Deep Learning for Multi-Label Disease Classification of Retinal Images: Insights from Brazilian Data for AI Development in Lower-Middle Income Countries

Abstract Retinal fundus imaging is a powerful tool for disease screening and diagnosis in opthalmology. With the advent of machine learning and artificial intelligence, in particular modern computer vision classification algorithms, there is broad scope for technology to improve accuracy, increase accessibility and reduce cost in these processes. In this paper we present the first deep learning model trained on the first Brazilian multi-label opthalmological datatset. We train a multi-label classifier using over 16,000 clinically-labelled fundus images. Across a range of 13 retinal diseases, we obtain frequency-weighted AUC and F1 scores of 0.92 and 0.70 respectively. Our work establishes a baseline model on this new dataset and furthermore demonstrates the applicability and power of artificial intelligence approaches to retinal fundus disease diagnosis in under-represented populations.