Loading…
PULMONARY NODULE CLASSIFICATION: SIZE DISTRIBUTION ISSUES
Automated nodule classification systems determine a model based on features extracted from documented databases of nodules. These databases cover a large size range and have an unequal distribution of malignant and benign nodules, leading to a high correlation between malignancy and size. For two re...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Conference Proceeding |
| Language: | English |
| Subjects: | |
| Online Access: | Request full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | |
|---|---|
| cites | |
| container_end_page | 1251 |
| container_issue | |
| container_start_page | 1248 |
| container_title | |
| container_volume | |
| creator | Jirapatnakul, A.C. Reeves, A.P. Apanasovich, T.V. Biancardi, A.M. Yankelevitz, D.F. Henschke, C.I. |
| description | Automated nodule classification systems determine a model based on features extracted from documented databases of nodules. These databases cover a large size range and have an unequal distribution of malignant and benign nodules, leading to a high correlation between malignancy and size. For two recent studies in the literature, much of the reported performance of the system may be derived from size based on analysis of their size distributions. We performed experiments to determine the effect of unequal size distribution on a nodule classification system's performance. Preliminary results indicate that the performance across the entire dataset (a sensitivity/specificity of 0.85/0.80) does not generalize to a subset of nodules (0.50/0.80), but performance can be improved by specifically training on that subset (0.60/0.80). Additional testing with larger datasets needs to be performed, but results reported in this area are overly optimistic. |
| doi_str_mv | 10.1109/ISBI.2007.357085 |
| format | conference_proceeding |
| fullrecord | <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_4193519</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>4193519</ieee_id><sourcerecordid>4193519</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-b0229729a2f656333efb9c59394e69fd06fd57b2278aeb59ebf1d9592b2f4c853</originalsourceid><addsrcrecordid>eNo1jE9LxDAUxOM_cF17F7z0C7QmL3lNn7dut6uB2sqmPehlabcJVBRk68Vvb8V1YBiYHzOM3QgeC8HpztiViYFzHUvUPMUTFpBOhQKleKIBTtlCkMIoVQhn7OofCHV-BJogvWTBNL3xWZJkgrhg9NyWT3WVbV_Cql63ZRHmZWat2Zg8a0xd3YfWvBbh2thma1btbxUaa9vCXrML371PLjjmkrWboskfo7J-mMdlNAqNX1HPAUgDdeATTKSUzve0R5KkXEJ-4IkfUPcAOu1cj-R6LwZCgh682qcol-z273d0zu0-D-NHd_jeKUESZ_8A4DpF6Q</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>PULMONARY NODULE CLASSIFICATION: SIZE DISTRIBUTION ISSUES</title><source>IEEE Xplore All Conference Series</source><creator>Jirapatnakul, A.C. ; Reeves, A.P. ; Apanasovich, T.V. ; Biancardi, A.M. ; Yankelevitz, D.F. ; Henschke, C.I.</creator><creatorcontrib>Jirapatnakul, A.C. ; Reeves, A.P. ; Apanasovich, T.V. ; Biancardi, A.M. ; Yankelevitz, D.F. ; Henschke, C.I.</creatorcontrib><description>Automated nodule classification systems determine a model based on features extracted from documented databases of nodules. These databases cover a large size range and have an unequal distribution of malignant and benign nodules, leading to a high correlation between malignancy and size. For two recent studies in the literature, much of the reported performance of the system may be derived from size based on analysis of their size distributions. We performed experiments to determine the effect of unequal size distribution on a nodule classification system's performance. Preliminary results indicate that the performance across the entire dataset (a sensitivity/specificity of 0.85/0.80) does not generalize to a subset of nodules (0.50/0.80), but performance can be improved by specifically training on that subset (0.60/0.80). Additional testing with larger datasets needs to be performed, but results reported in this area are overly optimistic.