Ganesh B. Chand

The paper identifies nine neuroimaging endophenotypes linked to genetic loci and shows they improve prediction of systemic diseases and mortality.

This study uses support vector machines and deep learning to analyze A{beta} distribution in Braak stages and their predictive relationships with cognitive impairment in MCI and HC participants.

The paper compares S1PR1 protein expression in schizophrenia subtypes using postmortem brain tissue and suggests its potential as an in vivo PET biomarker.

This paper introduces MAGIC, a multi-scale semi-supervised clustering method for brain imaging data to identify disease subtypes, and evaluates its performance on simulated and clinical datasets.

The paper quantifies neuro-anatomical and neuro-molecular markers in the salience network of MCI patients and shows that integrating these markers improves prediction of cognitive dysfunction.

This study uses fMRI to show that the salience network's controlling mechanism over the default-mode and central-executive networks is disrupted in schizophrenia.

This study identifies three neurocognitive subtypes of depression in youth using machine learning, showing distinct neural signatures despite similar clinical symptoms.

This study identifies two neurobiologically distinct subtypes of youth with internalizing symptoms using structural brain imaging and machine learning.