Resumen |
This chapter deals with the preliminary study of how artificial intelligence, primarily coded by artificial neural networks, could be an aid in a public health problem, which is diabetic retinopathy. The proposal is to train an intelligent system with information generated by ophthalmologists specializing in the follow-up of various retinal conditions caused by diabetes mellitus so that retinal image analysis can be performed on all patients without overloading the specialists. It is essential to point out that the purpose of this system is not to replace the physician but rather to serve as a support so that they can concentrate their attention on the patients/images that require it. The results of this first experiment are motivating. A neural network was trained to classify 70% of the pixels in the image correctly, but there is still a lot of work to bring these systems to a doctor’s office. © 2024 selection and editorial matter, Manuel Cebral-Loureda, Elvira G. Rincón-Flores and Gildardo Sanchez-Ante. |