Vinod Kumar

UltraCortex provides high-resolution 9.4 T brain MRI data and validated segmentations, addressing gaps in existing repositories.

This paper improves fMRI-based intelligence prediction by using semi-blind machine learning with educational level as supplementary data, achieving better accuracy even with small sample sizes.

This study identifies 42 genetic loci associated with thalamus and its nuclei volumes and finds genetic overlaps with cortical regions and ten brain disorders.

The paper introduces a machine learning algorithm that predicts intelligence from task-based fMRI data with high accuracy and faster scan times than resting state fMRI.

The paper examines how gray matter volume interacts with white matter connectivity to influence brain controllability, finding that gray matter has a significant impact in highly connected regions.

The paper evaluates different fc-MRI pipelines for detecting brain connectivity, finding that Savitzky Golay filters improve true connectivity detection compared to SPM pipelines.