Loading…
A multicentric study of radiomics and artificial intelligence analysis on contrast-enhanced mammography to identify different histotypes of breast cancer
Objective To evaluate the performance of radiomic analysis on contrast-enhanced mammography images to identify different histotypes of breast cancer mainly in order to predict grading, to identify hormone receptors, to discriminate human epidermal growth factor receptor 2 (HER2) and to identify lumi...
Saved in:
Published in: | Radiologia medica 2024-06, Vol.129 (6), p.864-878 |
---|---|
Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , |
Format: | Article |
Language: | English |
Subjects: | |
Citations: | Items that this one cites |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | |
---|---|
cites | cdi_FETCH-LOGICAL-c326t-be3f4630baf44e626bd6f5e79844983280f5cad52c4b9d0e16f4fdc4e137d7253 |
container_end_page | 878 |
container_issue | 6 |
container_start_page | 864 |
container_title | Radiologia medica |
container_volume | 129 |
creator | Petrillo, Antonella Fusco, Roberta Petrosino, Teresa Vallone, Paolo Granata, Vincenza Rubulotta, Maria Rosaria Pariante, Paolo Raiano, Nicola Scognamiglio, Giosuè Fanizzi, Annarita Massafra, Raffaella Lafranceschina, Miria La Forgia, Daniele Greco, Laura Ferranti, Francesca Romana De Soccio, Valeria Vidiri, Antonello Botta, Francesca Dominelli, Valeria Cassano, Enrico Sorgente, Eugenio Pecori, Biagio Cerciello, Vincenzo Boldrini, Luca |
description | Objective
To evaluate the performance of radiomic analysis on contrast-enhanced mammography images to identify different histotypes of breast cancer mainly in order to predict grading, to identify hormone receptors, to discriminate human epidermal growth factor receptor 2 (HER2) and to identify luminal histotype of the breast cancer.
Methods
From four Italian centers were recruited 180 malignant lesions and 68 benign lesions. However, only the malignant lesions were considered for the analysis. All patients underwent contrast-enhanced mammography in cranium caudal (CC) and medium lateral oblique (MLO) view. Considering histological findings as the ground truth, four outcomes were considered: (1) G1 + G2 vs. G3; (2) HER2 + vs. HER2 − ; (3) HR + vs. HR − ; and (4) non-luminal vs. luminal A or HR + /HER2− and luminal B or HR + /HER2 + . For multivariate analysis feature selection, balancing techniques and patter recognition approaches were considered.
Results
The univariate findings showed that the diagnostic performance is low for each outcome, while the results of the multivariate analysis showed that better performances can be obtained. In the HER2 + detection, the best performance (73% of accuracy and AUC = 0.77) was obtained using a linear regression model (LRM) with 12 features extracted by MLO view. In the HR + detection, the best performance (77% of accuracy and AUC = 0.80) was obtained using a LRM with 14 features extracted by MLO view. In grading classification, the best performance was obtained by a decision tree trained with three predictors extracted by MLO view reaching an accuracy of 82% on validation set. In the luminal versus non-luminal histotype classification, the best performance was obtained by a bagged tree trained with 15 predictors extracted by CC view reaching an accuracy of 94% on validation set.
