A Multi-attribute Controllable Generative Model for Histopathology Image Synthesis

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.

arXiv commentMICCAI 2021

References in corpus (10)

• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Self-Attention Generative Adversarial Networks
• Conditional Image Synthesis With Auxiliary Classifier GANs
• Compressed Sensing MRI Reconstruction using a Generative Adversarial Network with a Cyclic Loss
• MedGAN: Medical Image Translation using GANs
• Selective Synthetic Augmentation with HistoGAN for Improved Histopathology Image Classification
• ContraGAN: Contrastive Learning for Conditional Image Generation
• Efficient Attention: Attention with Linear Complexities
• GLU Variants Improve Transformer