A dynamic spatiotemporal representation framework for deciphering personal brain function

Abstract

Functional magnetic resonance imaging (fMRI) opens a window on observing spontaneous activities of the human brain in vivo. However, the high complexity of fMRI signals makes brain functional representations intractable. Here, we introduce a state decomposition method to reduce this complexity and decipher individual brain functions at multiple levels. Briefly, brain dynamics are captured by temporal first-order derivatives and spatially divided into ‘state sets’ at each time point based on the velocity and direction of change. This approach transforms the original signals into discrete series consisting of four fundamental states, which efficiently encode individual-specific information. Subsequently, we designed a suite of state-based metrics to quantify regional activities and network interactions. Compared with conventional representations such as resting-state fluctuation amplitude and Pearson’s functional connectivity, the state-based representations serve as more discriminative ‘brain fingerprints’ for individuals and produce reproducible spatial patterns across heterogeneous cohorts (n = 1015). Regarding functional organization, our proposed profiles extend previous representations into nonlinear domains, revealing not only the canonical default-mode dominant pattern but also patterns dominated by the attention network and basal ganglia. Moreover, we demonstrate that personal phenotypes (such as age and gender) can be decoded from regional representations with high accuracy. The equivalence between state series outperforms other existing network representations in predicting individual fluid intelligence. Overall, this framework establishes a foundation for enriching the repertoire of brain functional representations and enhancing the power of brain-phenotype modeling.