Loading…
Radiomic and Artificial Intelligence Analysis with Textural Metrics Extracted by Contrast-Enhanced Mammography and Dynamic Contrast Magnetic Resonance Imaging to Detect Breast Malignant Lesions
:The purpose of this study was to discriminate between benign and malignant breast lesions through several classifiers using, as predictors, radiomic metrics extracted from CEM and DCE-MRI images. In order to optimize the analysis, balancing and feature selection procedures were performed. : Fifty-f...
Saved in:
Published in: | Current oncology (Toronto) 2022-03, Vol.29 (3), p.1947-1966 |
---|---|
Main Authors: | , , , , , , , , , , , , , , , |
Format: | Article |
Language: | English |
Subjects: | |
Citations: | Items that this one cites Items that cite this one |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | cdi_FETCH-LOGICAL-c465t-684d6eb4ccba875e82504efff22625ce1bf96d926dbfcb216b6917bc9fd633563 |
---|---|
cites | cdi_FETCH-LOGICAL-c465t-684d6eb4ccba875e82504efff22625ce1bf96d926dbfcb216b6917bc9fd633563 |
container_end_page | 1966 |
container_issue | 3 |
container_start_page | 1947 |
container_title | Current oncology (Toronto) |
container_volume | 29 |
creator | Fusco, Roberta Di Bernardo, Elio Piccirillo, Adele Rubulotta, Maria Rosaria Petrosino, Teresa Barretta, Maria Luisa Mattace Raso, Mauro Vallone, Paolo Raiano, Concetta Di Giacomo, Raimondo Siani, Claudio Avino, Franca Scognamiglio, Giosuè Di Bonito, Maurizio Granata, Vincenza Petrillo, Antonella |
description | :The purpose of this study was to discriminate between benign and malignant breast lesions through several classifiers using, as predictors, radiomic metrics extracted from CEM and DCE-MRI images. In order to optimize the analysis, balancing and feature selection procedures were performed.
: Fifty-four patients with 79 histo-pathologically proven breast lesions (48 malignant lesions and 31 benign lesions) underwent both CEM and DCE-MRI. The lesions were retrospectively analyzed with radiomic and artificial intelligence approaches. Forty-eight textural metrics were extracted, and univariate and multivariate analyses were performed: non-parametric statistical test, receiver operating characteristic (ROC) and machine learning classifiers.
: Considering the single metrics extracted from CEM, the best predictors were KURTOSIS (area under ROC curve (AUC) = 0.71) and SKEWNESS (AUC = 0.71) calculated on late MLO view. Considering the features calculated from DCE-MRI, the best predictors were RANGE (AUC = 0.72), ENERGY (AUC = 0.72), ENTROPY (AUC = 0.70) and GLN (gray-level nonuniformity) of the gray-level run-length matrix (AUC = 0.72). Considering the analysis with classifiers and an unbalanced dataset, no significant results were obtained. After the balancing and feature selection procedures, higher values of accuracy, specificity and AUC were reached. The best performance was obtained considering 18 robust features among all metrics derived from CEM and DCE-MRI, using a linear discriminant analysis (accuracy of 0.84 and AUC = 0.88).
