Organisation:
Department:
Keywords:
Interests:
Shaun Stone is a final year Ph.D. ERC studying Medical Imaging at the University of Aberdeen under the supervision of Professor Alison Murray. He is the deputy student lead of the Image Analysis group of the Scottish Imaging Network: A Platform for Scientific Excellence (SINAPSE), a consortium of seven Scottish universities. His research is titled “Cognitive Reserve Estimation Models from Brain MRI in Healthy Ageing: A Machine Learning Approach”, under the supervision of Professor Alison D. Murray (University of Aberdeen), Dr Roger Staff (NHS), Professor Joanna Wardlaw, Professor Craig Ritchie (University of Edinburgh) and Dr Robin Wolz (IXICO). Cosupervisors to this project at Dr Gordon Waiter and Dr Anca Sandu-Giuraniuc. His project is funded by SINAPSE and industry partners IXICO.
His project aims to identify the most important MR imaging biomarkers that influence differences in cognitive resilience. That is, given the life-course of an individual, what are the imaging characteristics that allow us to predict increased risk of cognitive impairment? Further, what factors provide resilience against age- and disease-related brain changes? He is passionate about computational neuroscience, artificial intelligence and computer-assisted diagnosis in medical imaging. Shaun completed his undergraduate (BSc) degree in Psychology with Neuroscience, and postgraduate (MSc) degree in Neuroimaging at Bangor University, North Wales – where he gained experience using a range of neuroimaging techniques. Shaun continues to learn, using his neuro-background to transfer into computational medicine and diagnostic imaging and is looking forward to his future career in research or industry, thanks to this opportunity.
Research Themes:
The project aims to identify the most important life-course factors and brain biomarkers that influence differences in cognitive reserve and cognitive resilience. These proxies of cognitive decline will then be incorporated into machine learning algorithms for automatic detection and classification of dementia risk from a brain scan. Such machine learning models may be able to quantify the discrepancy between the amount of disease present (MR images) and cognitive symptoms and relate this to life-course determinants. That is, given the life-course of an individual, what are the imaging characteristics that allow us to predict cognitive decline and therefore future dementia risk? Providing these models are accurate in predicting patient pathology, these approaches will be extremely useful for both clinical/pharmaceutical trials and for earlier diagnosis of patients with dementia in the NHS – improving the accuracy of diagnosis and more importantly earlier diagnosis for more appropriate intervention and care.
Collaborators:
IXICO: Innovative Technologies for Treating Serious Diseases
Biomedical Imaging Research Centre (BRIC): University of North Carolina, School of Medicine, Bioinformatics