Lightweight Generative Adversarial Network Fundus Image Synthesis

Abstract

Blindness is a global health problem that affects billions of lives. Recent advancements in Artificial Intelligence (AI), (Deep Learning (DL)) has the intervention potential to address the blindness issue, particularly as an accurate and non-invasive technique for early detection and treatment of Diabetic Retinopathy (DR). DL-based techniques rely on extensive examples to be robust and accurate in capturing the features responsible for representing the data. However, the number of samples required is tremendous for the DL classifier to learn properly. This presents an issue in collecting and categorizing many samples. Therefore, in this paper, we present a lightweight Generative Neural Network (GAN) to synthesize fundus samples to train AI-based systems. The GAN was trained using samples collected from publicly available datasets. The GAN follows the structure of the recent Lightweight GAN (LGAN) architecture. The implementation and results of the LGAN training and image generation are described. Results indicate that the trained network was able to generate realistic high-resolution samples of normal and diseased fundus images accurately as the generated results managed to realistically represent key structures and their placements inside the generated samples, such as the optic disc, blood vessels, exudates, and others. Successful and unsuccessful generation samples were sorted manually, yielding 56.66% realistic results relative to the total generated samples. Rejected generated samples appear to be due to inconsistencies in shape, key structures, placements, and color.