Conclusions
The results suggest that radiomics analysis can be effectively applied to design a tool to support physician decision making in breast cancer classification. In particular, the classification of luminal versus non-luminal histotypes can be performed with high accuracy. |
doi_str_mv | 10.1007/s11547-024-01817-8 |
format | article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_3056669566</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3067417106</sourcerecordid><originalsourceid>FETCH-LOGICAL-c326t-be3f4630baf44e626bd6f5e79844983280f5cad52c4b9d0e16f4fdc4e137d7253</originalsourceid><addsrcrecordid>eNp9kc2OFSEQhYnROOPoC7gwJG7ctEJDQ_dyMhl_kknc6JrQUNzLpLu5UvSiH8W3lfaOP3HhBqjUd06lOIS85OwtZ0y_Q847qRvWyobxnuumf0Qued-qRg29ePzX-4I8Q7xnTDLOhqfkQvS6q1J9Sb5f03mdSnSwlBwdxbL6jaZAs_UxzdEhtYunNpcYoot2onEpME3xAIuD2rPThhFpWqhL1cJiaWA52tr0dLbznA7Zno4bLYlGX4fEsFEfQ4BcC3qMWFLZToD7zDFD1VO3q_Nz8iTYCeHFw31Fvr6__XLzsbn7_OHTzfVd40SrSjOCCFIJNtogJahWjV6FDvTQS1k3b3sWOmd91zo5Dp4BV0EG7yRwob1uO3FF3px9Tzl9WwGLmSO6uqJdIK1oBOuUUkM9Kvr6H_Q-rbl-wU4pLbnmbKfaM-VyQswQzCnH2ebNcGb24Mw5OFODMz-DM30VvXqwXscZ_G_Jr6QqIM4A1tZygPxn9n9sfwDhKadS</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3067417106</pqid></control><display><type>article</type><title>A multicentric study of radiomics and artificial intelligence analysis on contrast-enhanced mammography to identify different histotypes of breast cancer</title><source>Springer Link</source><creator>Petrillo, Antonella ; Fusco, Roberta ; Petrosino, Teresa ; Vallone, Paolo ; Granata, Vincenza ; Rubulotta, Maria Rosaria ; Pariante, Paolo ; Raiano, Nicola ; Scognamiglio, Giosuè ; Fanizzi, Annarita ; Massafra, Raffaella ; Lafranceschina, Miria ; La Forgia, Daniele ; Greco, Laura ; Ferranti, Francesca Romana ; De Soccio, Valeria ; Vidiri, Antonello ; Botta, Francesca ; Dominelli, Valeria ; Cassano, Enrico ; Sorgente, Eugenio ; Pecori, Biagio ; Cerciello, Vincenzo ; Boldrini, Luca</creator><creatorcontrib>Petrillo, Antonella ; Fusco, Roberta ; Petrosino, Teresa ; Vallone, Paolo ; Granata, Vincenza ; Rubulotta, Maria Rosaria ; Pariante, Paolo ; Raiano, Nicola ; Scognamiglio, Giosuè ; Fanizzi, Annarita ; Massafra, Raffaella ; Lafranceschina, Miria ; La Forgia, Daniele ; Greco, Laura ; Ferranti, Francesca Romana ; De Soccio, Valeria ; Vidiri, Antonello ; Botta, Francesca ; Dominelli, Valeria ; Cassano, Enrico ; Sorgente, Eugenio ; Pecori, Biagio ; Cerciello, Vincenzo ; Boldrini, Luca</creatorcontrib><description>Objective
To evaluate the performance of radiomic analysis on contrast-enhanced mammography images to identify different histotypes of breast cancer mainly in order to predict grading, to identify hormone receptors, to discriminate human epidermal growth factor receptor 2 (HER2) and to identify luminal histotype of the breast cancer.
Methods
From four Italian centers were recruited 180 malignant lesions and 68 benign lesions. However, only the malignant lesions were considered for the analysis. All patients underwent contrast-enhanced mammography in cranium caudal (CC) and medium lateral oblique (MLO) view. Considering histological findings as the ground truth, four outcomes were considered: (1) G1 + G2 vs. G3; (2) HER2 + vs. HER2 − ; (3) HR + vs. HR − ; and (4) non-luminal vs. luminal A or HR + /HER2− and luminal B or HR + /HER2 + . For multivariate analysis feature selection, balancing techniques and patter recognition approaches were considered.
