A morphological approach for efficient macular center detection to support pre-diagnosis of diabetic retinopathy

Diabetes is a disease with a worldwide presence and a high mortality rate, causing a significant social and economic impact. One of the more adverse effects of diabetes is visual loss due to diabetic retinopathy. Current methods to identify patients who need to be seen by a specialist to prevent vision impairment include screening and optical coherence tomography examinations; however, the number of devices and ophthalmologists is insufficient to cover the diabetic population. To address this, computational methods have been developed for rapid early-damage detection. This work presents an algorithm for ocular macula identification using simple image processing techniques for a low computational cost. The proposed algorithm achieved an Euclidean distance of 8.162 $\pm$ 6.774 px (1.496 $\pm$ 1.190% Relative error) in a processing time of 0.458 $\pm$ 0.874 s across four databases, demonstrating competitive accuracy (100%) and speed on low-resource hardware.