The contribution of AI in the detection of the Diabetic Retinopathy

The prevalence of diabetes is rising worldwide and in the last two decades, blindness and low vision due to diabetic eye complications have greatly increased. International Diabetes Federation (IDF) [1] reports that in 2000, the global estimated number of of adults with diabetes was 151 million. By 2009 it had grown by 88% to 285 million and today, it is reported that 9.3% of adults aged 2079 years - corresponding more or less to 463 million people are living with diabetes. IDF estimates that there will be 600 million of person with diabetes by 2035, and 700 million by 2045 Diabetic retinopathy (DR) is a complication of diabetes that affects eyes. It originates from the damage to the blood vessels of the light-sensitive tissue of the retina and is the leading cause of cases of blindness. While the primary method for evaluating diabetic retinopathy involves direct and indirect ophthalmoscopy, Artificial Intelligent, deep learning and big data have been on the rise in the eye care sector. These tools provide low-cost, effective and potential solutions in supporting early and accurate diagnosis, both facilitating the work of specialists and allowing to select specific treatments. In this paper we analyze AI tools used in the screening of diabetic retinopathy.