Conditional Generation of Medical Images via Disentangled Adversarial Inference

Abstract

Synthetic medical image generation has a huge potential for improving healthcare through many applications, from data augmentation for training machine learning systems to preserving patient privacy. Conditional Adversarial Generative Networks (cGANs) use a conditioning factor to generate images and have shown great success in recent years. Intuitively, the information in an image can be divided into two parts: 1) content which is presented through the conditioning vector and 2) style which is the undiscovered information missing from the conditioning vector. Current practices in using cGANs for medical image generation, only use a single variable for image generation (i.e., content) and therefore, do not provide much flexibility nor control over the generated image. In this work we propose a methodology to learn from the image itself, disentangled representations of style and content, and use this information to impose control over the generation process. In this framework, style is learned in a fully unsupervised manner, while content is learned through both supervised learning (using the conditioning vector) and unsupervised learning (with the inference mechanism). We undergo two novel regularization steps to ensure content-style disentanglement. First, we minimize the shared information between content and style by introducing a novel application of the gradient reverse layer (GRL); second, we introduce a self-supervised regularization method to further separate information in the content and style variables. We show that in general, two latent variable models achieve better performance and give more control over the generated image. We also show that our proposed model (DRAI) achieves the best disentanglement score and has the best overall performance.

Published in Medical Image Analysis

References in corpus (10)

• Conditional Generative Adversarial Nets
• A Simple Framework for Contrastive Learning of Visual Representations
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Semantic Segmentation using Adversarial Networks
• Bridging Theory and Algorithm for Domain Adaptation
• Synthetic Medical Images from Dual Generative Adversarial Networks
• Skin Lesion Synthesis with Generative Adversarial Networks
• Towards Adversarial Retinal Image Synthesis
• Continuous Domain Adaptation with Variational Domain-Agnostic Feature Replay
• Unsupervised Classification of Street Architectures Based on InfoGAN

Cited by in corpus (5)

• Learning Disentangled Representations in the Imaging Domain
• MouseGAN++: Unsupervised Disentanglement and Contrastive Representation for Multiple MRI Modalities Synthesis and Structural Segmentation of Mouse Brain
• Disentangling representations of retinal images with generative models
• Constrained Adversarial Learning for Automated Software Testing: a literature review
• Representation Synthesis by Probabilistic Many-Valued Logic Operation in Self-Supervised Learning