Purchase this article with an account.
R. Markham, A. Osareh, M. Mirmehdi, B. Thomas, M. Macipe; Automated Identification of Diabetic Retinal Exudates Using Support Vector Machines and Neural Networks . Invest. Ophthalmol. Vis. Sci. 2003;44(13):4000.
Download citation file:
© ARVO (1962-2015); The Authors (2016-present)
Purpose: To develop a system for automated identification of exudates in digital retinal photographs of diabetic retinopathy. Methods: We used 142 colour retinal images obtained from a non-mydriatic retinal camera, but with pupillary dilatation, using a 45 degree field of view. Image resolution was 760x570 at 24 bit RGB. Two preprocessing steps - normalisation of colour images to a preselected standard, and local contrast enhancement distributing the value of the pixels around the local mean to facilitate later segmentation, were performed. Candidate exudate regions were identified by carrying out a two stage colour segmentation algorithm based on a Gaussian-smoothed histogram analysis and Fuzzy C-Means clustering. Fuzzy approaches provide a mechanism to represent and manipulate uncertainty and ambiguity in the identification of fundus lesions, allowing pixels to belong to multiple classes with varying degrees of membership. In order to distinguish exudates from other lesions of similar appearance it is necessary to select a set of significant distinguishing features. Colour spaces which separate luminance and chrominance are most suitable. We used - mean Luv and standard deviation of the Luv values inside a candidate region mean Luv and standard deviation of the Luv values surrounding the region Luv values of the region centroid region size region compactness region edge strength Classification of the identified lesions into exudates and non-exudates was performed using either Support Vector Machines or Neural Networks. A neural network based approach using a back propagation learning method (NN-BP) performed marginally better than a support vector machine method, but the latter was more flexible in controlling the trade off between sensitivity and specificity rates. Results: The NN-BP system could achieve 95.5% sensitivity and 73.3% specificity for the identification of patients with exudative retinopathy by classifying whole images. Detection rates could be even higher for individual exudates within an image but at the cost of reduced specificity overall. We looked to see what types of mistakes (false positive or false negative) were made by these systems compared with the clinical judgment of an ophthalmologist. The commonest problem, reducing specificity, was that small light reflexes were often recorded as exudates. Conclusions: Accurate automated identification of exudates is possible. Further development of this system should allow the production of a clinically useful system.
This PDF is available to Subscribers Only