general>Elsevier Science</general><scope>IQODW</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>19990501</creationdate><title>Classification of microcalcifications in digital mammograms using trend-oriented radial basis function neural network</title><author>Tsujii, Osamu ; Freedman, Matthew T. ; Mun, Seong K.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c445t-ff295d3506ef510cdd166bf480f7b9e8202221cfa5753514fe947fb036525c813</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>1999</creationdate><topic>Applied sciences</topic><topic>Artificial intelligence</topic><topic>Biological and medical sciences</topic><topic>Calcification (biochemistry)</topic><topic>Classification</topic><topic>Computer science; control theory; systems</topic><topic>Computerized, statistical medical data processing and models in biomedicine</topic><topic>Connectionism. Neural networks</topic><topic>Euclidean distance measure</topic><topic>Exact sciences and technology</topic><topic>Feature selection</topic><topic>Karhunen–Loeve transformation</topic><topic>Mammograms</topic><topic>Mammography</topic><topic>Mathematical transformations</topic><topic>Medical management aid. Diagnosis aid</topic><topic>Medical sciences</topic><topic>Microcalcification</topic><topic>Neural network</topic><topic>Neural networks</topic><topic>Pattern recognition. Digital image processing. Computational geometry</topic><topic>Radial basis function</topic><topic>Receiver operating characteristic</topic><topic>Round-robin method</topic><topic>Two dimensional</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Tsujii, Osamu</creatorcontrib><creatorcontrib>Freedman, Matthew T.</creatorcontrib><creatorcontrib>Mun, Seong K.</creatorcontrib><collection>Pascal-Francis</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications 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>Pattern recognition</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Tsujii, Osamu</au><au>Freedman, Matthew T.</au><au>Mun, Seong K.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Classification of microcalcifications in digital mammograms using trend-oriented radial basis function neural network</atitle><jtitle>Pattern recognition</jtitle><date>1999-05-01</date><risdate>1999</risdate><volume>32</volume><issue>5</issue><spage>891</spage><epage>903</epage><pages>891-903</pages><issn>0031-3203</issn><eissn>1873-5142</eissn><coden>PTNRA8</coden><abstract>We proposed some novel classification features for the microcalcification of mammograms, and selected the effective combined features using Karhunen–Loeve (KL) transformation followed by the restricted Euclidean distance measure, and finally applied the proposed trend-oriented radial basis function neural network (TRBF-NN) to distinguish the benign group from the malignant group and evaluate the performance with the round-robin method. The two-dimensional KL features were more distinguishable than the raw two-dimensional features. The TRBF-NN was able to define the more generalized distribution than those distributions defined by the conventional RBF-NNs. According to the receiver operating characteristic analysis, the proposed system performed better than two trained radiologists.</abstract><cop>Oxford</cop><pub>Elsevier Ltd</pub><doi>10.1016/S0031-3203(98)00099-5</doi><tpages>13</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0031-3203 |
| ispartof | Pattern recognition, 1999-05, Vol.32 (5), p.891-903 |
| issn | 0031-3203 1873-5142 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_26887975 |
| source | Elsevier ScienceDirect Journals Complete |
| subjects | Applied sciences Artificial intelligence Biological and medical sciences Calcification (biochemistry) Classification Computer science control theory systems Computerized, statistical medical data processing and models in biomedicine Connectionism. Neural networks Euclidean distance measure Exact sciences and technology Feature selection Karhunen–Loeve transformation Mammograms Mammography Mathematical transformations Medical management aid. Diagnosis aid Medical sciences Microcalcification Neural network Neural networks Pattern recognition. Digital image processing. Computational geometry Radial basis function Receiver operating characteristic Round-robin method Two dimensional |
| title | Classification of microcalcifications in digital mammograms using trend-oriented radial basis function neural network |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-14T10%3A55%3A25IST&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=Classification%20of%20microcalcifications%20in%20digital%20mammograms%20using%20trend-oriented%20radial%20basis%20function%20neural%20network&rft.jtitle=Pattern%20recognition&rft.au=Tsujii,%20Osamu&rft.date=1999-05-01&rft.volume=32&rft.issue=5&rft.spage=891&rft.epage=903&rft.pages=891-903&rft.issn=0031-3203&rft.eissn=1873-5142&rft.coden=PTNRA8&rft_id=info:doi/10.1016/S0031-3203(98)00099-5&rft_dat=%3Cproquest_cross%3E399904%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=21404866&rft_id=info:pmid/&rft_els_id=S0031320398000995&rfr_iscdi=true |