Classifiers, adjusted with adaptive synthetic sampling and feature selection, allowed for increased diagnostic performance of CEM and DCE-MRI in the differentiation between benign and malignant lesions. |
doi_str_mv | 10.3390/curroncol29030159 |
format | article |
fullrecord | <record><control><sourceid>proquest_doaj_</sourceid><recordid>TN_cdi_doaj_primary_oai_doaj_org_article_d1541e52a547460dbbf1376fd0ca8de0</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><doaj_id>oai_doaj_org_article_d1541e52a547460dbbf1376fd0ca8de0</doaj_id><sourcerecordid>2642888542</sourcerecordid><originalsourceid>FETCH-LOGICAL-c465t-684d6eb4ccba875e82504efff22625ce1bf96d926dbfcb216b6917bc9fd633563</originalsourceid><addsrcrecordid>eNplks9uEzEQxlcIREvhAbggH7kE_Gdt716QQhogUiqkqpwtrz27cbVrB9spzePxZjhNW7XiZHvm930zGk9VvSf4E2Mt_mx2MQZvwkhbzDDh7YvqlEjSzKSk7csn95PqTUrXGDMmpXxdnTDOKGO8Pa3-XmrrwuQM0t6iecyud8bpEa18hnF0A3gDaO71uE8uoT8ub9AV3OZdLMwF5OhMQsvbHLXJYFG3R4vgyyvl2dJvdBFbdKGnKQxRbzf7uyrne68PFR_IAgwecolcQgr-IEKrSQ_ODygHdA4ZTEZfIxzZ0lRhMlpDcsGnt9WrXo8J3t2fZ9Wvb8urxY_Z-uf31WK-npla8DwTTW0FdLUxnW4kh4ZyXEPf95QKyg2Qrm-FbamwXW86SkQnWiI70_ZWlFEJdlatjr426Gu1jW7Sca-CduouEOKgdBmfGUFZwmsCnGpey1pg23U9YVL0FhvdWMDF68vRa7vrJrAGDoMYn5k-z3i3UUO4UU1bS0lYMfh4bxDD7x2krCaXTPkw7SHskqKipk3T8JoWlBxRE0NKEfrHMgSrwxqp_9aoaD487e9R8bA37B_KbMxm</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2642888542</pqid></control><display><type>article</type><title>Radiomic and Artificial Intelligence Analysis with Textural Metrics Extracted by Contrast-Enhanced Mammography and Dynamic Contrast Magnetic Resonance Imaging to Detect Breast Malignant Lesions</title><source>PubMed Central Free</source><creator>Fusco, Roberta ; Di Bernardo, Elio ; Piccirillo, Adele ; Rubulotta, Maria Rosaria ; Petrosino, Teresa ; Barretta, Maria Luisa ; Mattace Raso, Mauro ; Vallone, Paolo ; Raiano, Concetta ; Di Giacomo, Raimondo ; Siani, Claudio ; Avino, Franca ; Scognamiglio, Giosuè ; Di Bonito, Maurizio ; Granata, Vincenza ; Petrillo, Antonella</creator><creatorcontrib>Fusco, Roberta ; Di Bernardo, Elio ; Piccirillo, Adele ; Rubulotta, Maria Rosaria ; Petrosino, Teresa ; Barretta, Maria Luisa ; Mattace Raso, Mauro ; Vallone, Paolo ; Raiano, Concetta ; Di Giacomo, Raimondo ; Siani, Claudio ; Avino, Franca ; Scognamiglio, Giosuè ; Di Bonito, Maurizio ; Granata, Vincenza ; Petrillo, Antonella</creatorcontrib><description>:The purpose of this study was to discriminate between benign and malignant breast lesions through several classifiers using, as predictors, radiomic metrics extracted from CEM and DCE-MRI images. In order to optimize the analysis, balancing and feature selection procedures were performed.
: Fifty-four patients with 79 histo-pathologically proven breast lesions (48 malignant lesions and 31 benign lesions) underwent both CEM and DCE-MRI. The lesions were retrospectively analyzed with radiomic and artificial intelligence approaches. Forty-eight textural metrics were extracted, and univariate and multivariate analyses were performed: non-parametric statistical test, receiver operating characteristic (ROC) and machine learning classifiers.
