Introduction

In this section we examine the reasons why a number of research groups have embarked on developing methodology and computer software for automated image detection of retinal pathology. We shall see (1) that there is a need in clinical practice to find better and cheaper ways of identifying, managing, and treating retinal disease; (2) that in the research community there is a desire to better understand the underlying causes and progression of disease that requires the detailed analysis of large cohorts of retinal images; (3) that the recent advances in computer hardware and computing power, coupled with increasingly sophisticated image analysis and machine learning techniques, provide opportunities to meet the needs of clinical practice and the eye research community; and, finally, that images of the retina are both a gold mine and a minefield for the application of digital image processing and machine learning techniques, that can both reward the recent graduate and test to exasperation the most competent and innovative engineer.