Generative Data Augmentation for Diabetic Retinopathy Classification
Gilbert Lim, Pranav Thombre, Mong Li Lee, Wynne Hsu
Abstract
A fundamental factor limiting the effectiveness of classification algorithms, especially in the medical imaging domain, has been an insufficient quantity of relevant class-specific data. In particular, positive examples of disease conditions tend to be rare, and represent a common bottleneck in improving model performance. In this paper, we introduce GAN-based generative data augmentation methods with dynamic input sampling, and compare their performance against an image feature transfer technique, towards improving the performance of real-world diabetic retinopathy classification tasks. Results suggest that generative data augmentation has the potential to significantly improve classification performance over the baseline.