Deep Generative Modeling with Spatial and Network Images: An Explainable AI (XAI) Approach

2025-05-19

AI Summary

This work addresses the challenge of amplitude of low-frequency fluctuations (ALFF) modeling from resting-state fMRI in the Adolescent Brain Cognitive Development (ABCD) Study. We propose the first end-to-end interpretable generative framework that jointly models cortical structural features and multi-task co-activation networks to synthesize and infer ALFF spatial maps. Methodologically, we explicitly integrate multi-scale spatial–network interactions, subject-level heterogeneity, and spatial smoothness; incorporate network encoding, spatial regularization, and Monte Carlo Dropout to enable principled uncertainty quantification; and directly process high-resolution data without preprocessing. On the ABCD dataset, our model reveals statistically significant whole-brain associations between cortical morphology and ALFF. It achieves prediction accuracy competitive with state-of-the-art methods, delivers more reliable uncertainty estimates, and substantially improves computational efficiency.

Technology Category

• Reasoning under Uncertainty: Relational Probabilistic Models
• Machine Learning: Deep Generative Models & Autoencoders
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

This article addresses the challenge of modeling the amplitude of spatially indexed low frequency fluctuations (ALFF) in resting state functional MRI as a function of cortical structural features and a multi-task coactivation network in the Adolescent Brain Cognitive Development (ABCD) Study. It proposes a generative model that integrates effects of spatially-varying inputs and a network-valued input using deep neural networks to capture complex non-linear and spatial associations with the output. The method models spatial smoothness, accounts for subject heterogeneity and complex associations between network and spatial images at different scales, enables accurate inference of each images effect on the output image, and allows prediction with uncertainty quantification via Monte Carlo dropout, contributing to one of the first Explainable AI (XAI) frameworks for heterogeneous imaging data. The model is highly scalable to high-resolution data without the heavy pre-processing or summarization often required by Bayesian methods. Empirical results demonstrate its strong performance compared to existing statistical and deep learning methods. We applied the XAI model to the ABCD data which revealed associations between cortical features and ALFF throughout the entire brain. Our model performed comparably to existing methods in predictive accuracy but provided superior uncertainty quantification and faster computation, demonstrating its effectiveness for large-scale neuroimaging analysis. Open-source software in Python for XAI is available.

Problem

• Modeling ALFF in fMRI using cortical features and coactivation networks
• Integrating spatial and network inputs via deep neural networks
• Providing explainable AI for heterogeneous neuroimaging data analysis

Innovation

• Deep neural networks integrate spatial and network inputs
• Monte Carlo dropout enables uncertainty quantification
• Scalable to high-resolution data without heavy pre-processing