NeuroMark-HiFi: A Data-Driven Method for Detecting High-Spatial-Frequency Functional Brain Networks

Abstract

ObjectiveThe Traditional functional neuroimaging approaches typically focus on low-frequency spatial structures, potentially overlooking critical fine-scale connectivity disruptions associated with brain disorders MethodsWe introduce NeuroMark-HiFi, a fully automated algorithm designed to enhance the detection of high-spatial-frequency functional brain network patterns. NeuroMark-HiFi systematically preserves and analyzes fine-grained network variations by integrating reference-informed independent component analysis (ICA), 3D high-frequency spatial filtering, and a frequency-informed ICA decomposition to extract high-frequency functional components with greater precision. ResultsSimulation studies and mathematical evaluations demonstrate that NeuroMark-HiFi significantly improves sensitivity to both individual and group differences driven by small local shifts in spatial patterns of intrinsic connectivity networks (ICNs). Compared to traditional methods, NeuroMark-HiFi revealed additional group differences between individuals with schizophrenia (SZ) and healthy controls (HC), particularly in the visual, sensorimotor, frontal, temporal, and insular networks. ConclusionNeuroMark-HiFi successfully captures biologically meaningful alterations in spatial network patterns that conventional approaches may miss. SignificanceBy improving sensitivity to subtle brain network alterations, NeuroMark-HiFi holds promise for early diagnosis, treatment monitoring, neurodevelopment studies, aging research, and multimodal biomarker discovery, advancing the goals of precision psychiatry and neuroscience.