: Considering the single metrics extracted from CEM, the best predictors were KURTOSIS (area under ROC curve (AUC) = 0.71) and SKEWNESS (AUC = 0.71) calculated on late MLO view. Considering the features calculated from DCE-MRI, the best predictors were RANGE (AUC = 0.72), ENERGY (AUC = 0.72), ENTROPY (AUC = 0.70) and GLN (gray-level nonuniformity) of the gray-level run-length matrix (AUC = 0.72). Considering the analysis with classifiers and an unbalanced dataset, no significant results were obtained. After the balancing and feature selection procedures, higher values of accuracy, specificity and AUC were reached. The best performance was obtained considering 18 robust features among all metrics derived from CEM and DCE-MRI, using a linear discriminant analysis (accuracy of 0.84 and AUC = 0.88).
Classifiers, adjusted with adaptive synthetic sampling and feature selection, allowed for increased diagnostic performance of CEM and DCE-MRI in the differentiation between benign and malignant lesions.</description><identifier>ISSN: 1718-7729</identifier><identifier>ISSN: 1198-0052</identifier><identifier>EISSN: 1718-7729</identifier><identifier>DOI: 10.3390/curroncol29030159</identifier><identifier>PMID: 35323359</identifier><language>eng</language><publisher>Switzerland: MDPI</publisher><subject>Artificial Intelligence ; Benchmarking ; Contrast Media ; contrast-enhanced mammography ; Humans ; image enhancement ; magnetic resonance imaging ; Magnetic Resonance Imaging - methods ; Mammography ; radiomics ; Retrospective Studies</subject><ispartof>Current oncology (Toronto), 2022-03, Vol.29 (3), p.1947-1966</ispartof><rights>2022 by the authors. 2022</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c465t-684d6eb4ccba875e82504efff22625ce1bf96d926dbfcb216b6917bc9fd633563</citedby><cites>FETCH-LOGICAL-c465t-684d6eb4ccba875e82504efff22625ce1bf96d926dbfcb216b6917bc9fd633563</cites><orcidid>0000-0003-2465-5370 ; 0000-0002-6601-3221 ; 0000-0001-7584-2569</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC8947713/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC8947713/$$EHTML$$P50$$Gpubmedcentral$$Hfree_for_read</linktohtml><link.rule.ids>230,314,727,780,784,885,27924,27925,53791,53793</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/35323359$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Fusco, Roberta</creatorcontrib><creatorcontrib>Di Bernardo, Elio</creatorcontrib><creatorcontrib>Piccirillo, Adele</creatorcontrib><creatorcontrib>Rubulotta, Maria Rosaria</creatorcontrib><creatorcontrib>Petrosino, Teresa</creatorcontrib><creatorcontrib>Barretta, Maria Luisa</creatorcontrib><creatorcontrib>Mattace Raso, Mauro</creatorcontrib><creatorcontrib>Vallone, Paolo</creatorcontrib><creatorcontrib>Raiano, Concetta</creatorcontrib><creatorcontrib>Di Giacomo, Raimondo</creatorcontrib><creatorcontrib>Siani, Claudio</creatorcontrib><creatorcontrib>Avino, Franca</creatorcontrib><creatorcontrib>Scognamiglio, Giosuè</creatorcontrib><creatorcontrib>Di Bonito, Maurizio</creatorcontrib><creatorcontrib>Granata, Vincenza</creatorcontrib><creatorcontrib>Petrillo, Antonella</creatorcontrib><title>Radiomic and Artificial Intelligence Analysis with Textural Metrics Extracted by Contrast-Enhanced Mammography and Dynamic Contrast Magnetic Resonance Imaging to Detect Breast Malignant Lesions</title><title>Current oncology (Toronto)</title><addtitle>Curr Oncol</addtitle><description>:The purpose of this study was to discriminate between benign and malignant breast lesions through several classifiers using, as predictors, radiomic metrics extracted from CEM and DCE-MRI images. In order to optimize the analysis, balancing and feature selection procedures were performed.
: Fifty-four patients with 79 histo-pathologically proven breast lesions (48 malignant lesions and 31 benign lesions) underwent both CEM and DCE-MRI. The lesions were retrospectively analyzed with radiomic and artificial intelligence approaches. Forty-eight textural metrics were extracted, and univariate and multivariate analyses were performed: non-parametric statistical test, receiver operating characteristic (ROC) and machine learning classifiers.