Results
The univariate findings showed that the diagnostic performance is low for each outcome, while the results of the multivariate analysis showed that better performances can be obtained. In the HER2 + detection, the best performance (73% of accuracy and AUC = 0.77) was obtained using a linear regression model (LRM) with 12 features extracted by MLO view. In the HR + detection, the best performance (77% of accuracy and AUC = 0.80) was obtained using a LRM with 14 features extracted by MLO view. In grading classification, the best performance was obtained by a decision tree trained with three predictors extracted by MLO view reaching an accuracy of 82% on validation set. In the luminal versus non-luminal histotype classification, the best performance was obtained by a bagged tree trained with 15 predictors extracted by CC view reaching an accuracy of 94% on validation set.
Conclusions
The results suggest that radiomics analysis can be effectively applied to design a tool to support physician decision making in breast cancer classification. In particular, the classification of luminal versus non-luminal histotypes can be performed with high accuracy.</description><identifier>ISSN: 1826-6983</identifier><identifier>ISSN: 0033-8362</identifier><identifier>EISSN: 1826-6983</identifier><identifier>DOI: 10.1007/s11547-024-01817-8</identifier><identifier>PMID: 38755477</identifier><language>eng</language><publisher>Milan: Springer Milan</publisher><subject>Accuracy ; Adult ; Aged ; Artificial Intelligence ; Breast cancer ; Breast Neoplasms - diagnostic imaging ; Breast Neoplasms - pathology ; Breast Radiology ; Classification ; Contrast Media ; Cranium ; Decision trees ; Diagnostic Radiology ; Female ; Growth factors ; Humans ; Image contrast ; Image enhancement ; Imaging ; Interventional Radiology ; Italy ; Lesions ; Mammography ; Mammography - methods ; Medicine ; Medicine & Public Health ; Middle Aged ; Multivariate analysis ; Neoplasm Grading ; Neuroradiology ; Performance evaluation ; Radiographic Image Interpretation, Computer-Assisted - methods ; Radiology ; Radiomics ; Receptor, ErbB-2 ; Receptors ; Regression models ; Sensitivity and Specificity ; Ultrasound</subject><ispartof>Radiologia medica, 2024-06, Vol.129 (6), p.864-878</ispartof><rights>Italian Society of Medical Radiology 2024. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.</rights><rights>2024. Italian Society of Medical Radiology.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c326t-be3f4630baf44e626bd6f5e79844983280f5cad52c4b9d0e16f4fdc4e137d7253</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/38755477$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Petrillo, Antonella</creatorcontrib><creatorcontrib>Fusco, Roberta</creatorcontrib><creatorcontrib>Petrosino, Teresa</creatorcontrib><creatorcontrib>Vallone, Paolo</creatorcontrib><creatorcontrib>Granata, Vincenza</creatorcontrib><creatorcontrib>Rubulotta, Maria Rosaria</creatorcontrib><creatorcontrib>Pariante, Paolo</creatorcontrib><creatorcontrib>Raiano, Nicola</creatorcontrib><creatorcontrib>Scognamiglio, Giosuè</creatorcontrib><creatorcontrib>Fanizzi, Annarita</creatorcontrib><creatorcontrib>Massafra, Raffaella</creatorcontrib><creatorcontrib>Lafranceschina, Miria</creatorcontrib><creatorcontrib>La Forgia, Daniele</creatorcontrib><creatorcontrib>Greco, Laura</creatorcontrib><creatorcontrib>Ferranti, Francesca Romana</creatorcontrib><creatorcontrib>De Soccio, Valeria</creatorcontrib><creatorcontrib>Vidiri, Antonello</creatorcontrib><creatorcontrib>Botta, Francesca</creatorcontrib><creatorcontrib>Dominelli, Valeria</creatorcontrib><creatorcontrib>Cassano, Enrico</creatorcontrib><creatorcontrib>Sorgente, Eugenio</creatorcontrib><creatorcontrib>Pecori, Biagio</creatorcontrib><creatorcontrib>Cerciello, Vincenzo</creatorcontrib><creatorcontrib>Boldrini, Luca</creatorcontrib><title>A multicentric study of radiomics and artificial intelligence analysis on contrast-enhanced mammography to identify different histotypes of breast cancer</title><title>Radiologia medica</title><addtitle>Radiol med</addtitle><addtitle>Radiol Med</addtitle><description>Objective
To evaluate the performance of radiomic analysis on contrast-enhanced mammography images to identify different histotypes of breast cancer mainly in order to predict grading, to identify hormone receptors, to discriminate human epidermal growth factor receptor 2 (HER2) and to identify luminal histotype of the breast cancer.
