Diabetic Retinopathy Screening Method Using Adapted Wavelets Decompositions and Template Matching

Abstract

Purpose: : We propose an automatic method to detect microaneurysms in retina photographs. Automating this task, which is currently performed manually, would bring more objectivity and reproducibility in the current clinical practice.

Methods: : The screening method follows several steps. As a template of microaneurysms we use a generalized Gaussian. This template and retina Images are decomposed in several subbands by using the wavelet transform. We propose to detect the lesions by locally matching the template in a selection of subbands. To improve the method performance, we have searched for the best adapted wavelet within the lifting scheme framework.

Results: : Results are evaluated on 120 retinal images analyzed by an expert and the optimal wavelet is compared to different conventional mother wavelets. Depending on the imaging modality (color photographs, green filtered photographs and angiographs), microaneurysms were detected with a sensitivity of respectively 89.62%, 90.24% and 93.74% and a positive predictive value of respectively 89.50%, 89.75% and 91.67%, which is better than previously published methods.

Conclusions: : In this study, we have proposed a new method for detecting microaneurysms in retina. Given its simplicity and relative genericity, this method may be an answer for large screening of Diabetic Retinopathy.

Keywords: diabetic retinopathy • image processing