Exploring the variability of radiomic features of lung cancer lesions on unenhanced and contrast-enhanced chest CT imaging
•The behavior of radiomic features on unenhanced and contrast-enhanced chest CT imaging is evaluated.•Several radiomic features were affected by high variability when moving from unenhanced to contrast-enhanced CT imaging.•A subset of four stable features was isolated that produces the same tumor le...
Gespeichert in:
| Veröffentlicht in: | Physica medica 2021-02, Vol.82, p.321-331 |
|---|---|
| Hauptverfasser: | , , , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 331 |
|---|---|
| container_issue | |
| container_start_page | 321 |
| container_title | Physica medica |
| container_volume | 82 |
| creator | Tamponi, Matteo Crivelli, Paola Montella, Rino Sanna, Fabrizio Gabriele, Domenico Poggiu, Angela Sanna, Enrico Marini, Piergiorgio Meloni, Giovanni B Sverzellati, Nicola Conti, Maurizio |
| description | •The behavior of radiomic features on unenhanced and contrast-enhanced chest CT imaging is evaluated.•Several radiomic features were affected by high variability when moving from unenhanced to contrast-enhanced CT imaging.•A subset of four stable features was isolated that produces the same tumor lesion partition on both types of images.•The Gini’s coefficient proved effective to outline the discrimination power of radiomic features on both types of images.
The aim of this methods work is to explore the different behavior of radiomic features resulting by using or not the contrast medium in chest CT imaging of non-small cell lung cancer.
Chest CT scans, unenhanced and contrast-enhanced, of 17 patients were selected from images collected as part of the staging process. The major T1-T3 lesion was contoured through a semi-automatic approach. These lesions formed the lesion phantoms to study features behavior. The stability of 94 features of the 3D-Slicer package Radiomics was analyzed. Feature discrimination power was quantified by means of Gini's coefficient. Correlation between distance matrices was evaluated through Mantel statistic. Heatmap, cluster and silhouette plots were applied to find well-structured partitions of lesions.
The Gini's coefficient evidenced a low discrimination power, |
| doi_str_mv | 10.1016/j.ejmp.2021.02.014 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2501848755</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S1120179721001022</els_id><sourcerecordid>2501848755</sourcerecordid><originalsourceid>FETCH-LOGICAL-c356t-27ad0279106dfe26e5c0375fa27f1a7aa93270c8631037463cf0f2f423b40acb3</originalsourceid><addsrcrecordid>eNp9kE1r3DAQhkVJadK0f6CHomMudkcj29qFXsqy_YBALyn0JrTyKKvFljaSHZL--shskmNPEg_vjF49jH0SUAsQ3ZdDTYfxWCOgqAFrEM0bdiEUNpVYi79n5S4QKqHW6py9z_kAIBHb9h07l1Jh4eKC_ds-HIeYfLjl0574vUne7Pzgp0ceHU-m93H0ljsy05woL3CYS9iaYCnxgbKPoeDA50Bhv9Cem9BzG8OUTJ6qV2r3lCe-ueF-NLflwQ_srTNDpo_P5yX78317s_lZXf_-8Wvz7bqysu2mCpXpAUtZ6HpH2FFrQarWGVROGGXMWqICu-qkKLzppHXg0DUodw0Yu5OX7Oq095ji3Vw66NFnS8NgAsU5a2xBrJqVatsSxVPUpphzIqePqbRNj1qAXpzrg16c68W5BtTFeRn6_Lx_3o3Uv468SC6Br6cAlV_ee0o6W0-LE5_ITrqP_n_7nwA6GJP8</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2501848755</pqid></control><display><type>article</type><title>Exploring the variability of radiomic features of lung cancer lesions on unenhanced and contrast-enhanced chest CT imaging</title><source>Elsevier ScienceDirect Journals</source><creator>Tamponi, Matteo ; Crivelli, Paola ; Montella, Rino ; Sanna, Fabrizio ; Gabriele, Domenico ; Poggiu, Angela ; Sanna, Enrico ; Marini, Piergiorgio ; Meloni, Giovanni B ; Sverzellati, Nicola ; Conti, Maurizio</creator><creatorcontrib>Tamponi, Matteo ; Crivelli, Paola ; Montella, Rino ; Sanna, Fabrizio ; Gabriele, Domenico ; Poggiu, Angela ; Sanna, Enrico ; Marini, Piergiorgio ; Meloni, Giovanni B ; Sverzellati, Nicola ; Conti, Maurizio</creatorcontrib><description>•The behavior of radiomic features on unenhanced and contrast-enhanced chest CT imaging is evaluated.•Several radiomic features were affected by high variability when moving from unenhanced to contrast-enhanced CT imaging.•A subset of four stable features was isolated that produces the same tumor lesion partition on both types of images.•The Gini’s coefficient proved effective to outline the discrimination power of radiomic features on both types of images.