: Considering the single metrics extracted from CEM, the best predictors were KURTOSIS (area under ROC curve (AUC) = 0.71) and SKEWNESS (AUC = 0.71) calculated on late MLO view. Considering the features calculated from DCE-MRI, the best predictors were RANGE (AUC = 0.72), ENERGY (AUC = 0.72), ENTROPY (AUC = 0.70) and GLN (gray-level nonuniformity) of the gray-level run-length matrix (AUC = 0.72). Considering the analysis with classifiers and an unbalanced dataset, no significant results were obtained. After the balancing and feature selection procedures, higher values of accuracy, specificity and AUC were reached. The best performance was obtained considering 18 robust features among all metrics derived from CEM and DCE-MRI, using a linear discriminant analysis (accuracy of 0.84 and AUC = 0.88).
Classifiers, adjusted with adaptive synthetic sampling and feature selection, allowed for increased diagnostic performance of CEM and DCE-MRI in the differentiation between benign and malignant lesions.</description><subject>Artificial Intelligence</subject><subject>Benchmarking</subject><subject>Contrast Media</subject><subject>contrast-enhanced mammography</subject><subject>Humans</subject><subject>image enhancement</subject><subject>magnetic resonance imaging</subject><subject>Magnetic Resonance Imaging - methods</subject><subject>Mammography</subject><subject>radiomics</subject><subject>Retrospective Studies</subject><issn>1718-7729</issn><issn>1198-0052</issn><issn>1718-7729</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>DOA</sourceid><recordid>eNplks9uEzEQxlcIREvhAbggH7kE_Gdt716QQhogUiqkqpwtrz27cbVrB9spzePxZjhNW7XiZHvm930zGk9VvSf4E2Mt_mx2MQZvwkhbzDDh7YvqlEjSzKSk7csn95PqTUrXGDMmpXxdnTDOKGO8Pa3-XmrrwuQM0t6iecyud8bpEa18hnF0A3gDaO71uE8uoT8ub9AV3OZdLMwF5OhMQsvbHLXJYFG3R4vgyyvl2dJvdBFbdKGnKQxRbzf7uyrne68PFR_IAgwecolcQgr-IEKrSQ_ODygHdA4ZTEZfIxzZ0lRhMlpDcsGnt9WrXo8J3t2fZ9Wvb8urxY_Z-uf31WK-npla8DwTTW0FdLUxnW4kh4ZyXEPf95QKyg2Qrm-FbamwXW86SkQnWiI70_ZWlFEJdlatjr426Gu1jW7Sca-CduouEOKgdBmfGUFZwmsCnGpey1pg23U9YVL0FhvdWMDF68vRa7vrJrAGDoMYn5k-z3i3UUO4UU1bS0lYMfh4bxDD7x2krCaXTPkw7SHskqKipk3T8JoWlBxRE0NKEfrHMgSrwxqp_9aoaD487e9R8bA37B_KbMxm</recordid><startdate>20220313</startdate><enddate>20220313</enddate><creator>Fusco, Roberta</creator><creator>Di Bernardo, Elio</creator><creator>Piccirillo, Adele</creator><creator>Rubulotta, Maria Rosaria</creator><creator>Petrosino, Teresa</creator><creator>Barretta, Maria Luisa</creator><creator>Mattace Raso, Mauro</creator><creator>Vallone, Paolo</creator><creator>Raiano, Concetta</creator><creator>Di Giacomo, Raimondo</creator><creator>Siani, Claudio</creator><creator>Avino, Franca</creator><creator>Scognamiglio, Giosuè</creator><creator>Di Bonito, Maurizio</creator><creator>Granata, Vincenza</creator><creator>Petrillo, Antonella</creator><general>MDPI</general><general>MDPI AG</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><scope>5PM</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0003-2465-5370</orcidid><orcidid>https://orcid.org/0000-0002-6601-3221</orcidid><orcidid>https://orcid.org/0000-0001-7584-2569</orcidid></search><sort><creationdate>20220313</creationdate><title>Radiomic and Artificial Intelligence Analysis with Textural Metrics Extracted by Contrast-Enhanced Mammography and