Coventry University Featured PhD Programmes
FindA University Ltd Featured PhD Programmes
Sheffield Hallam University Featured PhD Programmes
Norwich Research Park Featured PhD Programmes
Cardiff University Featured PhD Programmes

Spatial statistical methods and machine learning for analysis of retinal images of optic disc

Project Description

Automated disease diagnosis using medical imaging data is an increasingly important problem. For example, colour retinal images are used to detect glaucoma - a major cause of blindness. Recently, we have developed a spatial statistical algorithm, which is based on the analysis of the shape of the optic disc; and competes with machine learning algorithms (MacCormick et al., 2019). The spatial algorithm is able to analyse scenario where a single image is obtained per patient. It is now important to extend the spatial algorithm to complex scenarios of multiple images collected over time from the same patient, to evaluate the risk factors, and to study how this algorithm compares to the recent machine and deep learning algorithms.

Specifically, the project will address the following research objectives:
1) Develop spatio-temporal statistical hierarchical models to study the changes in the shape of the optic disc over time, from both eyes, in glaucoma. A suitable model will need to be constructed to take into account the spatial correlations as well as the correlations over time, and correlations across the two eyes from the same patient.
2) Develop individualised risk prediction for patients, derive the confidence intervals for the risk and create a strategy for early detection of glaucoma.
3) Direct comparison of the spatial statistical algorithm with the machine and deep learning approaches toward disease diagnosis. The implementation of all three objectives will be done in software R or Matlab.

Funding Notes

This project is part of a competition funded by the Liverpool John Moores University. Closing Date 28th February 2019.

The successful candidate will gain expertise on statistical modelling, computer simulations, image analysis, data science and machine learning.

Applicants should have a good first degree. A Master’s degree in Mathematics, Computer Science, Data Science or related discipline is desirable.

Full funding is available to UK/EU candidates only, full-time PhD study only, covering a full studentship for three years. Successful applicants should expect to commence study in September 2019.


MacCormick et a. PlosOne, 2019, Accurate, fast, data efficient and interpretable glaucoma diagnosis with automated spatial analysis of the whole cup to disc profile.

How good is research at Liverpool John Moores University in Computer Science and Informatics?

FTE Category A staff submitted: 9.70

Research output data provided by the Research Excellence Framework (REF)

Click here to see the results for all UK universities

Email Now

Insert previous message below for editing? 
You haven’t included a message. Providing a specific message means universities will take your enquiry more seriously and helps them provide the information you need.
Why not add a message here
* required field
Send a copy to me for my own records.

Your enquiry has been emailed successfully

FindAPhD. Copyright 2005-2019
All rights reserved.