Alzheimers Disease Classification in Functional MRI With 4D Joint Temporal-Spatial Kernels in Novel 4D CNN Model

2025-06-01

AI Summary

Conventional 3D CNNs for fMRI 4D spatiotemporal data modeling neglect temporal dynamics, leading to suboptimal feature representation. Method: We propose the first end-to-end 4D convolutional neural network specifically designed for resting-state fMRI (rs-fMRI), featuring learnable 4D joint spatiotemporal convolution kernels that directly model cross-dimensional dependencies among voxels and time points in raw 4D voxel-time series. Integrated with standardized rs-fMRI preprocessing and a lightweight binary classification architecture, the model enables joint optimization of deep spatiotemporal features. Results: On the Alzheimer’s disease vs. normal control (AD/NC) classification task, our model significantly outperforms mainstream 3D CNN baselines (+3.2% accuracy, *p* < 0.01), enhancing early diagnostic sensitivity and robustness. This work establishes an interpretable and scalable 4D modeling paradigm for intelligent neuroimaging analysis.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision

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
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Previous works in the literature apply 3D spatial-only models on 4D functional MRI data leading to possible sub-par feature extraction to be used for downstream tasks like classification. In this work, we aim to develop a novel 4D convolution network to extract 4D joint temporal-spatial kernels that not only learn spatial information but in addition also capture temporal dynamics. Experimental results show promising performance in capturing spatial-temporal data in functional MRI compared to 3D models. The 4D CNN model improves Alzheimers disease diagnosis for rs-fMRI data, enabling earlier detection and better interventions. Future research could explore task-based fMRI applications and regression tasks, enhancing understanding of cognitive performance and disease progression.

Problem

• Improves Alzheimer's disease classification using 4D fMRI data
• Develops 4D CNN to capture spatial-temporal dynamics effectively
• Enhances early detection and intervention for Alzheimer's diagnosis

Innovation

• 4D CNN model for fMRI analysis
• Joint temporal-spatial kernels extraction
• Improved Alzheimer's disease diagnosis