3D MRI-Based Alzheimer's Disease Classification Using Multi-Modal 3D CNN with Leakage-Aware Subject-Level Evaluation

TL;DR

This paper introduces a multimodal 3D CNN approach for Alzheimer's classification using full brain MRI volumes, demonstrating improved accuracy and meaningful focus on relevant brain regions, with a focus on reproducibility and evaluation strategies.

Contribution

It presents a novel multimodal 3D CNN model for AD classification from volumetric MRI, emphasizing subject-level evaluation and analysis of data representation effects.

Findings

Achieved 72.34% accuracy and 0.7781 ROC AUC on OASIS 1 dataset.

GradCAM visualizations highlight focus on medial temporal lobe and ventricles.

Revealed impact of data representation and evaluation protocols on performance.

Abstract

Deep learning has become an important tool for Alzheimer's disease (AD) classification from structural MRI. Many existing studies analyze individual 2D slices extracted from MRI volumes, while clinical neuroimaging practice typically relies on the full three dimensional structure of the brain. From this perspective, volumetric analysis may better capture spatial relationships among brain regions that are relevant to disease progression. Motivated by this idea, this work proposes a multimodal 3D convolutional neural network for AD classification using raw OASIS 1 MRI volumes. The model combines structural T1 information with gray matter, white matter, and cerebrospinal fluid probability maps obtained through FSL FAST segmentation in order to capture complementary neuroanatomical information. The proposed approach is evaluated on the clinically labelled OASIS 1 cohort using 5 fold subject level cross validation, achieving a mean accuracy of 72.34% plus or minus 4.66% and a ROC AUC of 0.7781 plus or minus 0.0365. GradCAM visualizations further indicate that the model focuses on anatomically meaningful regions, including the medial temporal lobe and ventricular areas that are known to be associated with Alzheimer's related structural changes. To better understand how data representation and evaluation strategies may influence reported performance, additional diagnostic experiments were conducted on a slice based version of the dataset under both slice level and subject level protocols. These observations help provide context for the volumetric results. Overall, the proposed multimodal 3D framework establishes a reproducible subject level benchmark and highlights the potential benefits of volumetric MRI analysis for Alzheimer's disease classification.