Towards Adversarial Retinal Image Synthesis

Abstract

Synthesizing images of the eye fundus is a challenging task that has been previously approached by formulating complex models of the anatomy of the eye. New images can then be generated by sampling a suitable parameter space. In this work, we propose a method that learns to synthesize eye fundus images directly from data. For that, we pair true eye fundus images with their respective vessel trees, by means of a vessel segmentation technique. These pairs are then used to learn a mapping from a binary vessel tree to a new retinal image. For this purpose, we use a recent image-to-image translation technique, based on the idea of adversarial learning. Experimental results show that the original and the generated images are visually different in terms of their global appearance, in spite of sharing the same vessel tree. Additionally, a quantitative quality analysis of the synthetic retinal images confirms that the produced images retain a high proportion of the true image set quality.

References in corpus (2)

• Adam: A Method for Stochastic Optimization
• Unsupervised Learning of Visual Structure using Predictive Generative Networks

Cited by in corpus (20)

• GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification
• Generative Adversarial Network in Medical Imaging: A Review
• Application of Deep Learning in Fundus Image Processing for Ophthalmic Diagnosis -- A Review
• Adversarial Networks for Spatial Context-Aware Spectral Image Reconstruction from RGB
• Abnormal Colon Polyp Image Synthesis Using Conditional Adversarial Networks for Improved Detection Performance
• Data-Driven Color Augmentation Techniques for Deep Skin Image Analysis
• Unsupervised Histopathology Image Synthesis
• Translating and Segmenting Multimodal Medical Volumes with Cycle- and Shape-Consistency Generative Adversarial Network
• Photographic Text-to-Image Synthesis with a Hierarchically-nested Adversarial Network
• Conditional Generation of Medical Images via Disentangled Adversarial Inference
• LOGAN: Membership Inference Attacks Against Generative Models
• Oral-3D: Reconstructing the 3D Bone Structure of Oral Cavity from 2D Panoramic X-ray
• Hi-Net: Hybrid-fusion Network for Multi-modal MR Image Synthesis
• Multi-Domain Image Completion for Random Missing Input Data
• Self-Supervised Ultrasound to MRI Fetal Brain Image Synthesis
• A Deep learning Approach to Generate Contrast-Enhanced Computerised Tomography Angiography without the Use of Intravenous Contrast Agents
• Deep Diagnostics: Applying Convolutional Neural Networks for Vessels Defects Detection
• ASIST: Annotation-free Synthetic Instance Segmentation and Tracking by Adversarial Simulations
• Feature2Mass: Visual Feature Processing in Latent Space for Realistic Labeled Mass Generation
• Synthetic Image Augmentation for Improved Classification using Generative Adversarial Networks