Methods
From four Italian centers were recruited 180 malignant lesions and 68 benign lesions. However, only the malignant lesions were considered for the analysis. All patients underwent contrast-enhanced mammography in cranium caudal (CC) and medium lateral oblique (MLO) view. Considering histological findings as the ground truth, four outcomes were considered: (1) G1 + G2 vs. G3; (2) HER2 + vs. HER2 − ; (3) HR + vs. HR − ; and (4) non-luminal vs. luminal A or HR + /HER2− and luminal B or HR + /HER2 + . For multivariate analysis feature selection, balancing techniques and patter recognition approaches were considered.
Results
The univariate findings showed that the diagnostic performance is low for each outcome, while the results of the multivariate analysis showed that better performances can be obtained. In the HER2 + detection, the best performance (73% of accuracy and AUC = 0.77) was obtained using a linear regression model (LRM) with 12 features extracted by MLO view. In the HR + detection, the best performance (77% of accuracy and AUC = 0.80) was obtained using a LRM with 14 features extracted by MLO view. In grading classification, the best performance was obtained by a decision tree trained with three predictors extracted by MLO view reaching an accuracy of 82% on validation set. In the luminal versus non-luminal histotype classification, the best performance was obtained by a bagged tree trained with 15 predictors extracted by CC view reaching an accuracy of 94% on validation set.
Conclusions
The results suggest that radiomics analysis can be effectively applied to design a tool to support physician decision making in breast cancer classification. In particular, the classification of luminal versus non-luminal histotypes can be performed with high accuracy.</description><subject>Accuracy</subject><subject>Adult</subject><subject>Aged</subject><subject>Artificial Intelligence</subject><subject>Breast cancer</subject><subject>Breast Neoplasms - diagnostic imaging</subject><subject>Breast Neoplasms - pathology</subject><subject>Breast Radiology</subject><subject>Classification</subject><subject>Contrast Media</subject><subject>Cranium</subject><subject>Decision trees</subject><subject>Diagnostic Radiology</subject><subject>Female</subject><subject>Growth factors</subject><subject>Humans</subject><subject>Image contrast</subject><subject>Image enhancement</subject><subject>Imaging</subject><subject>Interventional Radiology</subject><subject>Italy</subject><subject>Lesions</subject><subject>Mammography</subject><subject>Mammography - methods</subject><subject>Medicine</subject><subject>Medicine & Public Health</subject><subject>Middle Aged</subject><subject>Multivariate analysis</subject><subject>Neoplasm Grading</subject><subject>Neuroradiology</subject><subject>Performance evaluation</subject><subject>Radiographic Image Interpretation, Computer-Assisted - methods</subject><subject>Radiology</subject><subject>Radiomics</subject><subject>Receptor, ErbB-2</subject><subject>Receptors</subject><subject>Regression models</subject><subject>Sensitivity and