Zening Fu

The paper compares imputed gene expression (gPRS) and SNP-based polygenic risk scores (sPRS) in predicting gray matter phenotypes using UK Biobank data, finding gPRS provides better prediction accuracy.

This study investigates the association between oral microbiome composition and brain functional connectivity in schizophrenia, finding significant microbiome shifts and correlations with brain network alterations.

The paper examines the association between static and dynamic functional network connectivity and genetic risk of Alzheimer's disease using rs-fMRI and APOE data from cognitively normal individuals.

This paper introduces a multi-scale spatially constrained ICA approach to analyze fMRI data, revealing consistent group differences and predictive patterns in schizophrenia.

The paper develops a reliable network template and methods to estimate individualized functional networks from resting-state fMRI data across 100k+ individuals, showing how data length and spatial resolution affect network estimation.

The paper introduces a multimodal framework to identify brain subspaces linked to biological age and Schizophrenia, showing improved performance over PCA-based methods.

The paper uses a kernel SVM algorithm with neuromark ICA to predict treatment response in bipolar and major depressive disorders with up to 89% accuracy.

The paper uses a Bayesian optimization framework to analyze brain functional subdomains in schizophrenia, showing that more complex models better capture discriminatory information in specific subdomains.

This study shows that intrinsic connectivity networks in fMRI are continuously present and overlapping, not just during discrete events, and that analyzing all time points provides more comprehensive insights into functional patterns and schizophrenia symptoms.

This study uses a Siamese CNN framework to predict individual identity from resting-state fMRI data, achieving 88% accuracy in subject discrimination using spatial network pairs.

This paper introduces multi-model order ICA to evaluate brain functional network connectivity across multiple spatial scales and finds that FNC between model orders 25 and 50 best predicts schizophrenia vs. healthy controls.

This study examines dynamic functional connectivity in the cognitive control network across Alzheimer's disease stages, finding altered temporal connectivity patterns associated with symptom progression.

The paper introduces a toolbox to automatically label and order brain activity maps with high accuracy using a pretrained model and integration of existing techniques.

This paper introduces msICA to analyze dynamic functional interactions across spatial scales in schizophrenia, finding sex-specific differences in connectivity patterns and their association with symptom scores.

This study uses resting-state fMRI to analyze dynamic functional connectivity in major depressive disorder patients before and after ECT, finding that specific network states predict treatment response.

The paper investigates dynamic functional connectivity (dFC) of the default mode network (DMN) in schizophrenia and links it to symptom severity using resting-state fMRI data from two datasets.

This study compares deep learning and standard machine learning on brain imaging data, showing deep learning's superior predictive power and robustness in age and gender classification.

The paper analyzes resting-state fMRI data across different frequency bins to assess functional network connectivity and finds distinct patterns at higher frequencies.

This study identifies 45 structural-functional component maps across 9 functional domains using independent component analysis in two cohorts, showing varying S-F coherence in different brain regions.

This paper uses ultra-high-order ICA to identify fine overlapping functional dynamic parcellations of the brain, highlighting their evolution over time.

This study analyzes age-related changes in brain structure and function across 5967 individuals from 13 to 72 years old, revealing nonlinear patterns in gray matter volume, structural network correlation, and functional network connectivity.

This paper introduces a method to fuse functional and structural MRI data by integrating temporal information, identifying linked variability and covariation in schizophrenia.

This study compares GIG-ICA and STR for identifying brain functional networks in schizophrenia, finding GIG-ICA more sensitive to group differences and better at classification.

This paper introduces a hierarchical approach to analyze spatial and temporal dynamics in brain function, revealing new insights into the chronnectome and identifying changes in schizophrenia patients.