Machine learning & deep learning algorithm reviews for diabetic retinopathy detection

An artificial neural network, expressed as (ANN) a very popular algorithm in machine learning, developed from artificial neurons, has less computation capability, and so is less popular amongst the researchers. Deep learning or may also be called as deep neural network (DNN) has evolved with great computation capabilities with graphic processing units and also large amount of data acquisition is possible with DNN. This paper is the pure analysis and review of the performances of the ML and DL algorithms and also compares the parameters of the fundus images as it aims the detection of Diabetic Retinopathy (DR) with better accuracies. It also speaks about the analysis of another type of images particularly Optical Coherence tomography angiography also called as OCTA used for detection of DR and shows how its accuracies of detection and grading of the disease differs from that of the fundus images. DR is an impairment of diabetes has an effect on eyes and is a consequence of damaged retinal blood vessels. If these complications are identified in the very early stage, then the patient's vision misfortune can be avoided.