Specificity</subject><subject>Ultrasound</subject><issn>1826-6983</issn><issn>0033-8362</issn><issn>1826-6983</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNp9kc2OFSEQhYnROOPoC7gwJG7ctEJDQ_dyMhl_kknc6JrQUNzLpLu5UvSiH8W3lfaOP3HhBqjUd06lOIS85OwtZ0y_Q847qRvWyobxnuumf0Qued-qRg29ePzX-4I8Q7xnTDLOhqfkQvS6q1J9Sb5f03mdSnSwlBwdxbL6jaZAs_UxzdEhtYunNpcYoot2onEpME3xAIuD2rPThhFpWqhL1cJiaWA52tr0dLbznA7Zno4bLYlGX4fEsFEfQ4BcC3qMWFLZToD7zDFD1VO3q_Nz8iTYCeHFw31Fvr6__XLzsbn7_OHTzfVd40SrSjOCCFIJNtogJahWjV6FDvTQS1k3b3sWOmd91zo5Dp4BV0EG7yRwob1uO3FF3px9Tzl9WwGLmSO6uqJdIK1oBOuUUkM9Kvr6H_Q-rbl-wU4pLbnmbKfaM-VyQswQzCnH2ebNcGb24Mw5OFODMz-DM30VvXqwXscZ_G_Jr6QqIM4A1tZygPxn9n9sfwDhKadS</recordid><startdate>20240601</startdate><enddate>20240601</enddate><creator>Petrillo, Antonella</creator><creator>Fusco, Roberta</creator><creator>Petrosino, Teresa</creator><creator>Vallone, Paolo</creator><creator>Granata, Vincenza</creator><creator>Rubulotta, Maria Rosaria</creator><creator>Pariante, Paolo</creator><creator>Raiano, Nicola</creator><creator>Scognamiglio, Giosuè</creator><creator>Fanizzi, Annarita</creator><creator>Massafra, Raffaella</creator><creator>Lafranceschina, Miria</creator><creator>La Forgia, Daniele</creator><creator>Greco, Laura</creator><creator>Ferranti, Francesca Romana</creator><creator>De Soccio, Valeria</creator><creator>Vidiri, Antonello</creator><creator>Botta, Francesca</creator><creator>Dominelli, Valeria</creator><creator>Cassano, Enrico</creator><creator>Sorgente, Eugenio</creator><creator>Pecori, Biagio</creator><creator>Cerciello, Vincenzo</creator><creator>Boldrini, Luca</creator><general>Springer Milan</general><general>Springer Nature B.V</general><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>7X8</scope></search><sort><creationdate>20240601</creationdate><title>A multicentric study of radiomics and artificial intelligence analysis on contrast-enhanced mammography to identify different histotypes of breast cancer</title><author>Petrillo, Antonella ; Fusco, Roberta ; Petrosino, Teresa ; Vallone, Paolo ; Granata, Vincenza ; Rubulotta, Maria Rosaria ; Pariante, Paolo ; Raiano, Nicola ; Scognamiglio, Giosuè ; Fanizzi, Annarita ; Massafra, Raffaella ; Lafranceschina, Miria ; La Forgia, Daniele ; Greco, Laura ; Ferranti, Francesca Romana ; De Soccio, Valeria ; Vidiri, Antonello ; Botta, Francesca ; Dominelli, Valeria ; Cassano, Enrico ; Sorgente, Eugenio ; Pecori, Biagio ; Cerciello, Vincenzo ; Boldrini, Luca</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c326t-be3f4630baf44e626bd6f5e79844983280f5cad52c4b9d0e16f4fdc4e137d7253</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Accuracy</topic><topic>Adult</topic><topic>Aged</topic><topic>Artificial Intelligence</topic><topic>Breast cancer</topic><topic>Breast Neoplasms - diagnostic imaging</topic><topic>Breast Neoplasms - pathology</topic><topic>Breast Radiology</topic><topic>Classification</topic><topic>Contrast Media</topic><topic>Cranium</topic><topic>Decision trees</topic><topic>Diagnostic Radiology</topic><topic>Female</topic><topic>Growth factors</topic><topic>Humans</topic><topic>Image contrast</topic><topic>Image enhancement</topic><topic>Imaging</topic><topic>Interventional Radiology</topic><topic>Italy</topic><topic>Lesions</topic><topic>Mammography</topic><topic>Mammography - methods</topic><topic>Medicine</topic><topic>Medicine & Public Health</topic><topic>Middle