Functional MRI Time Series Generation via Wavelet-Based Image Transform and Spectral Flow Matching for Brain Disorder Identification

2026-05-28

AI Summary

Existing fMRI data generation methods struggle to capture the non-stationarity, complex spatiotemporal dynamics, and inter-individual physiological variability of BOLD signals, limiting data-driven brain disorder analysis. To address this, this work proposes a Dual Spectral Flow Matching (DSFM) framework that, for the first time, integrates Discrete Wavelet Transform (DWT) and Discrete Cosine Transform (DCT) to jointly model the multi-scale transient characteristics and low-frequency energy concentration inherent in BOLD signals. By performing flow matching in the spectral domain under class-conditional settings, DSFM constructs a structured spectral prior that preserves essential physiological dynamics while significantly enhancing the realism and discriminability of generated data. The resulting synthetic fMRI sequences substantially improve downstream brain network classification performance, demonstrating the method’s practical utility in brain disease identification.

Abstract

Functional Magnetic Resonance Imaging (fMRI) provides non-invasive access to dynamic brain activity by measuring blood oxygen level-dependent (BOLD) signals over time. However, the resource-intensive nature of fMRI acquisition limits the availability of high-fidelity samples required for data-driven brain analysis models. While modern generative models can synthesize fMRI data, they often remain challenging in replicating their inherent non-stationarity, intricate spatiotemporal dynamics, and physiological variations of raw BOLD signals. To address these challenges, we propose Dual-Spectral Flow Matching (DSFM), a novel fMRI generative framework that cascades dual frequency representation of BOLD signals with spectral flow matching. Specifically, our framework first converts BOLD signals into a wavelet decomposition map via a discrete wavelet transform (DWT) to capture globalized transient and multi-scale variations, and projects into the discrete cosine transform (DCT) space across brain regions and time to exploit localized energy compaction of low-frequency dominant BOLD coefficients. Subsequently, a spectral flow matching model is trained to generate class-conditioned cosine-frequency representation. The generated samples are reconstructed through inverse DCT and inverse DWT operations to recover physiologically plausible time-domain BOLD signals. This dual-transform approach imposes structured frequency priors and preserves key physiological brain dynamics. Ultimately, we demonstrate the efficacy of our approach through improved downstream fMRI-based brain network classification. The code is available at https://github.com/htew0001/DSFM.git .

Problem

• fMRI generation
• non-stationarity
• spatiotemporal dynamics
• BOLD signals
• physiological variations

Innovation

• Wavelet Transform
• Spectral Flow Matching
• fMRI Generation
• Discrete Cosine Transform
• Non-stationary Time Series