Explainable Artificial Intelligence in Deep Learning Neural Nets-Based Digital Images Analysis

Abstract

This review shows the capabilities of artificial intelligence (AI) in the analysis of digital images in the field of medicine using convolutional neural networks of deep learning (DL). A new generation of AI systems is described with an explanation of decision-making algorithms to the user—explainable artificial intelligence (XAI). The taxonomy of the methods of explanation and the description of the methods themselves are given. The need to use XAI in classification tasks is substantiated on the example of ophthalmic diseases. The components of DL methods used in the reviewed works (neural network architecture, accuracy, characteristics of data sets) and XAI (methods of explanation, criteria for the accuracy of explanation) are studied. As an example, the problem of recognizing two of the most commonly diagnosed eye diseases is considered: diabetic retinopathy and glaucoma by artificial neural networks.