A Federated Learning System with Biometric Medical Image Authentication for Alzheimer's Diagnosis

Francesco Castro, Donato Impedovo, Giuseppe Pirlo

2024

Abstract

There are concerns within the medical/scientific community about the use of machine learning models for disease diagnosis from medical images. The causes are related not only to the high performance required in models for disease diagnosis but also to the sensitivity of the data processed and the protection of patient privacy. There are stringent policies on medical image dissemination to prevent image theft, image de-anonymization, data poisoning attacks, and other security issues. The proposed system for AD diagnosis from RGB MRI brain images implements the Federated Learning (FL) architecture and a strategy of medical image authentication through biometric recognition to protect the privacy and confidentiality of the medical image used for the training model and to mitigate the data poisoning attacks on the model. Experiments conducted on two datasets of RGB MRI images (OASIS and ADNI) demonstrate that the proposed system achieved performance comparable to a centralized ML system without a privacy-preserving strategy. The proposed system represents a solution to solve security and privacy issues in a healthcare application for AD diagnosis.

Paper Citation

in Harvard Style

Castro F., Impedovo D. and Pirlo G. (2024). A Federated Learning System with Biometric Medical Image Authentication for Alzheimer's Diagnosis. In Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: NeroPRAI; ISBN 978-989-758-684-2, SciTePress, pages 951-960. DOI: 10.5220/0012550200003654

in Bibtex Style

@conference{neroprai24,
author={Francesco Castro and Donato Impedovo and Giuseppe Pirlo},
title={A Federated Learning System with Biometric Medical Image Authentication for Alzheimer's Diagnosis},
booktitle={Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: NeroPRAI},
year={2024},
pages={951-960},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012550200003654},
isbn={978-989-758-684-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: NeroPRAI
TI - A Federated Learning System with Biometric Medical Image Authentication for Alzheimer's Diagnosis
SN - 978-989-758-684-2
AU - Castro F.
AU - Impedovo D.
AU - Pirlo G.
PY - 2024
SP - 951
EP - 960
DO - 10.5220/0012550200003654
PB - SciTePress