True Microaneurysms Detection in Cluttered Retinal Photographs for the Detection of Diabetic Retinopathy

Abstract

Microaneurysms are the first clinical sign of diabetic retinopathy. The number of microaneurysms is used to indicate the severity of the disease. Early microaneurysm detection can help reduce the incidence of blindness. This paper analyzes the Threshold based technique and Wavelet Decomposition technique to reject specific classes of noises while passing majority of true Microaneurysms using a set of specialized features. The rejection strategy is formulated based on the occurrence frequency and discriminability of the underlying clutter. Threshold based technique separates both classes and further allows various subgroups of clutter class to be handled through a cascade solution. Further a set of morphological and appearance based features are introduced to characterize the clutter and MA structures. This gives flexibility to achieve better result of finding Microaneurysms separately from the clutter classes. These two methods have been analyzed based on Microaneurysms detection. Experimental results shows that, the Threshold based technique reduces the noise in an efficient way and affected Microaneurysms portion is obtained clearly.