Efficient Deep Learning Approaches for Processing Ultra-widefield Retinal Imaging

Abstract

Deep learning has emerged as the predominant solution for classifying medical images. We intend to apply these developments to the ultra-widefield (UWF) retinal imaging dataset. Since UWF images can accurately diagnose various retina diseases, it is very important to classify them accurately and prevent them with early treatment. However, processing images manually is time-consuming and labor-intensive, and there are two challenges to automating this process. First, high performance usually requires high computational resources. Artificial intelligence medical technology is better suited for places with limited medical resources, but using high-performance processing units in such environments is challenging. Second, the problem of the accuracy of colour fundus photography (CFP) methods. In general, the UWF method provides more information for retinal diagnosis than the CFP method, but most of the research has been conducted based on the CFP method. Thus, we demonstrate that these problems can be efficiently addressed in low-performance units using methods such as strategic data augmentation and model ensembles, which balance performance and computational resources while utilizing UWF images.