Bradley Thomas Baker

Replicable Connectivity and Spectral Alterations of Functional Networks in Major Depression

This study identifies consistent connectivity, spectral, and spatial changes in intrinsic brain networks in major depression across independent cohorts.

Neuromark Fusion: A Replicable Multimodal Template for Structure-Function Fusion of Brain MRI

The paper develops a normative template for multimodal brain MRI fusion using ICA, showing it guides new dataset analyses and correlates with age.

Template-driven dynamic functional network connectivity predicts medication response for major depression and bipolar disorders

This paper introduces a template-driven method to generate dynamic functional network connectivity features from neuroimaging data, showing improved prediction of medication response in mood disorders.

Explicitly Nonlinear Connectivity-Matrix Independent Component Analysis in Resting fMRI Data

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

dcSBM: A federated constrained source-based morphometry approach for multivariate brain structure mapping

The paper introduces dcSBM, a decentralized constrained source-based morphometry method for multivariate brain structure analysis, showing it reliably identifies group differences in brain morphology across sites.

Enhancing Collaborative Neuroimaging Research: Introducing COINSTAC Vaults for Federated Analysis and Reproducibility

This paper introduces COINSTAC Vaults to enhance collaborative neuroimaging research through federated analysis and reproducibility by hosting standardized datasets.

Machine Learning Predicts Treatment Response in Bipolar & Major Depressive Disorders

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.

Individualized Spatial Network Predictions Using Siamese Convolutional Neural Networks: A Resting-State fMRI Study of over 11,000 Unaffected Individuals

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.