Dynamic Contrast Magnetic Resonance Imaging to Detect Breast Malignant Lesions</title><author>Fusco, Roberta ; Di Bernardo, Elio ; Piccirillo, Adele ; Rubulotta, Maria Rosaria ; Petrosino, Teresa ; Barretta, Maria Luisa ; Mattace Raso, Mauro ; Vallone, Paolo ; Raiano, Concetta ; Di Giacomo, Raimondo ; Siani, Claudio ; Avino, Franca ; Scognamiglio, Giosuè ; Di Bonito, Maurizio ; Granata, Vincenza ; Petrillo, Antonella</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c465t-684d6eb4ccba875e82504efff22625ce1bf96d926dbfcb216b6917bc9fd633563</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Artificial Intelligence</topic><topic>Benchmarking</topic><topic>Contrast Media</topic><topic>contrast-enhanced mammography</topic><topic>Humans</topic><topic>image enhancement</topic><topic>magnetic resonance imaging</topic><topic>Magnetic Resonance Imaging - methods</topic><topic>Mammography</topic><topic>radiomics</topic><topic>Retrospective Studies</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Fusco, Roberta</creatorcontrib><creatorcontrib>Di Bernardo, Elio</creatorcontrib><creatorcontrib>Piccirillo, Adele</creatorcontrib><creatorcontrib>Rubulotta, Maria Rosaria</creatorcontrib><creatorcontrib>Petrosino, Teresa</creatorcontrib><creatorcontrib>Barretta, Maria Luisa</creatorcontrib><creatorcontrib>Mattace Raso, Mauro</creatorcontrib><creatorcontrib>Vallone, Paolo</creatorcontrib><creatorcontrib>Raiano, Concetta</creatorcontrib><creatorcontrib>Di Giacomo, Raimondo</creatorcontrib><creatorcontrib>Siani, Claudio</creatorcontrib><creatorcontrib>Avino, Franca</creatorcontrib><creatorcontrib>Scognamiglio, Giosuè</creatorcontrib><creatorcontrib>Di Bonito, Maurizio</creatorcontrib><creatorcontrib>Granata, Vincenza</creatorcontrib><creatorcontrib>Petrillo, Antonella</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><collection>PubMed Central (Full Participant titles)</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>Current oncology (Toronto)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Fusco, Roberta</au><au>Di Bernardo, Elio</au><au>Piccirillo, Adele</au><au>Rubulotta, Maria Rosaria</au><au>Petrosino, Teresa</au><au>Barretta, Maria Luisa</au><au>Mattace Raso, Mauro</au><au>Vallone, Paolo</au><au>Raiano, Concetta</au><au>Di Giacomo, Raimondo</au><au>Siani, Claudio</au><au>Avino, Franca</au><au>Scognamiglio, Giosuè</au><au>Di Bonito, Maurizio</au><au>Granata, Vincenza</au><au>Petrillo, Antonella</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Radiomic and Artificial Intelligence Analysis with Textural Metrics Extracted by Contrast-Enhanced Mammography and Dynamic Contrast Magnetic Resonance Imaging to Detect Breast Malignant Lesions</atitle><jtitle>Current oncology (Toronto)</jtitle><addtitle>Curr Oncol</addtitle><date>2022-03-13</date><risdate>2022</risdate><volume>29</volume><issue>3</issue><spage>1947</spage><epage>1966</epage><pages>1947-1966</pages><issn>1718-7729</issn><issn>1198-0052</issn><eissn>1718-7729</eissn><abstract>:The purpose of this study was to discriminate between benign and malignant breast lesions through several classifiers using, as predictors, radiomic metrics extracted from CEM and DCE-MRI images. In order to optimize the analysis, balancing and feature selection procedures were performed.
