A Multi-attribute Controllable Generative Model for Histopathology Image Synthesis
This work addresses the need for more controllable image synthesis in medical training, though it is incremental as it builds upon existing GANs with added modules.
The authors tackled the problem of generating controllable and interpretable histopathology images by developing AttributeGAN, a multi-attribute generative model that produces high-quality images based on input attributes, showing improved attribute reflection and smoother interpolation compared to existing single-attribute models.
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.