Physics-based image interpretation to aid the detection of early signs of retinopathies

Ela Claridge, School of Computer Science, The University of Birmingham
Jonathan Gibson, Department of Ophthalmology, Heartlands Hospital, Birmingham

Supported by EPSRC grant number GR/S09906/01

Diabetic retinopathy is the largest single cause of blindness amongst working age population in the United Kingdom. If pathological changes are detected early, appropriate measures taken to prevent loss of sight are likely to be more effective.

This project aims to develop and validate a new physics based image interpretation method for the ocular fundus and to evaluate its potential in detecting early signs of diabetic retinopathies. An understanding of the physical interaction of light with ocular tissue is utilised to formulate a mathematical model capable of predicting colours which correspond to different tissue composition. Colours in digitized clinical images will be interpreted through reference to this model, generating "retinal maps" which show separately the quantities and distribution of blood, retinal pigment and pathological exudates at every image point. In clinical use the maps would be viewed alongside the conventional image, helping clinical interpretation by highlighting changes, showing the presence of pathologies and removing the masking effect of melanin on small blood variations. For the patient, the new method would be no more onerous than current fundus photography, but the instant availability of the retinal maps would enhance the effectiveness of retinal photographic screening, allowing prompt feedback to the patient and referring medical staff.

Page maintained by Ela Claridge