Comparative Evaluation of Machine Learning-Based Radiomics and Deep Learning for Breast Lesion Classification in Mammography

<b>Background:</b> Breast cancer is the second leading cause of cancer-related mortality among women, accounting for 12% of cases. Early diagnosis, based on the identification of radiological features, such as masses and microcalcifications in mammograms, is crucial for reducing mortalit...

Full description

Saved in:
Bibliographic Details
Main Authors: Alessandro Stefano, Fabiano Bini, Eleonora Giovagnoli, Mariangela Dimarco, Nicolò Lauciello, Daniela Narbonese, Giovanni Pasini, Franco Marinozzi, Giorgio Russo, Ildebrando D’Angelo
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Diagnostics
Subjects:
Online Access:https://www.mdpi.com/2075-4418/15/8/953
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850183665344053248
author Alessandro Stefano
Fabiano Bini
Eleonora Giovagnoli
Mariangela Dimarco
Nicolò Lauciello
Daniela Narbonese
Giovanni Pasini
Franco Marinozzi
Giorgio Russo
Ildebrando D’Angelo
author_facet Alessandro Stefano
Fabiano Bini
Eleonora Giovagnoli
Mariangela Dimarco
Nicolò Lauciello
Daniela Narbonese
Giovanni Pasini
Franco Marinozzi
Giorgio Russo
Ildebrando D’Angelo
author_sort Alessandro Stefano
collection DOAJ
description <b>Background:</b> Breast cancer is the second leading cause of cancer-related mortality among women, accounting for 12% of cases. Early diagnosis, based on the identification of radiological features, such as masses and microcalcifications in mammograms, is crucial for reducing mortality rates. However, manual interpretation by radiologists is complex and subject to variability, emphasizing the need for automated diagnostic tools to enhance accuracy and efficiency. This study compares a radiomics workflow based on machine learning (ML) with a deep learning (DL) approach for classifying breast lesions as benign or malignant. <b>Methods</b>: matRadiomics was used to extract radiomics features from mammographic images of 1219 patients from the CBIS-DDSM public database, including 581 cases of microcalcifications and 638 of masses. Among the ML models, a linear discriminant analysis (LDA) demonstrated the best performance for both lesion types. External validation was conducted on a private dataset of 222 images to evaluate generalizability to an independent cohort. Additionally, a deep learning approach based on the EfficientNetB6 model was employed for comparison. <b>Results</b>: The LDA model achieved a mean validation AUC of 68.28% for microcalcifications and 61.53% for masses. In the external validation, AUC values of 66.9% and 61.5% were obtained, respectively. In contrast, the EfficientNetB6 model demonstrated superior performance, achieving an AUC of 81.52% for microcalcifications and 76.24% for masses, highlighting the potential of DL for improved diagnostic accuracy. <b>Conclusions</b>: This study underscores the limitations of ML-based radiomics in breast cancer diagnosis. Deep learning proves to be a more effective approach, offering enhanced accuracy and supporting clinicians in improving patient management.
format Article
id doaj-art-bd10c9c062d243af93043cf6ede07ad2
institution OA Journals
issn 2075-4418
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Diagnostics
spelling doaj-art-bd10c9c062d243af93043cf6ede07ad22025-08-20T02:17:19ZengMDPI AGDiagnostics2075-44182025-04-0115895310.3390/diagnostics15080953Comparative Evaluation of Machine Learning-Based Radiomics and Deep Learning for Breast Lesion Classification in MammographyAlessandro Stefano0Fabiano Bini1Eleonora Giovagnoli2Mariangela Dimarco3Nicolò Lauciello4Daniela Narbonese5Giovanni Pasini6Franco Marinozzi7Giorgio Russo8Ildebrando D’Angelo9Institute of Bioimaging and Complex Biological Systems, National Research Council (IBSBC-CNR), Contrada, Pietrapollastra-Pisciotto, 90015 Cefalù, ItalyDepartment of Mechanical and Aerospace Engineering, Sapienza University of Rome, Eudossiana 18, 00184 Rome, ItalyDepartment of Mechanical and Aerospace Engineering, Sapienza University of Rome, Eudossiana 18, 00184 Rome, ItalyDepartment of Radiology, Fondazione Istituto “G. Giglio”, 90015 Cefalù, ItalyInstitute of Bioimaging and Complex Biological Systems, National Research Council (IBSBC-CNR), Contrada, Pietrapollastra-Pisciotto, 90015 Cefalù, ItalyDepartment of Radiology, Fondazione Istituto “G. Giglio”, 90015 Cefalù, ItalyInstitute of Bioimaging and Complex Biological Systems, National Research Council (IBSBC-CNR), Contrada, Pietrapollastra-Pisciotto, 90015 Cefalù, ItalyDepartment of Mechanical and Aerospace Engineering, Sapienza University of Rome, Eudossiana 18, 00184 Rome, ItalyInstitute of Bioimaging and Complex Biological Systems, National Research Council (IBSBC-CNR), Contrada, Pietrapollastra-Pisciotto, 90015 Cefalù, ItalyDepartment of Radiology, Fondazione Istituto “G. Giglio”, 90015 Cefalù, Italy<b>Background:</b> Breast cancer is the second leading cause of cancer-related mortality among women, accounting for 12% of cases. Early diagnosis, based on the identification of radiological features, such as masses and microcalcifications in mammograms, is crucial for reducing mortality rates. However, manual interpretation by radiologists is complex and subject to variability, emphasizing the need for automated diagnostic tools to enhance accuracy and efficiency. This study compares a radiomics workflow based on machine learning (ML) with a deep learning (DL) approach for classifying breast lesions as benign or malignant. <b>Methods</b>: matRadiomics was used to extract radiomics features from mammographic images of 1219 patients from the CBIS-DDSM public database, including 581 cases of microcalcifications and 638 of masses. Among the ML models, a linear discriminant analysis (LDA) demonstrated the best performance for both lesion types. External validation was conducted on a private dataset of 222 images to evaluate generalizability to an independent cohort. Additionally, a deep learning approach based on the EfficientNetB6 model was employed for comparison. <b>Results</b>: The LDA model achieved a mean validation AUC of 68.28% for microcalcifications and 61.53% for masses. In the external validation, AUC values of 66.9% and 61.5% were obtained, respectively. In contrast, the EfficientNetB6 model demonstrated superior performance, achieving an AUC of 81.52% for microcalcifications and 76.24% for masses, highlighting the potential of DL for improved diagnostic accuracy. <b>Conclusions</b>: This study underscores the limitations of ML-based radiomics in breast cancer diagnosis. Deep learning proves to be a more effective approach, offering enhanced accuracy and supporting clinicians in improving patient management.https://www.mdpi.com/2075-4418/15/8/953mammographyradiomicsdeep learningautomated diagnostic systemsbreast lesion classification
spellingShingle Alessandro Stefano
Fabiano Bini
Eleonora Giovagnoli
Mariangela Dimarco
Nicolò Lauciello
Daniela Narbonese
Giovanni Pasini
Franco Marinozzi
Giorgio Russo
Ildebrando D’Angelo
Comparative Evaluation of Machine Learning-Based Radiomics and Deep Learning for Breast Lesion Classification in Mammography
Diagnostics
mammography
radiomics
deep learning
automated diagnostic systems
breast lesion classification
title Comparative Evaluation of Machine Learning-Based Radiomics and Deep Learning for Breast Lesion Classification in Mammography
title_full Comparative Evaluation of Machine Learning-Based Radiomics and Deep Learning for Breast Lesion Classification in Mammography
title_fullStr Comparative Evaluation of Machine Learning-Based Radiomics and Deep Learning for Breast Lesion Classification in Mammography
title_full_unstemmed Comparative Evaluation of Machine Learning-Based Radiomics and Deep Learning for Breast Lesion Classification in Mammography
title_short Comparative Evaluation of Machine Learning-Based Radiomics and Deep Learning for Breast Lesion Classification in Mammography
title_sort comparative evaluation of machine learning based radiomics and deep learning for breast lesion classification in mammography
topic mammography
radiomics
deep learning
automated diagnostic systems
breast lesion classification
url https://www.mdpi.com/2075-4418/15/8/953
work_keys_str_mv AT alessandrostefano comparativeevaluationofmachinelearningbasedradiomicsanddeeplearningforbreastlesionclassificationinmammography
AT fabianobini comparativeevaluationofmachinelearningbasedradiomicsanddeeplearningforbreastlesionclassificationinmammography
AT eleonoragiovagnoli comparativeevaluationofmachinelearningbasedradiomicsanddeeplearningforbreastlesionclassificationinmammography
AT mariangeladimarco comparativeevaluationofmachinelearningbasedradiomicsanddeeplearningforbreastlesionclassificationinmammography
AT nicololauciello comparativeevaluationofmachinelearningbasedradiomicsanddeeplearningforbreastlesionclassificationinmammography
AT danielanarbonese comparativeevaluationofmachinelearningbasedradiomicsanddeeplearningforbreastlesionclassificationinmammography
AT giovannipasini comparativeevaluationofmachinelearningbasedradiomicsanddeeplearningforbreastlesionclassificationinmammography
AT francomarinozzi comparativeevaluationofmachinelearningbasedradiomicsanddeeplearningforbreastlesionclassificationinmammography
AT giorgiorusso comparativeevaluationofmachinelearningbasedradiomicsanddeeplearningforbreastlesionclassificationinmammography
AT ildebrandodangelo comparativeevaluationofmachinelearningbasedradiomicsanddeeplearningforbreastlesionclassificationinmammography