Fatemeh Geranmayeh

CALM-VLM improves confidence and reliability in brain MRI classification by calibrating vision-language models and enabling selective prediction.

This study shows that multi-echo fMRI techniques improve cerebrovascular reactivity estimates in stroke patients by reducing noise and negative values.

This paper introduces an iterative delay correction method to improve breath-hold cerebrovascular reactivity mapping in clinical populations by adjusting the temporal search range for each voxel.

This study compares data-driven and theory-based biomarkers for predicting chronic motor outcomes after stroke, finding data-driven models perform better, especially when using structural disconnection measures.

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.

This paper uses Bayesian optimisation with fMRI to rapidly map residual brain network function in stroke patients, revealing patient-specific abnormalities linked to behavioural performance.