Partially-shared Imaging Regression on Integrating Heterogeneous Brain-Cognition Associations across Alzheimer's Diagnoses

2025-05-30

AI Summary

This study addresses the heterogeneity in brain imaging–cognition associations across Alzheimer’s disease (AD) diagnostic groups—such as cognitively normal (CN) and mild cognitive impairment (MCI)—by proposing a learnable partially shared multi-task regression model. Methodologically, it innovatively integrates selective integration penalty (SIP) with total variation (TV) regularization, coupled with weighted spatial component decomposition and an adaptive parameter-sharing mechanism, enabling both cross-group coefficient sharing and fine-grained characterization of neuroimaging spatial patterns. Experiments on the ADNI dataset demonstrate significantly improved cognitive prediction performance. Furthermore, the model reveals dynamic changes in hippocampal functional contributions during disease progression: minimal overall hippocampal contribution in the CN group, but markedly enhanced signals from CA1, CA3, and the presubiculum in the MCI group—highlighting stage-specific structural modulation in AD pathophysiology.

Technology Category

• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Machine Learning: Multi-instance/Multi-view 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: User modeling for targeted and personalized online advertising
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

This paper is motivated by the heterogeneous associations among demographic covariates, imaging data, and cognitive performances across different diagnostic groups within the Alzheimer's Disease Neuroimaging Initiative (ADNI) study. We propose a novel PArtially-shared Imaging Regression (PAIR) model with smooth spatial component integration to capture heterogeneous imaging coefficients across multiple data sources. The model assumes that each imaging coefficient can be represented as a weighted combination of a set of smooth spatial components. Additionally, we apply a Total Variation (TV) penalty on each component to capture complex spatial patterns and introduce a Selective Integration Penalty (SIP) to adaptively learn the degree of partial-sharing among imaging coefficients. Applied to ADNI data, PAIR significantly improves predictive performance and uncovers distinct heterogeneous relationships. After adjusting for demographic covariates, hippocampal imaging minimally contributes to cognitive scores in the cognitively normal (CN) group but substantially in the cognitively impaired (CI) group. Furthermore, the effects of demographic covariates on cognitive scores remain stable among CN participants yet change notably for CI participants after imaging adjustment, suggesting hippocampal structural modulation. Imaging coefficient analysis reveals weak hippocampal signals in CN subjects, whereas prominent positive signals in CA1, CA3, and presubiculum subfields characterize the CI group. These analyses facilitate further investigation into functional mechanisms underlying Alzheimer's disease (AD) progression.

Problem

• Modeling heterogeneous brain-cognition associations across Alzheimer's diagnostic groups
• Integrating multiple data sources with partially-shared imaging regression
• Identifying distinct hippocampal contributions to cognitive scores in normal vs impaired groups

Innovation

• PAIR model integrates heterogeneous brain-cognition associations
• Total Variation penalty captures complex spatial patterns
• Selective Integration Penalty adaptively learns partial-sharing