</description><identifier>ISSN: 1945-7928</identifier><identifier>ISBN: 1424406714</identifier><identifier>ISBN: 9781424406715</identifier><identifier>EISSN: 1945-8452</identifier><identifier>EISBN: 9781424406722</identifier><identifier>EISBN: 1424406722</identifier><identifier>DOI: 10.1109/ISBI.2007.357085</identifier><language>eng</language><subject>Biomedical engineering ; Cancer ; Computed tomography ; Educational institutions ; Feature extraction ; Industrial engineering ; Lesions ; Operations research ; Sensitivity and specificity ; Spatial databases</subject><ispartof>2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2007, p.1248-1251</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/4193519$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2056,27923,54553,54918,54930</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/4193519$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Jirapatnakul, A.C.</creatorcontrib><creatorcontrib>Reeves, A.P.</creatorcontrib><creatorcontrib>Apanasovich, T.V.</creatorcontrib><creatorcontrib>Biancardi, A.M.</creatorcontrib><creatorcontrib>Yankelevitz, D.F.</creatorcontrib><creatorcontrib>Henschke, C.I.</creatorcontrib><title>PULMONARY NODULE CLASSIFICATION: SIZE DISTRIBUTION ISSUES</title><title>2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro</title><addtitle>ISBI</addtitle><description>Automated nodule classification systems determine a model based on features extracted from documented databases of nodules. These databases cover a large size range and have an unequal distribution of malignant and benign nodules, leading to a high correlation between malignancy and size. For two recent studies in the literature, much of the reported performance of the system may be derived from size based on analysis of their size distributions. We performed experiments to determine the effect of unequal size distribution on a nodule classification system's performance. Preliminary results indicate that the performance across the entire dataset (a sensitivity/specificity of 0.85/0.80) does not generalize to a subset of nodules (0.50/0.80), but performance can be improved by specifically training on that subset (0.60/0.80). Additional testing with larger datasets needs to be performed, but results reported in this area are overly optimistic.</description><subject>Biomedical engineering</subject><subject>Cancer</subject><subject>Computed tomography</subject><subject>Educational institutions</subject><subject>Feature extraction</subject><subject>Industrial engineering</subject><subject>Lesions</subject><subject>Operations research</subject><subject>Sensitivity and specificity</subject><subject>Spatial databases</subject><issn>1945-7928</issn><issn>1945-8452</issn><isbn>1424406714</isbn><isbn>9781424406715</isbn><isbn>9781424406722</isbn><isbn>1424406722</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2007</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNo1jE9LxDAUxOM_cF17F7z0C7QmL3lNn7dut6uB2sqmPehlabcJVBRk68Vvb8V1YBiYHzOM3QgeC8HpztiViYFzHUvUPMUTFpBOhQKleKIBTtlCkMIoVQhn7OofCHV-BJogvWTBNL3xWZJkgrhg9NyWT3WVbV_Cql63ZRHmZWat2Zg8a0xd3YfWvBbh2thma1btbxUaa9vCXrML371PLjjmkrWboskfo7J-mMdlNAqNX1HPAUgDdeATTKSUzve0R5KkXEJ-4IkfUPcAOu1cj-R6LwZCgh682qcol-z273d0zu0-D-NHd_jeKUESZ_8A4DpF6Q</recordid><startdate>200704</startdate><enddate>200704</enddate><creator>Jirapatnakul, A.C.</creator><creator>Reeves, A.P.</creator><creator>Apanasovich, T.V.</creator><creator>Biancardi, A.M.</creator><creator>Yankelevitz, D.F.</creator><creator>Henschke, C.I.</creator><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>200704</creationdate><title>PULMONARY NODULE CLASSIFICATION: SIZE DISTRIBUTION ISSUES</title><author>Jirapatnakul, A.C. ; Reeves, A.P. ; Apanasovich, T.V. ; Biancardi, A.M. ; Yankelevitz, D.F. ; Henschke, C.I.