A Dual-Head Transformer-State-Space Architecture for Neurocircuit Mechanism Decomposition from fMRI

TL;DR

This paper introduces a dual-head transformer-state-space model that decomposes fMRI functional connectivity into neurobiological mechanisms, aiming to improve understanding and treatment of psychiatric disorders.

Contribution

It presents a novel dual-head architecture combining a transformer and state-space model for detailed neurocircuit mechanism decomposition from fMRI data.

Findings

Decomposes fMRI connectivity into biologically interpretable mechanisms.

Provides pathway-specific routing and drive signals.

Applied to cortico-basal ganglia-thalamo-cortical circuit.

Abstract

Precision psychiatry aspires to elucidate brain-based biomarkers of psychopathology to bolster disease risk assessment and treatment development. To this end, functional magnetic resonance imaging (fMRI) has helped triangulate brain circuits whose functional features are correlated with or even predictive of forms of psychopathology. Yet, fMRI biomarkers to date remain largely descriptive identifiers of where, rather than how, neurobiology is aberrant, limiting their utility for guiding treatment. We present a method for decomposing fMRI-based functional connectivity (FC) into constituent biomechanisms - output drive, input responsivity, modulator gating - with clearer alignment to differentiable therapeutic interventions. Neurocircuit mechanism decomposition (NMD) integrates (i) a graph-constrained, lag-aware transformer to estimate directed, pathway-specific routing distributions and drive signals, with (ii) a measurement-aware state-space model (SSM) that models hemodynamic convolution and recovers intrinsic latent dynamics. This dual-head architecture yields interpretable circuit parameters that may provide a more direct bridge from fMRI to treatment strategy selection. We instantiate the model in an anatomically and electrophysiologically well-defined circuit: the cortico-basal ganglia-thalamo-cortical loop.