This research examines stroke risk in sickle cell disease by modelling blood flow in the Circle of Willis. While ultrasound predicts risk in children, it fails in adults. Using MRI-based, patient-specific simulations, the study identifies major differences in blood flow patterns, offering a non-invasive, more reliable method for adult stroke prediction.

This research combines CT and MRI brain imaging using machine learning to detect stroke risk markers more quickly. By translating fast CT scans into MRI-level insights, clinicians may identify dangerous intraplaque hemorrhages earlier, improving stroke prevention and diagnosis. The multimodal approach could also enhance imaging for neurological diseases such as Alzheimer’s and Parkinson’s.