Diabetic retinopathy is a disease in an eye caused due to the diabetic
condition present in the person, resulting in blindness. Early diagnosis of the disease
prevents the progression of blindness. Microaneurysms are the significant symptoms of
the early detection of diabetic retinopathy and are initiated by dilating the thin blood
vessels. Microaneurysms are red lesions, which may be round and sometimes irregular
in shape. Generally, microaneurysms appear near the macula or close to the blood
vessel. The present study concentrates on detecting microaneurysms to detect diabetic
retinopathy in the early stage. This chapter utilizes the Particle Swarm Optimization
(PSO) algorithm to effectively segment the microaneurysms. The segmented
microaneurysm is analyzed using the measures of Entropy, Skewness, and Kurtosis.
The elevated PSO clustering gives high performance irrespective of image contrast.
The elevated continuous PSO clustering successfully detects microaneurysms and helps
diagnose diabetic retinopathy in the early stage in an efficient way. This work uses
digital image processing techniques and mainly concentrates on the effective detection
of microaneurysms. The results proved that the proposed approach improves
performance in the early detection of diabetic retinopathy.
Keywords: Diabetic retinopathy, Microaneurysms, Particle Swarm Optimization, PSO Clustering, Raspberry PI, etc.