The aim of this methods work is to explore the different behavior of radiomic features resulting by using or not the contrast medium in chest CT imaging of non-small cell lung cancer.
Chest CT scans, unenhanced and contrast-enhanced, of 17 patients were selected from images collected as part of the staging process. The major T1-T3 lesion was contoured through a semi-automatic approach. These lesions formed the lesion phantoms to study features behavior. The stability of 94 features of the 3D-Slicer package Radiomics was analyzed. Feature discrimination power was quantified by means of Gini's coefficient. Correlation between distance matrices was evaluated through Mantel statistic. Heatmap, cluster and silhouette plots were applied to find well-structured partitions of lesions.
The Gini's coefficient evidenced a low discrimination power, <0.05, for four features and a large discrimination power, around 0.8, for five features. About 90% of features was affected by the contrast medium, masking tumor lesions variability; thirteen features only were found stable. On 8178 combinations of stable features, only one group of four features produced the same partition of lesions with the silhouette width greater than 0.51, both on unenhanced and contrast-enhanced images.
Gini’s coefficient highlighted the features discrimination power in both CT series. Many features were sensitive to the use of the contrast medium, masking the lesions intrinsic variability. Four stable features produced, on both series, the same partition of cancer lesions with reasonable structure; this may merit being objects of further validation studies and interpretative investigations.</description><identifier>ISSN: 1120-1797</identifier><identifier>EISSN: 1724-191X</identifier><identifier>DOI: 10.1016/j.ejmp.2021.02.014</identifier><identifier>PMID: 33721791</identifier><language>eng</language><publisher>Italy: Elsevier Ltd</publisher><subject>Contrast medium ; CT imaging ; Features stability ; Gini’s coefficient and Mackin’s index ; Lung cancer ; Radiomics</subject><ispartof>Physica medica, 2021-02, Vol.82, p.321-331</ispartof><rights>2021 Associazione Italiana di Fisica Medica</rights><rights>Copyright © 2021 Associazione Italiana di Fisica Medica. Published by Elsevier Ltd. All rights reserved.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c356t-27ad0279106dfe26e5c0375fa27f1a7aa93270c8631037463cf0f2f423b40acb3</citedby><cites>FETCH-LOGICAL-c356t-27ad0279106dfe26e5c0375fa27f1a7aa93270c8631037463cf0f2f423b40acb3</cites><orcidid>0000-0002-9376-6181 ; 0000-0002-3700-086X</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.sciencedirect.com/science/article/pii/S1120179721001022$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,776,780,3537,27901,27902,65306</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/33721791$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Tamponi, Matteo</creatorcontrib><creatorcontrib>Crivelli, Paola</creatorcontrib><creatorcontrib>Montella, Rino</creatorcontrib><creatorcontrib>Sanna, Fabrizio</creatorcontrib><creatorcontrib>Gabriele, Domenico</creatorcontrib><creatorcontrib>Poggiu, Angela</creatorcontrib><creatorcontrib>Sanna, Enrico</creatorcontrib><creatorcontrib>Marini, Piergiorgio</creatorcontrib><creatorcontrib>Meloni, Giovanni B</creatorcontrib><creatorcontrib>Sverzellati, Nicola</creatorcontrib><creatorcontrib>Conti, Maurizio</creatorcontrib><title>Exploring the variability of radiomic features of lung cancer lesions on unenhanced and contrast-enhanced chest CT imaging</title><title>Physica medica</title><addtitle>Phys Med</addtitle><description>•The behavior of radiomic features on unenhanced and contrast-enhanced chest CT imaging is evaluated.•Several radiomic features were affected by high variability when moving from unenhanced to contrast-enhanced CT imaging.•A subset of four stable features was isolated that produces the same tumor lesion partition on both types of images.•The Gini’s coefficient proved effective to outline the discrimination power of radiomic features on both types of images.
The aim of this methods work is to explore the different behavior of radiomic features resulting by using or not the contrast medium in chest CT imaging of non-small cell lung cancer.
