AlzFed-XAI: High-Fidelity Interpretable Alzheimer's Diagnosis with Privacy-Preserving Federated Learning

Md. Abdur Rahman, Md. Tofael Ahmed Bhuiyan, Abdul Kadar Muhammad Masum

Keywords: Federated Learning, Medical Imaging, Alzheimer's Disease, Privacy-Preserving AI, Interpretable Deep Learning, Convolutional Neural Networks (CNNs)

TL;DR: We present a lightweight, privacy-preserving federated learning framework for Alzheimer's diagnosis that achieves performance comparable to centralized training while providing model interpretability.

Abstract: Data privacy constraints hinder deep learning in medical imaging by preventing data centralization. We introduce AlzFed-XAI, a federated learning framework for Alzheimer's diagnosis from decentralized MRIs. AlzFed-XAI trains a lightweight CNN (FedNet, 378K parameters) across data silos without exposing raw patient information. On the imbalanced OASIS-1 dataset, our framework achieves 99.73\% accuracy and a 0.9970 macro F1-score, demonstrating a negligible performance drop compared to a centralized baseline. To foster clinical trust, Grad-CAM visualizations confirm the model learns neuroanatomically relevant features. Our work presents a robust, privacy-by-design solution, demonstrating a viable pathway for building high-performance, interpretable AI for critical healthcare diagnostics.

Track: Track 2: ML by Muslim Authors

Submission Number: 56