Generative AI Enables Structural Brain Network Construction from fMRI via Symmetric Diffusion Learning

TL;DR

This paper introduces DiffGAN-F2S, a novel symmetric diffusion generative model that predicts structural brain connectivity from fMRI data, enhancing multimodal brain network analysis and clinical biomarker discovery.

Contribution

It proposes a unified framework combining diffusion probabilistic models and adversarial learning for high-fidelity symmetric SC prediction from fMRI.

Findings

Outperforms existing models in SC prediction accuracy.

Effectively uncovers important brain regions and connections.

Demonstrates clinical relevance on ADNI dataset.

Abstract

Mapping from functional connectivity (FC) to structural connectivity (SC) can facilitate multimodal brain network fusion and discover potential biomarkers for clinical implications. However, it is challenging to directly bridge the reliable non-linear mapping relations between SC and functional magnetic resonance imaging (fMRI). In this paper, a novel symmetric diffusive generative adversarial network-based fMRI-to-SC (DiffGAN-F2S) model is proposed to predict SC from brain fMRI in a unified framework. To be specific, the proposed DiffGAN-F2S leverages denoising diffusion probabilistic models (DDPMs) and adversarial learning to efficiently generate symmetric and high-fidelity SC through a few steps from fMRI. By designing the dual-channel multi-head spatial attention (DMSA) and graph convolutional modules, the symmetric graph generator first captures global relations among direct and indirect connected brain regions, then models the local brain region interactions. It can uncover the complex mapping relations between fMRI and symmetric structural connectivity. Furthermore, the spatially connected consistency loss is devised to constrain the generator to preserve global-local topological information for accurate symmetric SC prediction. Testing on the public Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, the proposed model can effectively generate empirical SC-preserved connectivity from four-dimensional imaging data and shows superior performance in SC prediction compared with other related models. Furthermore, the proposed model can identify the vast majority of important brain regions and connections derived from the empirical method, providing an alternative way to fuse multimodal brain networks and analyze clinical brain disease.