Chest CT scans, unenhanced and contrast-enhanced, of 17 patients were selected from images collected as part of the staging process. The major T1-T3 lesion was contoured through a semi-automatic approach. These lesions formed the lesion phantoms to study features behavior. The stability of 94 features of the 3D-Slicer package Radiomics was analyzed. Feature discrimination power was quantified by means of Gini's coefficient. Correlation between distance matrices was evaluated through Mantel statistic. Heatmap, cluster and silhouette plots were applied to find well-structured partitions of lesions.
The Gini's coefficient evidenced a low discrimination power, <0.05, for four features and a large discrimination power, around 0.8, for five features. About 90% of features was affected by the contrast medium, masking tumor lesions variability; thirteen features only were found stable. On 8178 combinations of stable features, only one group of four features produced the same partition of lesions with the silhouette width greater than 0.51, both on unenhanced and contrast-enhanced images.
Gini’s coefficient highlighted the features discrimination power in both CT series. Many features were sensitive to the use of the contrast medium, masking the lesions intrinsic variability. Four stable features produced, on both series, the same partition of cancer lesions with reasonable structure; this may merit being objects of further validation studies and interpretative investigations.</description><subject>Contrast medium</subject><subject>CT imaging</subject><subject>Features stability</subject><subject>Gini’s coefficient and Mackin’s index</subject><subject>Lung cancer</subject><subject>Radiomics</subject><issn>1120-1797</issn><issn>1724-191X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><recordid>eNp9kE1r3DAQhkVJadK0f6CHomMudkcj29qFXsqy_YBALyn0JrTyKKvFljaSHZL--shskmNPEg_vjF49jH0SUAsQ3ZdDTYfxWCOgqAFrEM0bdiEUNpVYi79n5S4QKqHW6py9z_kAIBHb9h07l1Jh4eKC_ds-HIeYfLjl0574vUne7Pzgp0ceHU-m93H0ljsy05woL3CYS9iaYCnxgbKPoeDA50Bhv9Cem9BzG8OUTJ6qV2r3lCe-ueF-NLflwQ_srTNDpo_P5yX78317s_lZXf_-8Wvz7bqysu2mCpXpAUtZ6HpH2FFrQarWGVROGGXMWqICu-qkKLzppHXg0DUodw0Yu5OX7Oq095ji3Vw66NFnS8NgAsU5a2xBrJqVatsSxVPUpphzIqePqbRNj1qAXpzrg16c68W5BtTFeRn6_Lx_3o3Uv468SC6Br6cAlV_ee0o6W0-LE5_ITrqP_n_7nwA6GJP8</recordid><startdate>202102</startdate><enddate>202102</enddate><creator>Tamponi, Matteo</creator><creator>Crivelli, Paola</creator><creator>Montella, Rino</creator><creator>Sanna, Fabrizio</creator><creator>Gabriele, Domenico</creator><creator>Poggiu, Angela</creator><creator>Sanna, Enrico</creator><creator>Marini, Piergiorgio</creator><creator>Meloni, Giovanni B</creator><creator>Sverzellati, Nicola</creator><creator>Conti, Maurizio</creator><general>Elsevier Ltd</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0002-9376-6181</orcidid><orcidid>https://orcid.org/0000-0002-3700-086X</orcidid></search><sort><creationdate>202102</creationdate><title>Exploring the variability of radiomic features of lung cancer lesions on unenhanced and contrast-enhanced chest CT imaging</title><author>Tamponi, Matteo ; Crivelli, Paola ; Montella, Rino ; Sanna, Fabrizio ; Gabriele, Domenico ; Poggiu, Angela ; Sanna, Enrico ; Marini, Piergiorgio ; Meloni, Giovanni B ; Sverzellati, Nicola ; Conti, Maurizio</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c356t-27ad0279106dfe26e5c0375fa27f1a7aa93270c8631037463cf0f2f423b40acb3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Contrast medium</topic><topic>CT imaging</topic><topic>Features stability</topic><topic>Gini’s coefficient and Mackin’s index</topic><topic>Lung cancer</topic><topic>Radiomics</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Tamponi, Matteo</creatorcontrib><creatorcontrib>Crivelli, Paola</creatorcontrib><creatorcontrib>Montella, Rino</creatorcontrib><creatorcontrib>Sanna, Fabrizio</creatorcontrib><creatorcontrib>Gabriele, Domenico</creatorcontrib><creatorcontrib>Poggiu, Angela</creatorcontrib><creatorcontrib>Sanna, Enrico</creatorcontrib><creatorcontrib>Marini, Piergiorgio</creatorcontrib><creatorcontrib>Meloni, Giovanni B</creatorcontrib><creatorcontrib>Sverzellati, Nicola</creatorcontrib><creatorcontrib>Conti, Maurizio</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>Physica