PhD Studentship: Deep Learning Discovery & Visualization from Longitudinal Data

Published on: 12th May 2017

This project aims to apply deep learning techniques on the large, rich bioresources available in Dundee (e.g. goDARTS) to discover novel biomarkers for high-prevalence conditions like diabetes and complications, CVD and dementia.

The focus is on deep learning, a class of machine learning algorithms which has pushed forward the field dramatically, and is increasingly being deployed in data mining/data analytics in genomics, healthcare and many other disciplines.

The student will learn about deep learning and deep network architectures as well as statistical packages (e.g. R) and “conventional” statistical methods.

The aim is to explore the potential of deep learning to discover biomarkers in image data (especially), and to visualize the relevant image features in a way suitable for human interpretation.

The project is a collaboration with the VAMPIRE/CVIP group in Computing (SSEN), which hosts state-of-the-art NVIDIA hardware to run specialised DL architectures.

(This PhD Studentship is funded by the MRC)


Alex Doney & Emanuele Trucco

If you would like to discuss the project then please e-mail:


R Annunziata, E Trucco: Accelerating Convolutional Sparse Coding for Curvilinear Structures Segmentation by Refining SCIRD-TS Filter Banks. IEEE Transactions on Medical Imaging, vol 35 no 11, Nov 2016, pp 2381-2392.

Yann LeCun, Yoshua Bengio & Geoffrey Hinton: Deep learning. Nature 521, 436–444 (28 May 2015) doi:10.1038/nature14539

S. McGrory, A. M. Taylor, J. Corley, A. Pattie, S. R. Cox, B. Dhillon, J. M. Wardlaw, F. N. Doubal, J. M. Starr, E. Trucco, T. J. MacGillivray, I. J. Deary, Retinal microvascular network geometry and cognitive abilities in community-dwelling older people: The Lothian Birth Cohort 1936 Study. British Journal of Ophthalmology, bjophthalmol-2016-309017; DOI: 10.1136/bjophthalmol-2016-309017

Back to top+