A Multimodal Deep Learning Model for the Classification of Breast Cancer Subtypes

<b>Background</b>: Breast cancer is a heterogeneous disease with distinct molecular subtypes, each requiring tailored therapeutic strategies. Accurate classification of these subtypes is crucial for optimizing treatment and improving patient outcomes. While immunohistochemistry remains t...

Full description

Saved in:
Bibliographic Details
Main Authors: Chaima Ben Rabah, Aamenah Sattar, Ahmed Ibrahim, Ahmed Serag
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Diagnostics
Subjects:
Online Access:https://www.mdpi.com/2075-4418/15/8/995
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849713844228718592
author Chaima Ben Rabah
Aamenah Sattar
Ahmed Ibrahim
Ahmed Serag
author_facet Chaima Ben Rabah
Aamenah Sattar
Ahmed Ibrahim
Ahmed Serag
author_sort Chaima Ben Rabah
collection DOAJ
description <b>Background</b>: Breast cancer is a heterogeneous disease with distinct molecular subtypes, each requiring tailored therapeutic strategies. Accurate classification of these subtypes is crucial for optimizing treatment and improving patient outcomes. While immunohistochemistry remains the gold standard for subtyping, it is invasive and may not fully capture tumor heterogeneity. Artificial Intelligence (AI), particularly Deep Learning (DL), offers a promising non-invasive alternative by analyzing medical imaging data. <b>Methods</b>: In this study, we propose a multimodal DL model that integrates mammography images with clinical metadata to classify breast lesions into five categories: benign, luminal A, luminal B, HER2-enriched, and triple-negative. Using the publicly available Chinese Mammography Database (CMMD), our model was trained and evaluated on a dataset of 4056 images from 1775 patients. <b>Results</b>: The proposed multimodal approach significantly outperformed a unimodal model based solely on mammography images, achieving an AUC of 88.87% for multiclass classification of these five categories, compared to 61.3% AUC for the unimodal model. <b>Conclusions</b>: These findings highlight the potential of multimodal AI-driven approaches for non-invasive breast cancer subtype classification, paving the way for improved diagnostic precision and personalized treatment strategies.
format Article
id doaj-art-ec5ce93a9ee64a31be42c58177aeb8e0
institution DOAJ
issn 2075-4418
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Diagnostics
spelling doaj-art-ec5ce93a9ee64a31be42c58177aeb8e02025-08-20T03:13:51ZengMDPI AGDiagnostics2075-44182025-04-0115899510.3390/diagnostics15080995A Multimodal Deep Learning Model for the Classification of Breast Cancer SubtypesChaima Ben Rabah0Aamenah Sattar1Ahmed Ibrahim2Ahmed Serag3AI Innovation Lab, Weill Cornell Medicine, Doha 24144, QatarDepartment of Medicine, New Vision University, 0159 Tbilisi, GeorgiaAI Innovation Lab, Weill Cornell Medicine, Doha 24144, QatarAI Innovation Lab, Weill Cornell Medicine, Doha 24144, Qatar<b>Background</b>: Breast cancer is a heterogeneous disease with distinct molecular subtypes, each requiring tailored therapeutic strategies. Accurate classification of these subtypes is crucial for optimizing treatment and improving patient outcomes. While immunohistochemistry remains the gold standard for subtyping, it is invasive and may not fully capture tumor heterogeneity. Artificial Intelligence (AI), particularly Deep Learning (DL), offers a promising non-invasive alternative by analyzing medical imaging data. <b>Methods</b>: In this study, we propose a multimodal DL model that integrates mammography images with clinical metadata to classify breast lesions into five categories: benign, luminal A, luminal B, HER2-enriched, and triple-negative. Using the publicly available Chinese Mammography Database (CMMD), our model was trained and evaluated on a dataset of 4056 images from 1775 patients. <b>Results</b>: The proposed multimodal approach significantly outperformed a unimodal model based solely on mammography images, achieving an AUC of 88.87% for multiclass classification of these five categories, compared to 61.3% AUC for the unimodal model. <b>Conclusions</b>: These findings highlight the potential of multimodal AI-driven approaches for non-invasive breast cancer subtype classification, paving the way for improved diagnostic precision and personalized treatment strategies.https://www.mdpi.com/2075-4418/15/8/995breast cancermolecular subtype classificationdeep learningartificial intelligencemultimodalpersonalized medicine
spellingShingle Chaima Ben Rabah
Aamenah Sattar
Ahmed Ibrahim
Ahmed Serag
A Multimodal Deep Learning Model for the Classification of Breast Cancer Subtypes
Diagnostics
breast cancer
molecular subtype classification
deep learning
artificial intelligence
multimodal
personalized medicine
title A Multimodal Deep Learning Model for the Classification of Breast Cancer Subtypes
title_full A Multimodal Deep Learning Model for the Classification of Breast Cancer Subtypes
title_fullStr A Multimodal Deep Learning Model for the Classification of Breast Cancer Subtypes
title_full_unstemmed A Multimodal Deep Learning Model for the Classification of Breast Cancer Subtypes
title_short A Multimodal Deep Learning Model for the Classification of Breast Cancer Subtypes
title_sort multimodal deep learning model for the classification of breast cancer subtypes
topic breast cancer
molecular subtype classification
deep learning
artificial intelligence
multimodal
personalized medicine
url https://www.mdpi.com/2075-4418/15/8/995
work_keys_str_mv AT chaimabenrabah amultimodaldeeplearningmodelfortheclassificationofbreastcancersubtypes
AT aamenahsattar amultimodaldeeplearningmodelfortheclassificationofbreastcancersubtypes
AT ahmedibrahim amultimodaldeeplearningmodelfortheclassificationofbreastcancersubtypes
AT ahmedserag amultimodaldeeplearningmodelfortheclassificationofbreastcancersubtypes
AT chaimabenrabah multimodaldeeplearningmodelfortheclassificationofbreastcancersubtypes
AT aamenahsattar multimodaldeeplearningmodelfortheclassificationofbreastcancersubtypes
AT ahmedibrahim multimodaldeeplearningmodelfortheclassificationofbreastcancersubtypes
AT ahmedserag multimodaldeeplearningmodelfortheclassificationofbreastcancersubtypes