SPD Matrix Learning for Neuroimaging Analysis: Perspectives, Methods, and Challenges

arXiv:2504.18882v3 Announce Type: replace-cross Abstract: Neuroimaging provides essential tools for characterizing brain activity, structure, and connectivity through modalities that capture complementary aspects of brain organization. Across these diverse modalities, a unifying perspective arises when measurements are modeled as symmetric positive-definite (SPD)-valued representations through appropriate estimation or regularization procedures. Endowed with Riemannian geometry, the SPD manifold provides a non-Euclidean framework for principled statistical inference and machine learning on these representations. This review organizes these analytical and learning approaches within a framework for SPD matrix learning that connects classical geometric statistics with modern machine learning across neuroimaging and neurophysiological applications. We systematically survey the progression from modality-specific representations to geometric shallow and deep learning paradigms, highlighting how SPD matrix learning preserves underlying structural constraints while extending to modern AI applications in neuroimaging and brain-computer interfaces.

Related

• NeuroStrata: An Electroencephalographic Connectivity-Aware Deep Representation Learning Framework for Dynamic Brain Network Analysis of Mental Stress
• Learning Multi-Scale Hypergraph for High-Order Brain Connectivity Analysis
• Machine Learning Methods for Studying Latent Neural Activity Dynamics
• Longitudinal Bayesian Learning of Continuous Disease Position across the Alzheimer's Disease Continuum

Source: arXiv cs.AI | 2026-08-24