A hybrid explainable federated-based vision transformer framework for breast cancer prediction via risk factors

Abstract Breast cancer remains a leading cause of mortality in women, underscoring the need for timely and accurate diagnosis. This paper addresses this challenge by introducing a comprehensive explainable federated learning framework for breast cancer prediction. We evaluate three deep learning app...

Full description

Saved in:
Bibliographic Details
Main Authors: Aymen M. Al-Hejri, Archana Harsing Sable, Riyadh M. Al-Tam, Mugahed A. Al-antari, Sultan S. Alshamrani, Kaled M. Alshmrany, Wedad Alatebi
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-96527-0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850231274701062144
author Aymen M. Al-Hejri
Archana Harsing Sable
Riyadh M. Al-Tam
Mugahed A. Al-antari
Sultan S. Alshamrani
Kaled M. Alshmrany
Wedad Alatebi
author_facet Aymen M. Al-Hejri
Archana Harsing Sable
Riyadh M. Al-Tam
Mugahed A. Al-antari
Sultan S. Alshamrani
Kaled M. Alshmrany
Wedad Alatebi
author_sort Aymen M. Al-Hejri
collection DOAJ
description Abstract Breast cancer remains a leading cause of mortality in women, underscoring the need for timely and accurate diagnosis. This paper addresses this challenge by introducing a comprehensive explainable federated learning framework for breast cancer prediction. We evaluate three deep learning approaches in both centralized and federated scenario settings: (1) individual artificial intelligence (AI) models, (2) high-level feature space ensemble models, and (3) a hybrid model combining global Vision Transformer (ViT) and local convolutional neural network (CNN) features. These models are assessed on binary, multi-class, and Breast Imaging Reporting and Data System (BI-RADS) classification tasks using a unique dataset encompassing real-world risk factors. In the federated scenario, we employ three clients with the same approaches as the centralized setting, aggregating their predictions using an AI global model. Explainable AI (XAI) technique is incorporated to enhance AI models’ transparency. Our federated learning approach demonstrates superior performance, achieving accuracies of 98.65%, 97.30%, and 95.59% for binary, multi-class, and BI-RADS tasks, respectively. The proposed model, evaluated with a 95% Confidence Interval (CI) and Areas Under Curve (AUC) curves, registers top classifiers with an AUC of 0.970 [0.917–1]. Local Interpretable Model-Agnostic Explanations (LIME) XAI-based federated learning framework offers a promising solution for privacy-preserving and accurate breast cancer prediction in both research and clinical practice.
format Article
id doaj-art-c7f2db48fd9a4ed3bdd3ed7fe0abe597
institution OA Journals
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-c7f2db48fd9a4ed3bdd3ed7fe0abe5972025-08-20T02:03:35ZengNature PortfolioScientific Reports2045-23222025-05-0115112310.1038/s41598-025-96527-0A hybrid explainable federated-based vision transformer framework for breast cancer prediction via risk factorsAymen M. Al-Hejri0Archana Harsing Sable1Riyadh M. Al-Tam2Mugahed A. Al-antari3Sultan S. Alshamrani4Kaled M. Alshmrany5Wedad Alatebi6School of Computational Sciences, Swami Ramanand Teerth Marathwada UniversitySchool of Computational Sciences, Swami Ramanand Teerth Marathwada UniversitySchool of Computational Sciences, Swami Ramanand Teerth Marathwada UniversityDepartment of Artificial Intelligence and Data Science, Daeyang AI Center, College of AI Convergence, Sejong UniversityDepartment of Information Technology, College of Computers and Information Technology, Taif UniversityInstitute of Public AdministrationDepartment of Statistics, College of Science, Tabuk UniversityAbstract Breast cancer remains a leading cause of mortality in women, underscoring the need for timely and accurate diagnosis. This paper addresses this challenge by introducing a comprehensive explainable federated learning framework for breast cancer prediction. We evaluate three deep learning approaches in both centralized and federated scenario settings: (1) individual artificial intelligence (AI) models, (2) high-level feature space ensemble models, and (3) a hybrid model combining global