Don't miss our weekly PhD newsletter | Sign up now Don't miss our weekly PhD newsletter | Sign up now

  Automated Brain Image Analysis: Identification of Brain Imaging Features of Degenerative Brain Disease


   School of Science and Engineering

This project is no longer listed on FindAPhD.com and may not be available.

Click here to search FindAPhD.com for PhD studentship opportunities
  Prof S McKenna, Dr A Doney  No more applications being accepted  Competition Funded PhD Project (UK Students Only)

About the Project

Degenerative brain disease is a rapidly developing challenge for society. Improved understanding of its development is urgently required to improve prevention and management. Cerebral Microbleeds (CMBs) are emerging as important imaging features of an aging brain. Not only are they markers for unhealthy blood vessels associated with development of dementia, they also indicate increased risk of cerebral bleeding. This project aims to develop and validate image analysis and deep learning methods to reliably detect, measure and map features such as cerebral microbleeds (CMBs) fully automatically.

CMBs appear as small dark regions in certain types of magnetic resonance imaging. Detecting them manually is time-consuming and exhibits inter-observer variability [1]. Methods developed so far to detect CMBs make many false detections and so are only useful to assist manual review [2]. A fully automatic, high-throughput system for detecting and mapping CMBs would make possible population-based studies exploiting large clinical datasets [3] and increase our understanding of conditions such as stroke and dementia, ultimately improving clinical decision-making.

This project is an interdisciplinary collaboration between Computer Vision & Image Processing (CVIP) in the School of Science & Engineering, and the School of Medicine at Ninewells Hospital. The PhD student will develop image analysis algorithms (with state-of-the-art machine learning) and apply these in large ongoing biomedical research programmes. The student will benefit from access to both technical and clinical expertise, to relevant taught modules, and to a large set of home-grown and commercial software tools. The CVIP research group has considerable experience developing novel methods for biomedical image analysis applications and has won several recent international contests in this area. Our graduated PhDs find work in other prime academic research groups (e.g. UCL, Edinburgh, Toronto) and companies (e.g. Toyota, Toshiba, OPTOS plc).

For information on Evaluation and Criteria Guidance, Funding and Eligibility & How to Apply please click here - https://www.findaphd.com/search/PhDDetails.aspx?CAID=3380

References

[1] Charidimou et al. (2012) Cerebral microbleed detection and mapping: Principles, methodological aspects and rationale in vascular dementia. Experimental Gerontology 47:843-852

[2] Dou, Qi, et al. (2016) Automatic detection of cerebral microbleeds from MR images via
3D CNNs. IEEE Transactions on Medical Imaging 35(5):1182-1195

[3] Yates et al. (2014) Cerebral microbleeds: a review of clinical, genetic, and neuroimaging associations. Frontiers in Neurology 4, January

Where will I study?

 About the Project