Aged</topic><topic>Multivariate analysis</topic><topic>Neoplasm Grading</topic><topic>Neuroradiology</topic><topic>Performance evaluation</topic><topic>Radiographic Image Interpretation, Computer-Assisted - methods</topic><topic>Radiology</topic><topic>Radiomics</topic><topic>Receptor, ErbB-2</topic><topic>Receptors</topic><topic>Regression models</topic><topic>Sensitivity and Specificity</topic><topic>Ultrasound</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Petrillo, Antonella</creatorcontrib><creatorcontrib>Fusco, Roberta</creatorcontrib><creatorcontrib>Petrosino, Teresa</creatorcontrib><creatorcontrib>Vallone, Paolo</creatorcontrib><creatorcontrib>Granata, Vincenza</creatorcontrib><creatorcontrib>Rubulotta, Maria Rosaria</creatorcontrib><creatorcontrib>Pariante, Paolo</creatorcontrib><creatorcontrib>Raiano, Nicola</creatorcontrib><creatorcontrib>Scognamiglio, Giosuè</creatorcontrib><creatorcontrib>Fanizzi, Annarita</creatorcontrib><creatorcontrib>Massafra, Raffaella</creatorcontrib><creatorcontrib>Lafranceschina, Miria</creatorcontrib><creatorcontrib>La Forgia, Daniele</creatorcontrib><creatorcontrib>Greco, Laura</creatorcontrib><creatorcontrib>Ferranti, Francesca Romana</creatorcontrib><creatorcontrib>De Soccio, Valeria</creatorcontrib><creatorcontrib>Vidiri, Antonello</creatorcontrib><creatorcontrib>Botta, Francesca</creatorcontrib><creatorcontrib>Dominelli, Valeria</creatorcontrib><creatorcontrib>Cassano, Enrico</creatorcontrib><creatorcontrib>Sorgente, Eugenio</creatorcontrib><creatorcontrib>Pecori, Biagio</creatorcontrib><creatorcontrib>Cerciello, Vincenzo</creatorcontrib><creatorcontrib>Boldrini, Luca</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>Radiologia medica</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Petrillo, Antonella</au><au>Fusco, Roberta</au><au>Petrosino, Teresa</au><au>Vallone, Paolo</au><au>Granata, Vincenza</au><au>Rubulotta, Maria Rosaria</au><au>Pariante, Paolo</au><au>Raiano, Nicola</au><au>Scognamiglio, Giosuè</au><au>Fanizzi, Annarita</au><au>Massafra, Raffaella</au><au>Lafranceschina, Miria</au><au>La Forgia, Daniele</au><au>Greco, Laura</au><au>Ferranti, Francesca Romana</au><au>De Soccio, Valeria</au><au>Vidiri, Antonello</au><au>Botta, Francesca</au><au>Dominelli, Valeria</au><au>Cassano, Enrico</au><au>Sorgente, Eugenio</au><au>Pecori, Biagio</au><au>Cerciello, Vincenzo</au><au>Boldrini, Luca</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A multicentric study of radiomics and artificial intelligence analysis on contrast-enhanced mammography to identify different histotypes of breast cancer</atitle><jtitle>Radiologia medica</jtitle><stitle>Radiol med</stitle><addtitle>Radiol Med</addtitle><date>2024-06-01</date><risdate>2024</risdate><volume>129</volume><issue>6</issue><spage>864</spage><epage>878</epage><pages>864-878</pages><issn>1826-6983</issn><issn>0033-8362</issn><eissn>1826-6983</eissn><abstract>Objective
To evaluate the performance of radiomic analysis on contrast-enhanced mammography images to identify different histotypes of breast cancer mainly in order to predict grading, to identify hormone receptors, to discriminate human epidermal growth factor receptor 2 (HER2) and to identify luminal histotype of the breast cancer.