: Fifty-four patients with 79 histo-pathologically proven breast lesions (48 malignant lesions and 31 benign lesions) underwent both CEM and DCE-MRI. The lesions were retrospectively analyzed with radiomic and artificial intelligence approaches. Forty-eight textural metrics were extracted, and univariate and multivariate analyses were performed: non-parametric statistical test, receiver operating characteristic (ROC) and machine learning classifiers.
: Considering the single metrics extracted from CEM, the best predictors were KURTOSIS (area under ROC curve (AUC) = 0.71) and SKEWNESS (AUC = 0.71) calculated on late MLO view. Considering the features calculated from DCE-MRI, the best predictors were RANGE (AUC = 0.72), ENERGY (AUC = 0.72), ENTROPY (AUC = 0.70) and GLN (gray-level nonuniformity) of the gray-level run-length matrix (AUC = 0.72). Considering the analysis with classifiers and an unbalanced dataset, no significant results were obtained. After the balancing and feature selection procedures, higher values of accuracy, specificity and AUC were reached. The best performance was obtained considering 18 robust features among all metrics derived from CEM and DCE-MRI, using a linear discriminant analysis (accuracy of 0.84 and AUC = 0.88).
Classifiers, adjusted with adaptive synthetic sampling and feature selection, allowed for increased diagnostic performance of CEM and DCE-MRI in the differentiation between benign and malignant lesions.</abstract><cop>Switzerland</cop><pub>MDPI</pub><pmid>35323359</pmid><doi>10.3390/curroncol29030159</doi><tpages>20</tpages><orcidid>https://orcid.org/0000-0003-2465-5370</orcidid><orcidid>https://orcid.org/0000-0002-6601-3221</orcidid><orcidid>https://orcid.org/0000-0001-7584-2569</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 1718-7729 |
ispartof | Current oncology (Toronto), 2022-03, Vol.29 (3), p.1947-1966 |
issn | 1718-7729 1198-0052 1718-7729 |
language | eng |
recordid | cdi_doaj_primary_oai_doaj_org_article_d1541e52a547460dbbf1376fd0ca8de0 |
source | PubMed Central Free |
subjects | Artificial Intelligence Benchmarking Contrast Media contrast-enhanced mammography Humans image enhancement magnetic resonance imaging Magnetic Resonance Imaging - methods Mammography radiomics Retrospective Studies |
title | Radiomic and Artificial Intelligence Analysis with Textural Metrics Extracted by Contrast-Enhanced Mammography and Dynamic Contrast Magnetic Resonance Imaging to Detect Breast Malignant Lesions |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T14%3A04%3A03IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_doaj_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Radiomic%20and%20Artificial%20Intelligence%20Analysis%20with%20Textural%20Metrics%20Extracted%20by%20Contrast-Enhanced%20Mammography%20and%20Dynamic%20Contrast%20Magnetic%20Resonance%20Imaging%20to%20Detect%20Breast%20Malignant%20Lesions&rft.jtitle=Current%20oncology%20(Toronto)&rft.au=Fusco,%20Roberta&rft.date=2022-03-13&rft.volume=29&rft.issue=3&rft.spage=1947&rft.epage=1966&rft.pages=1947-1966&rft.issn=1718-7729&rft.eissn=1718-7729&rft_id=info:doi/10.3390/curroncol29030159&rft_dat=%3Cproquest_doaj_%3E2642888542%3C/proquest_doaj_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c465t-684d6eb4ccba875e82504efff22625ce1bf96d926dbfcb216b6917bc9fd633563%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2642888542&rft_id=info:pmid/35323359&rfr_iscdi=true |