medica</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Tamponi, Matteo</au><au>Crivelli, Paola</au><au>Montella, Rino</au><au>Sanna, Fabrizio</au><au>Gabriele, Domenico</au><au>Poggiu, Angela</au><au>Sanna, Enrico</au><au>Marini, Piergiorgio</au><au>Meloni, Giovanni B</au><au>Sverzellati, Nicola</au><au>Conti, Maurizio</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Exploring the variability of radiomic features of lung cancer lesions on unenhanced and contrast-enhanced chest CT imaging</atitle><jtitle>Physica medica</jtitle><addtitle>Phys Med</addtitle><date>2021-02</date><risdate>2021</risdate><volume>82</volume><spage>321</spage><epage>331</epage><pages>321-331</pages><issn>1120-1797</issn><eissn>1724-191X</eissn><abstract>•The behavior of radiomic features on unenhanced and contrast-enhanced chest CT imaging is evaluated.•Several radiomic features were affected by high variability when moving from unenhanced to contrast-enhanced CT imaging.•A subset of four stable features was isolated that produces the same tumor lesion partition on both types of images.•The Gini’s coefficient proved effective to outline the discrimination power of radiomic features on both types of images.
The aim of this methods work is to explore the different behavior of radiomic features resulting by using or not the contrast medium in chest CT imaging of non-small cell lung cancer.
Chest CT scans, unenhanced and contrast-enhanced, of 17 patients were selected from images collected as part of the staging process. The major T1-T3 lesion was contoured through a semi-automatic approach. These lesions formed the lesion phantoms to study features behavior. The stability of 94 features of the 3D-Slicer package Radiomics was analyzed. Feature discrimination power was quantified by means of Gini's coefficient. Correlation between distance matrices was evaluated through Mantel statistic. Heatmap, cluster and silhouette plots were applied to find well-structured partitions of lesions.
The Gini's coefficient evidenced a low discrimination power, <0.05, for four features and a large discrimination power, around 0.8, for five features. About 90% of features was affected by the contrast medium, masking tumor lesions variability; thirteen features only were found stable. On 8178 combinations of stable features, only one group of four features produced the same partition of lesions with the silhouette width greater than 0.51, both on unenhanced and contrast-enhanced images.
Gini’s coefficient highlighted the features discrimination power in both CT series. Many features were sensitive to the use of the contrast medium, masking the lesions intrinsic variability. Four stable features produced, on both series, the same partition of cancer lesions with reasonable structure; this may merit being objects of further validation studies and interpretative investigations.</abstract><cop>Italy</cop><pub>Elsevier Ltd</pub><pmid>33721791</pmid><doi>10.1016/j.ejmp.2021.02.014</doi><tpages>11</tpages><orcidid>https://orcid.org/0000-0002-9376-6181</orcidid><orcidid>https://orcid.org/0000-0002-3700-086X</orcidid></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1120-1797 |
| ispartof | Physica medica, 2021-02, Vol.82, p.321-331 |
| issn | 1120-1797 1724-191X |
| language | eng |
| recordid | cdi_proquest_miscellaneous_2501848755 |
| source | Elsevier ScienceDirect Journals |
| subjects | Contrast medium CT imaging Features stability Gini’s coefficient and Mackin’s index Lung cancer Radiomics |
| title | Exploring the variability of radiomic features of lung cancer lesions on unenhanced and contrast-enhanced chest CT imaging |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-05T11%3A08%3A41IST&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=Exploring%20the%20variability%20of%20radiomic%20features%20of%20lung%20cancer%20lesions%20on%20unenhanced%20and%20contrast-enhanced%20chest%20CT%20imaging&rft.jtitle=Physica%20medica&rft.au=Tamponi,%20Matteo&rft.date=2021-02&rft.volume=82&rft.spage=321&rft.epage=331&rft.pages=321-331&rft.issn=1120-1797&rft.eissn=1724-191X&rft_id=info:doi/10.1016/j.ejmp.2021.02.014&rft_dat=%3Cproquest_cross%3E2501848755%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=2501848755&rft_id=info:pmid/33721791&rft_els_id=S1120179721001022&rfr_iscdi=true |