Differing Matched Filter Responsivity for the Detection of Proliferative Diabetic Retinopathy

Roshan A. Welikala, Vikas Tah, Tom H. Williamson, Andreas Hoppe, Jamshid Dehmeshki, and Sarah A. Barman


Diabetic retinopathy, New vessels, Image processing, Matched filter


Diabetic retinopathy (DR) is a retinal vascular disease and is one of the most common causes of blindness worldwide. Proliferative diabetic retinopathy (PDR) is the most advanced stage of the disease and poses a high risk of severe visual impairment. PDR is characterised by the growth of abnormal new vessels known as neovascularisation. In this paper, we propose the use of the matched filter (MF) technique for vessel segmentation with emphasis on using two different sets of parameters to allow for the detection of new vessels. Parameters are selected to first increase and then decrease the MF response to new vessels, followed by thresholding to produce two separate binary vessel maps. The difference image removes most normal vessels and retains all possible new vessels, therefore making further analysis a much simpler task. Several steps are also included to reduce the detection of non vessel objects (dark and bright lesions). Five local features associated with the morphology of the vasculature are used to create a feature set. Based on these features, regions of the retina are categorized as normal or abnormal using a k-nearest neighbour classifier. Sensitivity and specificity results were 100% and 70% respectively on a per image basis.

Important Links:

Go Back