A Dual-Discriminator Fourier Acquisitive GAN for Generating Retinal Optical Coherence Tomography Images

Abstract

Optical coherence tomography (OCT) images are widely used for clinical examination of the retina. Automatic deep learning-based methods have been developed to classify normal and pathological OCT images. However, lack of the big enough training data reduces the performance of these models. A synthesis of data using generative adversarial networks (GANs) is already known as an efficient alternative to increase the amount of the training data. However, the recent works show that despite high structural similarity between the synthetic data and the real images, a considerable distortion is observed in frequency domain. Here, we propose a dual-discriminator Fourier acquisitive GAN (DDFA-GAN) to generate more realistic OCT images with considering the Fourier domain similarity in structural design of the GAN. By applying two discriminators, the proposed DDFA-GAN is jointly trained with the Fourier and spatial details of the images and is proven to be feasible with a limited number of training data. Results are compared with popular GANs, namely, deep convolutional GAN (DCGAN), Wasserstein GAN with gradient penalized (WGAN-GP), and least square GAN (LS-GAN). In comparison, a Frechet inception distance (FID) score of 51.30 and a multiscale structural similarity index measure (MS-SSIM) of 0.19 indicate the superiority of the proposed method in producing images resembling the same quality, discriminative features, and diversity, as the real normal and diabetic macular edema (DME) OCT images. The statistical comparison illustrates this similarity in the spatial and frequency domains, as well. Overall, DDFA-GAN generates realistic OCT images to meet requirements of the training data in automatic deep learning-based methods, used for clinical examination of the retina, and to improve the accuracy of the subsequent measurements.