HoechstGAN: Virtual Lymphocyte Staining Using Generative Adversarial Networks
This addresses the need for cost-effective and rapid immune cell analysis in clinical oncology, though it is incremental as it applies existing GAN methods to a new medical imaging task.
The authors tackled the problem of expensive and time-consuming immunofluorescence staining for identifying T-cell subtypes in cancer by developing a GAN-based framework to virtually stain cheap Hoechst images with CD3 and CD8 markers, achieving a novel metric to quantify staining quality.
The presence and density of specific types of immune cells are important to understand a patient's immune response to cancer. However, immunofluorescence staining required to identify T cell subtypes is expensive, time-consuming, and rarely performed in clinical settings. We present a framework to virtually stain Hoechst images (which are cheap and widespread) with both CD3 and CD8 to identify T cell subtypes in clear cell renal cell carcinoma using generative adversarial networks. Our proposed method jointly learns both staining tasks, incentivising the network to incorporate mutually beneficial information from each task. We devise a novel metric to quantify the virtual staining quality, and use it to evaluate our method.