Laura M. Parkes

This paper evaluates automated white matter lesion segmentation methods in Parkinson's disease and healthy controls, finding U-Net-pgs to be the most accurate and reliable approach across multiple metrics and datasets.

This study applies voxel-wise tracer kinetic model selection to DCE-MRI data to improve sensitivity in differentiating normal from pathological tissue compared to the Patlak model.

This paper introduces a hierarchical Bayesian modelling approach for diffusion and exchange MRI data, showing improved accuracy and noise resilience compared to traditional least-squares methods.

The paper identifies a plasma proteomic signature linked to blood-brain barrier dysfunction, which predicts cognitive decline after ischemic stroke.

This paper develops a machine learning method to detect memory reactivation during sleep using EEG data and finds it is more effective in slow wave sleep than stage 2.