On the comparison of NN-based architectures for diabetic damage detection in retinal images

The automatic screening of retinal images for an early detection of diabetic symptoms and an early prevention of diabetic retinopathies has been a prime focus in recent times. In this paper a contribution to improve diabetic damage detection in retinal images via neural networks is proposed by comparing two neural strategies. By considering the first architecture, fundus oculi symptomatic pale regions are firstly highlighted by enhanc- ing image contrast with a neurofuzzy subnet, which is synthesized using a Sparsely- Connected Neural Network. Then, obtained contrast-enhanced images with bimodal histograms are globally segmented, after an optimal thresholding performed by a neural subsystem. In output binary images, suspect diabetic areas are finally isolated. By con- sidering the second architecture, an EBP MLP neural net is synthesized, where a suitable training set of suspect patterns is developed by (5 × 5) windows centered on damaged pixels in gold standard images provided by clinicians. Performances are evaluated by percentage measures of exactness in the detection of suspect damaged areas via a com- parison with gold standard images provided by clinicians. Results of both strategies are discussed and compared with other researchers’ ones.