Hosung Kim

This study compares fMRI complexity and tau-PET in classifying cognitive impairment, finding fMRI matches tau-PET performance with better F1-score and AUC.

The paper investigates age and sex differences in BBB function using MRI in 186 participants, finding more pronounced decline in males starting in the early 60s, particularly in parietal and temporal regions.

This paper uses a GAN-based style transfer approach to harmonize multi-site MRI images without site labels, effectively removing cross-site variation while preserving clinical patterns.

The paper identifies an expanded subventricular zone in neonatal gyrencephalic brains that supports ongoing neuronal migration to the cortex.

This study finds that smaller ipsilesional hippocampal volume is associated with worse upper limb sensorimotor impairment in chronic stroke patients, with a stronger effect in women.

This study shows that global brain health, measured by brain age, influences post-stroke sensorimotor outcomes and mediates the effect of lesion damage.

The paper introduces an EEG-based brain age index to assess brain health and sleep disorders, finding higher indices correlate with cortical thinning and specific sleep disorder patterns.

This study compares hippocampal development in preterm and term-born neonates using MRI, finding asymmetrical structural impairments in preterm infants.

This study finds that smaller spared subcortical nuclei are linked to worse sensorimotor outcomes after stroke, varying by time since stroke and type of impairment.

This study identifies functional connectivity neuromarkers that reveal distinct cognitive recovery patterns in patients with overt hepatic encephalopathy after liver transplantation.

This paper uses a graph convolutional neural network to predict brain age in preterm neonates, showing it outperforms other methods and links brain age to future neurodevelopmental outcomes.

This paper introduces a robust T1 MRI cortical surface pipeline for neonatal brains and evaluates it across multiple datasets, showing high accuracy and reproducibility.

This study uses MRI to analyze cyto/myeloarchitectural changes in preterm neonates' cortical gray matter and white matter, identifying spatiotemporal patterns and associations with developmental outcomes.

This paper uses a GAN-based style transfer approach to harmonize multi-site MRI images without requiring site labels or traveling subjects.

The paper compares automated lesion segmentation methods for chronic stroke T1-weighted MRI data, finding LINDA performs best overall while Gaussian Bayes has highest recall.

The paper introduces ATLAS, a dataset of 304 T1-weighted MRIs with manual lesion segmentations to improve lesion segmentation algorithm accuracy.