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-b0229729a2f656333efb9c59394e69fd06fd57b2278aeb59ebf1d9592b2f4c853</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2007</creationdate><topic>Biomedical engineering</topic><topic>Cancer</topic><topic>Computed tomography</topic><topic>Educational institutions</topic><topic>Feature extraction</topic><topic>Industrial engineering</topic><topic>Lesions</topic><topic>Operations research</topic><topic>Sensitivity and specificity</topic><topic>Spatial databases</topic><toplevel>online_resources</toplevel><creatorcontrib>Jirapatnakul, A.C.</creatorcontrib><creatorcontrib>Reeves, A.P.</creatorcontrib><creatorcontrib>Apanasovich, T.V.</creatorcontrib><creatorcontrib>Biancardi, A.M.</creatorcontrib><creatorcontrib>Yankelevitz, D.F.</creatorcontrib><creatorcontrib>Henschke, C.I.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Xplore</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Jirapatnakul, A.C.</au><au>Reeves, A.P.</au><au>Apanasovich, T.V.</au><au>Biancardi, A.M.</au><au>Yankelevitz, D.F.</au><au>Henschke, C.I.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>PULMONARY NODULE CLASSIFICATION: SIZE DISTRIBUTION ISSUES</atitle><btitle>2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro</btitle><stitle>ISBI</stitle><date>2007-04</date><risdate>2007</risdate><spage>1248</spage><epage>1251</epage><pages>1248-1251</pages><issn>1945-7928</issn><eissn>1945-8452</eissn><isbn>1424406714</isbn><isbn>9781424406715</isbn><eisbn>9781424406722</eisbn><eisbn>1424406722</eisbn><abstract>Automated nodule classification systems determine a model based on features extracted from documented databases of nodules. These databases cover a large size range and have an unequal distribution of malignant and benign nodules, leading to a high correlation between malignancy and size. For two recent studies in the literature, much of the reported performance of the system may be derived from size based on analysis of their size distributions. We performed experiments to determine the effect of unequal size distribution on a nodule classification system's performance. Preliminary results indicate that the performance across the entire dataset (a sensitivity/specificity of 0.85/0.80) does not generalize to a subset of nodules (0.50/0.80), but performance can be improved by specifically training on that subset (0.60/0.80). Additional testing with larger datasets needs to be performed, but results reported in this area are overly optimistic.</abstract><doi>10.1109/ISBI.2007.357085</doi><tpages>4</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1945-7928 |
| ispartof | 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2007, p.1248-1251 |
| issn | 1945-7928 1945-8452 |
| language | eng |
| recordid | cdi_ieee_primary_4193519 |
| source | IEEE Xplore All Conference Series |
| subjects | Biomedical engineering Cancer Computed tomography Educational institutions Feature extraction Industrial engineering Lesions Operations research Sensitivity and specificity Spatial databases |
| title | PULMONARY NODULE CLASSIFICATION: SIZE DISTRIBUTION ISSUES |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-14T01%3A50%3A17IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=PULMONARY%20NODULE%20CLASSIFICATION:%20SIZE%20DISTRIBUTION%20ISSUES&rft.btitle=2007%204th%20IEEE%20International%20Symposium%20on%20Biomedical%20Imaging:%20From%20Nano%20to%20Macro&rft.au=Jirapatnakul,%20A.C.&rft.date=2007-04&rft.spage=1248&rft.epage=1251&rft.pages=1248-1251&rft.issn=1945-7928&rft.eissn=1945-8452&rft.isbn=1424406714&rft.isbn_list=9781424406715&rft_id=info:doi/10.1109/ISBI.2007.357085&rft.eisbn=9781424406722&rft.eisbn_list=1424406722&rft_dat=%3Cieee_CHZPO%3E4193519%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i175t-b0229729a2f656333efb9c59394e69fd06fd57b2278aeb59ebf1d9592b2f4c853%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=4193519&rfr_iscdi=true |