Diabetic retinopathy is a major complication affecting people with diabetes and can be detected by retinal scans. NHS Grampian uses a software (DRIA-2) to automatically such images and thus reduce the workload on practitioners. In a further development of this software (DRIA-3), risk factors for future progression of the disease were identified by traditional computer vision methods.
In this study, we aim at leveraging the advances in machine learning, and particularly deep learning, to further improve the analysis of retinal images. We plan a two-stage approach: 1) automatically assess the usability of retinal images (e.g. presence of the full retinal disk), and 2) automatically classify images according to the severity of the disease, from healthy to severe. To save on iteration time and improve performance, we plan to use Neural Architecture Search (NAS) to build both predictive models.
Selection will be made on the basis of academic merit. The successful candidate should have, or expect to obtain, a UK Honours degree at 2.1 or above (or equivalent) in Computer Science, Robotics, Electrical, Electronic, Mechanical engineering or related fields. A relevant Master’s degree and/or experience in one of the above will be an advantage.
Formal applications can be completed online: https://www.abdn.ac.uk/pgap/login.php
• Apply for Degree of Doctor of Philosophy in Computing Science
• State name of the lead supervisor as the Name of Proposed Supervisor
• State ‘Self-funded’ as Intended Source of Funding
• State the exact project title on the application form
When applying please ensure all required documents are attached:
• All degree certificates and transcripts (Undergraduate AND Postgraduate MSc-officially translated into English where necessary)
• Detailed CV, Personal Statement/Motivation Letter and Intended source of funding
Informal inquiries can be made to Dr D Yi ([Email Address Removed]) with a copy of your curriculum vitae and cover letter. All general enquiries should be directed to the Postgraduate Research School ([Email Address Removed])