Session Title: Free Paper Session 23: Vascular Diseases & Diabetic Retinopathy VI
Session Date/Time: Sunday 10/09/2017 | 08:00-09:30
Paper Time: 09:12
Venue: Room 120
First Author: : J.Wawrzynski UK
Co Author(s): : G. Saleh T. Peto L. Da Cruz P. Smith S. Wang L. Tang
Over the coming decades it will be essential to integrate automated systems within diabetic retinopathy screening programmes to assist human graders as the worldwide incidence of diabetes continues to rise. Patients without diabetic retinopathy (DR) represent a large proportion of the caseload seen by the DR screening service so reliable recognition of the absence of DR in digital fundus images (DFIs) is a prime focus of automated DR screening research. We investigate the use of a novel automated DR detection algorithm to assess retinal DFIs for absence of DR.
Eye clinics in six countries set up to take digital fundus photographs.
A retrospective, masked, controlled image-based study was undertaken. 17,850 DFIs of patients from six different countries were assessed for DR by the automated system and by human graders. The number of images from each country was: Kenya 12,587, Botswana 500, Norway 840, Mongolia 1636, China 1079 and UK 1208. The present study examined fovea centred images. The maximum image resolution was 3888 x 2592 pixels in Mongolia and the minimum was 768 x 576 pixels in the UK. The system’s ability to identify DR was compared across DFIs from the different countries/ racial groups. The sensitivity and specificity of the automated system’s ability to detect DR were analysed for each of the populations studied, taking the human graders’ results as the gold standard. Standardised positive and negative predictive values of the automated system were also calculated for each country based on the known prevalence of DR amongst patients with diabetes within the relevant racial group.
The sensitivities, defined as the proportion of patients classified as having microaneurysms by human graders that were correctly identified by the automated system were as follows: Kenya 92.8%, Botswana 90.1%, Norway 93.5%, Mongolia 91.3%, China 91.9% and UK 90.1%. The standard deviation in the sensitivity values across the six countries was 1.3%. The specificities, defined as to the proportion of patients classified as not having microaneurysms by human graders that were correctly identified as such by the automated system were Kenya 82.7%, Botswana 83.2%, Norway 81.3%, Mongolia 82.5%, China 83.0% and UK 79.0%. The standard deviation in the specificity values across the six countries was 1.5%. The positive predictive values were Kenya 87%, Botswana 87%, Norway 82%, Mongolia 66%, China 67% and UK 79%. The negative predictive values were Kenya 90%, Botswana 87%, Norway 93%, Mongolia 96%, China 97% and UK 90%.
The system presented here was able to rapidly and reliably identify the absence of DR with a high negative predictive value of above 87% in populations from all countries studied. The system returned consistently robust results despite inter-racial differences in choroidal pigmentation/ retinal vasculature and also when presented with images of varying resolution and lighting. Given that the majority of patients attending screening do not have DR, the use of such a system has the potential to vastly reduce the number of images requiring human grading.