Automatic computer screening for diabetic retinopathy & glaucoma


Dr Yalin Zheng, University of Liverpool: 1 interactive CET Point

Diabetes related eye problem, known as diabetic retinopathy (DR), is a leading cause of blindness in the working age population in the western world. The number of patients is rising rapidly in the UK (approx. 5% per year) and around the world. The current screening programme is very expensive while manual grading requires extensive training and tight quality assurance to reduce the risk of error. The development of computer programs that can grade images like human graders is believed to be able to help reduce cost and improve patient care in the UK and worldwide, in particular in developing countries where resources are limited.

In this talk, I will first give a brief overview of the problem of diabetic retinopathy and the existing national screening programs. I will then give a short introduction on machine learning techniques and in particular those that have been explored for automated DR screening. I will then review existing automated screening tools and some new deep learning based techniques including our recent innovative work. I will conclude the presentation with new challenges and future directions.

The lecture will be delivered by using Microsoft PowerPoint slides with extensive images and videos.

Learning Objectives

  • Diabetic retinopathy and screening systems
  • Machine learning including deep learning techniques
  • Automated DR screening techniques and new trends

This piece of CET is approved for Optometrists and Dispensing Opticians