Tristram A. P. Lett

The paper develops a digital twin brain model that simulates and manipulates functional brain networks to predict mental illness symptoms and responses to interventions.

The paper introduces DeepTaskGen, a deep learning method that generates synthetic task-based contrast maps from resting-state fMRI data, outperforming benchmarks and enabling biomarker development for cognitive tasks.

This study shows diurnal oscillations exist in MRI metrics of healthy adults and bipolar disorder patients, with similar rhythmicity parameters except for greater phase variation in cerebral blood flow in patients.

The paper identifies genetic loci associated with human cortical structure and finds genetic correlations with neuropsychiatric disorders.