Methods
From four Italian centers were recruited 180 malignant lesions and 68 benign lesions. However, only the malignant lesions were considered for the analysis. All patients underwent contrast-enhanced mammography in cranium caudal (CC) and medium lateral oblique (MLO) view. Considering histological findings as the ground truth, four outcomes were considered: (1) G1 + G2 vs. G3; (2) HER2 + vs. HER2 − ; (3) HR + vs. HR − ; and (4) non-luminal vs. luminal A or HR + /HER2− and luminal B or HR + /HER2 + . For multivariate analysis feature selection, balancing techniques and patter recognition approaches were considered.
Results
The univariate findings showed that the diagnostic performance is low for each outcome, while the results of the multivariate analysis showed that better performances can be obtained. In the HER2 + detection, the best performance (73% of accuracy and AUC = 0.77) was obtained using a linear regression model (LRM) with 12 features extracted by MLO view. In the HR + detection, the best performance (77% of accuracy and AUC = 0.80) was obtained using a LRM with 14 features extracted by MLO view. In grading classification, the best performance was obtained by a decision tree trained with three predictors extracted by MLO view reaching an accuracy of 82% on validation set. In the luminal versus non-luminal histotype classification, the best performance was obtained by a bagged tree trained with 15 predictors extracted by CC view reaching an accuracy of 94% on validation set.
Conclusions
The results suggest that radiomics analysis can be effectively applied to design a tool to support physician decision making in breast cancer classification. In particular, the classification of luminal versus non-luminal histotypes can be performed with high accuracy.</abstract><cop>Milan</cop><pub>Springer Milan</pub><pmid>38755477</pmid><doi>10.1007/s11547-024-01817-8</doi><tpages>15</tpages></addata></record> |
fulltext | fulltext |
identifier | ISSN: 1826-6983 |
ispartof | Radiologia medica, 2024-06, Vol.129 (6), p.864-878 |
issn | 1826-6983 0033-8362 1826-6983 |
language | eng |
recordid | cdi_proquest_miscellaneous_3056669566 |
source | Springer Link |
subjects | Accuracy Adult Aged Artificial Intelligence Breast cancer Breast Neoplasms - diagnostic imaging Breast Neoplasms - pathology Breast Radiology Classification Contrast Media Cranium Decision trees Diagnostic Radiology Female Growth factors Humans Image contrast Image enhancement Imaging Interventional Radiology Italy Lesions Mammography Mammography - methods Medicine Medicine & Public Health Middle Aged Multivariate analysis Neoplasm Grading Neuroradiology Performance evaluation Radiographic Image Interpretation, Computer-Assisted - methods Radiology Radiomics Receptor, ErbB-2 Receptors Regression models Sensitivity and Specificity Ultrasound |
title | A multicentric study of radiomics and artificial intelligence analysis on contrast-enhanced mammography to identify different histotypes of breast cancer |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T13%3A00%3A17IST&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=A%20multicentric%20study%20of%20radiomics%20and%20artificial%20intelligence%20analysis%20on%20contrast-enhanced%20mammography%20to%20identify%20different%20histotypes%20of%20breast%20cancer&rft.jtitle=Radiologia%20medica&rft.au=Petrillo,%20Antonella&rft.date=2024-06-01&rft.volume=129&rft.issue=6&rft.spage=864&rft.epage=878&rft.pages=864-878&rft.issn=1826-6983&rft.eissn=1826-6983&rft_id=info:doi/10.1007/s11547-024-01817-8&rft_dat=%3Cproquest_cross%3E3067417106%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c326t-be3f4630baf44e626bd6f5e79844983280f5cad52c4b9d0e16f4fdc4e137d7253%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=3067417106&rft_id=info:pmid/38755477&rfr_iscdi=true |