Vision Transformer (ViT) and local convolutional neural network (CNN) features. These models are assessed on binary, multi-class, and Breast Imaging Reporting and Data System (BI-RADS) classification tasks using a unique dataset encompassing real-world risk factors. In the federated scenario, we employ three clients with the same approaches as the centralized setting, aggregating their predictions using an AI global model. Explainable AI (XAI) technique is incorporated to enhance AI models’ transparency. Our federated learning approach demonstrates superior performance, achieving accuracies of 98.65%, 97.30%, and 95.59% for binary, multi-class, and BI-RADS tasks, respectively. The proposed model, evaluated with a 95% Confidence Interval (CI) and Areas Under Curve (AUC) curves, registers top classifiers with an AUC of 0.970 [0.917–1]. Local Interpretable Model-Agnostic Explanations (LIME) XAI-based federated learning framework offers a promising solution for privacy-preserving and accurate breast cancer prediction in both research and clinical practice.https://doi.org/10.1038/s41598-025-96527-0Breast cancerRisk factorsFederated and centralized learningEnsemble learningVision transformerExplainable artificial intelligence
spellingShingle Aymen M. Al-Hejri
Archana Harsing Sable
Riyadh M. Al-Tam
Mugahed A. Al-antari
Sultan S. Alshamrani
Kaled M. Alshmrany
Wedad Alatebi
A hybrid explainable federated-based vision transformer framework for breast cancer prediction via risk factors
Scientific Reports
Breast cancer
Risk factors
Federated and centralized learning
Ensemble learning
Vision transformer
Explainable artificial intelligence
title A hybrid explainable federated-based vision transformer framework for breast cancer prediction via risk factors
title_full A hybrid explainable federated-based vision transformer framework for breast cancer prediction via risk factors
title_fullStr A hybrid explainable federated-based vision transformer framework for breast cancer prediction via risk factors
title_full_unstemmed A hybrid explainable federated-based vision transformer framework for breast cancer prediction via risk factors
title_short A hybrid explainable federated-based vision transformer framework for breast cancer prediction via risk factors
title_sort hybrid explainable federated based vision transformer framework for breast cancer prediction via risk factors
topic Breast cancer
Risk factors
Federated and centralized learning
Ensemble learning
Vision transformer
Explainable artificial intelligence
url https://doi.org/10.1038/s41598-025-96527-0
work_keys_str_mv AT aymenmalhejri ahybridexplainablefederatedbasedvisiontransformerframeworkforbreastcancerpredictionviariskfactors
AT archanaharsingsable ahybridexplainablefederatedbasedvisiontransformerframeworkforbreastcancerpredictionviariskfactors
AT riyadhmaltam ahybridexplainablefederatedbasedvisiontransformerframeworkforbreastcancerpredictionviariskfactors
AT mugahedaalantari ahybridexplainablefederatedbasedvisiontransformerframeworkforbreastcancerpredictionviariskfactors
AT sultansalshamrani ahybridexplainablefederatedbasedvisiontransformerframeworkforbreastcancerpredictionviariskfactors
AT kaledmalshmrany ahybridexplainablefederatedbasedvisiontransformerframeworkforbreastcancerpredictionviariskfactors
AT wedadalatebi ahybridexplainablefederatedbasedvisiontransformerframeworkforbreastcancerpredictionviariskfactors
AT aymenmalhejri hybridexplainablefederatedbasedvisiontransformerframeworkforbreastcancerpredictionviariskfactors
AT archanaharsingsable hybridexplainablefederatedbasedvisiontransformerframeworkforbreastcancerpredictionviariskfactors
AT riyadhmaltam hybridexplainablefederatedbasedvisiontransformerframeworkforbreastcancerpredictionviariskfactors
AT mugahedaalantari hybridexplainablefederatedbasedvisiontransformerframeworkforbreastcancerpredictionviariskfactors
AT sultansalshamrani hybridexplainablefederatedbasedvisiontransformerframeworkforbreastcancerpredictionviariskfactors
AT kaledmalshmrany hybridexplainablefederatedbasedvisiontransformerframeworkforbreastcancerpredictionviariskfactors
AT wedadalatebi hybridexplainablefederatedbasedvisiontransformerframeworkforbreastcancerpredictionviariskfactors