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

2026-03-17

AI Summary

This study addresses the limitations of existing Alzheimer’s disease (AD) classification methods that predominantly rely on 2D MRI slices and thus fail to capture the spatial relationships inherent in three-dimensional brain structures. To overcome this, the authors propose a multimodal 3D convolutional neural network that integrates raw T1-weighted MRI scans with gray matter, white matter, and cerebrospinal fluid probability maps generated by FSL FAST. Evaluated on the OASIS-1 dataset using subject-level five-fold cross-validation to prevent data leakage, the model achieves an average accuracy of 72.34% ± 4.66% and a ROC AUC of 0.7781 ± 0.0365. Grad-CAM visualizations confirm that the model’s attention aligns closely with brain regions known to be affected by AD, establishing a reproducible benchmark for 3D multimodal AD classification.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Humans and AI: Brain-Sensing and Analysis

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

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.

Problem

• Alzheimer's disease
• 3D MRI
• disease classification
• volumetric analysis
• subject-level evaluation

Innovation

• 3D CNN
• multimodal MRI
• subject-level evaluation
• Alzheimer's disease classification
• volumetric analysis