2D adaptive filtering and region growing algorithm for the detection of microaneurysms in retinal angiograms

The diabetic retinopathy is a common disease among diabetic patients that can cause blindness. The number of microaneurysms in an eve fundus indicates the evolution stage of the illness. In this paper, an algorithm to automatically detect microaneurysms in retinal angiograms is proposed. The method has three main steps: preprocessing step, seed detection and a subsequent region-growing algorithm. The preprocessing step consists of a Gaussian high pass filtering followed by a top-hat filtering. The aim of this preprocessing step is to eliminate the vascular tree while enhancing microaneurysms. In the second step, a 2-D adaptive filtering is performed and those pixels where the prediction error is high are considered seeds. After the region growing, only regions that fit certain validation criteria are considered microaneurysms. These criteria are intensity, contrast and shape criteria. Intensity, and contrast ones are typical criteria used in region-growing algorithms. To create the shape criterion. we have used the fact that microaneurysms can be modelled as 2D Gaussian functions. During the application of this criterion we pass each grown region through a bank of nine correlators, a 2D Gaussian function and eight linear segments oriented in eight different directions. Then we compare the outputs of this bank and we impose that a region can be a microaneurysm when the maximum peak of correlation is obtained when passing through the Gaussian correlator. In this study we have tested the algorithim with 11 images containing 711 microaneurysms in all and we have obtained a sensitivity of 90,72% for a predictive positive value of 82,35%.