VTGAN: Semi-supervised Retinal Image Synthesis and Disease Prediction using Vision Transformers

Abstract

In Fluorescein Angiography (FA), an exogenous dye is injected in the bloodstream to image the vascular structure of the retina. The injected dye can cause adverse reactions such as nausea, vomiting, anaphylactic shock, and even death. In contrast, color fundus imaging is a non-invasive technique used for photographing the retina but does not have sufficient fidelity for capturing its vascular structure. The only non-invasive method for capturing retinal vasculature is optical coherence tomography-angiography (OCTA). However, OCTA equipment is quite expensive, and stable imaging is limited to small areas on the retina. In this paper, we propose a novel conditional generative adversarial network (GAN) capable of simultaneously synthesizing FA images from fundus photographs while predicting retinal degeneration. The proposed system has the benefit of addressing the problem of imaging retinal vasculature in a non-invasive manner as well as predicting the existence of retinal abnormalities. We use a semi-supervised approach to train our GAN using multiple weighted losses on different modalities of data. Our experiments validate that the proposed architecture exceeds recent state-of-the-art generative networks for fundus-to-angiography synthesis. Moreover, our vision transformer-based discriminators generalize quite well on out-of-distribution data sets for retinal disease prediction.

arXiv commentAccepted to ICCV 2021 Workshop on Computer Vision for Automated Medical Diagnosis

References in corpus (15)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Transformers in Vision: A Survey
• Gaussian Error Linear Units (GELUs)
• Self-Attention Generative Adversarial Networks
• Predicting Cardiovascular Risk Factors from Retinal Fundus Photographs using Deep Learning
• CovidGAN: Data Augmentation Using Auxiliary Classifier GAN for Improved Covid-19 Detection
• Disc-aware Ensemble Network for Glaucoma Screening from Fundus Image
• U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation
• Demystifying MMD GANs
• Optic-Net: A Novel Convolutional Neural Network for Diagnosis of Retinal Diseases from Optical Tomography Images
• Attention2AngioGAN: Synthesizing Fluorescein Angiography from Retinal Fundus Images using Generative Adversarial Networks
• Fundus2Angio: A Conditional GAN Architecture for Generating Fluorescein Angiography Images from Retinal Fundus Photography

Cited by in corpus (4)

• ResViT: Residual vision transformers for multi-modal medical image synthesis
• Recent Progress in Transformer-based Medical Image Analysis
• One Model to Synthesize Them All: Multi-contrast Multi-scale Transformer for Missing Data Imputation
• ECG-Adv-GAN: Detecting ECG Adversarial Examples with Conditional Generative Adversarial Networks