A Multi-attribute Controllable Generative Model for Histopathology Image Synthesis

TL;DR

This paper introduces AttributeGAN, a controllable GAN model that synthesizes high-quality histopathology images based on multiple attributes, improving attribute control and interpolation over existing models for medical image generation.

Contribution

The paper presents a novel multi-attribute controllable GAN for histopathology image synthesis, enhancing attribute reflection and interpolation capabilities.

Findings

Outperforms existing models in attribute accuracy and image quality.

Enables smooth interpolation among attribute values.

Demonstrates effectiveness on urothelial carcinoma histopathology images.

Abstract

Generative models have been applied in the medical imaging domain for various image recognition and synthesis tasks. However, a more controllable and interpretable image synthesis model is still lacking yet necessary for important applications such as assisting in medical training. In this work, we leverage the efficient self-attention and contrastive learning modules and build upon state-of-the-art generative adversarial networks (GANs) to achieve an attribute-aware image synthesis model, termed AttributeGAN, which can generate high-quality histopathology images based on multi-attribute inputs. In comparison to existing single-attribute conditional generative models, our proposed model better reflects input attributes and enables smoother interpolation among attribute values. We conduct experiments on a histopathology dataset containing stained H&E images of urothelial carcinoma and demonstrate the effectiveness of our proposed model via comprehensive quantitative and qualitative comparisons with state-of-the-art models as well as different variants of our model. Code is available at https://github.com/karenyyy/MICCAI2021AttributeGAN.