Doheny Eye Institute, UCLA – Retina Department
Scientific Institute San Raffaele
The major progress achieved in ocular imaging offered to ophthalmologists worldwide the opportunity to access and analyze subclinical features. Although, the development of millions of morphological datasets raised the necessity to identify a method to quantify these subclinical features with high reliability and applicability. Large scientific datasets can be analyzed in a fast and non-invasive manner by Artificial Intelligence (AI), using algorithms based on machine learning, especially deep learning. Convolutional neural networks reproduce the path of the human brain for object recognition through deep learning of pathological features learned from training sets. The integration of AI with clinical practice has become a necessity in order to improve prediction and prognostic data and to analyze sublinical data, empowering the ophthalmologists to reach a higher quality of care. Our purpose of this Methods Collection is to present a review of AI applications in ophthalmology.