Approved Research

Create multi-modal brain image priors for use in Bayesian models to be applied in stroke lesion segmentation and AD diagnosis studies

Lay summary

Stroke and neurodegenerative disorders such as Alzheimer's disease are among the leading causes of death worldwide and have imposed a heavy economic burden on society. The development of imaging-based biomarkers for the early and accurate diagnosis of them is of critical clinical need. In this research, we seek to: (1) characterize the normal brain features using the UK Biobank imaging data; (2) develop a lesion detection algorithm that separates the lesion tissue from normal brain tissue using Biobank image data; (3) develop an algorithm for the early detection of Alzheimer's disease using Biobank image data; (4) Investigate the influence of genetic and environmental risk factors to the variations in brain features.