Spatial statistical modelling for medical images at University of Liverpool on FindAPhD.com

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

Click here to search FindAPhD.com for PhD studentship opportunities

Dr G Czanner, Dr Y Zheng Applications accepted all year round

About the Project

The Institute of Ageing and Chronic Disease is part of the Faculty of Health and Life Sciences. We excel in high quality research that contributes to improved health and quality of life for older people and animals and alleviates chronic diseases at all ages. Our departments are now seeking to attract highly motivated self-funded PhD candidates of outstanding ability to join our internationally rated research teams.

Project description
Images are an essential aspect of diagnosis and monitoring in clinical management and clinical research such as in diabetic retinopathy. The retina is considered part of the CNS and reflects many systemic diseases. Clinical care and research in retinal diseases relies heavily in image interpretation. The main problem of the retinal imaging studies is that the images are graded manually by graders, which is costly and achieves only 85% agreement rate between the graders. Another problem is that the manual grading only reports a presence or absence of pathology (such as haemorrhage) and not its total area or spatial distribution, hence the image is not fully utilised.
This project will develop a spatial statistical modelling approach; aiming to create an automated computerized approach for evaluation of clinical images. This will be accomplished by development of spatial and spatio-temporal statistical models which will allow investigation of the association between the location, size of pathologies and disease stage, and to produce individual-specific predictions of the medically relevant outcomes (e.g. onset of disease) or disease stage diagnosis, and therefore, to make the best decision about patient’s treatment in diabetic retinopathy.
The student will be supervised by Dr Gabriela Czanner, Dr Yalin Zheng and Professor Simon Harding and will get training in statistical techniques (hierarchical mixed-effect models, maximum-likelihood estimation, derivation of confidence intervals, simulations), in computer science (programming in R or Matlab, feature-selection approaches). Furthermore the student will obtain skills in data collection, data processing, analysis, writing methodological and clinical papers.

The Institute of Ageing and Chronic Disease is fully committed to promoting gender equality in all activities. In recruitment we emphasize the supportive nature of the working environment and the flexible family support that the University provides. The Institute holds a silver Athena SWAN award in recognition of on-going commitment to ensuring that the Athena SWAN principles are embedded in its activities and strategic initiatives.

This project is for an individual wishing to develop an expertise on intersection of statistics, imaging and computer science. The interested candidate need to have a relevant degree in mathematics containing courses in statistics, programming languages (such as R or Matlab) and previous knowledge in image processing. If you are interested, please send your CV and a covering letter to Dr Gabriela Czanner [Email Address Removed] with a copy to [Email Address Removed]

Funding Notes

The successful candidate should have, or expect to have an Honours Degree at 2.1 or above (or equivalent). Candidates whose first language is not English should have an IELTS score of 6.5 or equivalent.
The successful applicant will be expected to provide the funding for tuition fees and living expenses plus research costs of around £3,000 per year. There is NO funding attached to this project. Details of costs can be found on the University website. We have a thriving international researcher community and encourage applications from students of any nationality able to fund their own studies.

References

(1) Baladan- dayuthapani V et al. Bayesian hierarchical spatially correlated functional data analysis with application to colon carcinogenesis,” Biometrics 2008;64: 64–73.
(2) Bowman FD and Waller LA, Modelling of Cardiac imaging data with spatial correlation,” Stat Med 2004;23(6): 965–985.
(3) Fleming AD, Philip S, Goatman KA, Prescott GJ, Sharp PF, Olson JA. The evidence for automated grading in diabetic retinopathy screening. Curr Diabetes Rev 2011;7(4):246-52.
(4) Niemeijer et al. Retinopathy online challenge: automatic detection of microaneurysms in digital color fundus photographs. IEEE Trans Med Imaging. 2010; 29(1):185-195.
(5) Ramsay JO and Silverman BW. Functional Data Analysis. 2nd ed. New York: Springer; 2010.

Where will I study?

University of Liverpool

We are curious problem solvers at the forefront of world-leading research. A hotbed of discovery and innovation, we're committed to addressing some of the toughest challenges in our society, both now and in the future. Join us in the search for answers by pursuing your PhD at the Original Redbrick.

Spatial statistical modelling for medical images

University of Liverpool Institute of Ageing and Chronic Disease