Armin Iraji

This study uses sgr-ICA with 500 components on a large rsfMRI dataset to identify fine-grained intrinsic connectivity networks (ICNs) and reveals dysconnectivity patterns in schizophrenia.

This study introduces a method to identify dynamic brain states from resting-state fMRI data, revealing distinct convergence and divergence patterns in four psychiatric disorders.

NeuroMark-HiFi detects high-spatial-frequency functional brain networks, revealing additional group differences in schizophrenia and healthy controls.

This study links short-term brain dynamics to long-term changes in the functional connectome during postnatal development, finding a strong association between specific brain states and non-linear developmental acceleration.

This study links multi-scale brain connectivity networks to cognitive and behavioral functions in adolescents, finding significant associations with attention, working memory, and behavioral regulation.

This study identifies distinct functional connectivity patterns in mental disorders using dFIPs derived from rs-fMRI data, revealing disorder-specific and shared neural signatures.

This study uses high-order ICA on PET scans to identify amyloid-beta networks in Alzheimer's Disease, revealing distinct gray and white matter patterns associated with cognitive impairment.

This study examines time-varying spatial propagation of brain networks in fMRI data and links propagative patterns to schizophrenia.

The paper presents a WM intrinsic connectivity network template derived from 100,000 fMRI scans, showing distinct WM and GM networks with task-related activity and differences in schizophrenia.

This study identifies adult-like multi-scale brain networks in infants using rsfMRI, showing early emergence of functional connectivity patterns.

This paper introduces a nonlinear method to estimate brain networks from fMRI data, showing it better distinguishes schizophrenia patients from controls than linear methods.

This paper introduces TICA, a method for analyzing fMRI data across multiple spatial scales to detect functional brain networks and differences between healthy and schizophrenia cohorts.

This paper uses phase portraits and fuzzy recurrence plots to analyze nonlinear dynamics in brain networks, showing they can capture functional connectivity and predict neural behavior.

This paper creates a whole-brain functional atlas from resting-state fMRI data to standardize terminology and improve consistency across neuroimaging studies.

This paper introduces a method to identify linear and explicitly nonlinear dependencies in resting fMRI data and applies it to detect differences in schizophrenia.

This study examines dynamic spatial brain networks in resting-state fMRI data, finding atypical variability and coupling in schizophrenia linked to cognitive impairment.

SpaDE is a deep learning model for biclustering neuroimaging data that identifies coherent subject and feature subgroups with improved interpretability and performance over existing methods.

This paper introduces a multi-modal AI model for schizophrenia classification using imaging and genetic data, achieving 94.10% accuracy and identifying key brain regions and genes associated with the disorder.

This study uses complexity measures like fuzzy recurrence plots and sample entropy to analyze functional connectivity in the psychotic brain, revealing patterns of neural activity and synchronization.

This study identifies shared and divergent functional brain connections between humans and marmosets using topological graph analysis of whole-brain functional connectivity.

This paper introduces sfCICA, a multi-modal ICA model combining structural and functional brain connectivity to estimate ICNs, showing improved modularity and network distinction in schizophrenia.

The paper develops a method to estimate time-resolved spatial networks and applies it to study sex-specific schizophrenia disruptions and their genetic links.

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 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.

This study introduces a method to analyze explicitly nonlinear dynamic functional connectivity in resting-state fMRI data and finds significant group differences between schizophrenia patients and healthy controls.

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 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 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.

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