Multimodal Deep Learning for Dynamic and Static Neuroimaging: Integrating MRI and fMRI for Alzheimer Disease Analysis

TL;DR

This paper introduces a multimodal deep learning framework combining MRI and fMRI data to improve Alzheimer's disease classification, emphasizing the role of data augmentation and dataset size.

Contribution

The work presents a novel joint spatial-temporal deep learning model for multimodal neuroimaging data, demonstrating the impact of data augmentation on small datasets.

Findings

Data augmentation improves classification stability for small datasets.

Multimodal fusion outperforms single-modality approaches.

Augmentation is less effective for large single-modality datasets.

Abstract

Magnetic Resonance Imaging (MRI) provides detailed structural information, while functional MRI (fMRI) captures temporal brain activity. In this work, we present a multimodal deep learning framework that integrates MRI and fMRI for multi-class classification of Alzheimer Disease (AD), Mild Cognitive Impairment, and Normal Cognitive State. Structural features are extracted from MRI using 3D convolutional neural networks, while temporal features are learned from fMRI sequences using recurrent architectures. These representations are fused to enable joint spatial-temporal learning. Experiments were conducted on a small paired MRI-fMRI dataset (29 subjects), both with and without data augmentation. Results show that data augmentation substantially improves classification stability and generalization, particularly for the multimodal 3DCNN-LSTM model. In contrast, augmentation was found to be ineffective for a large-scale single-modality MRI dataset. These findings highlight the importance of dataset size and modality when designing augmentation strategies for neuroimaging-based AD classification.