论文标题
Hoechstgan：使用生成对抗网络的虚拟淋巴细胞染色
HoechstGAN: Virtual Lymphocyte Staining Using Generative Adversarial Networks
论文作者
论文摘要
特定类型的免疫细胞的存在和密度对于了解患者对癌症的免疫反应很重要。但是，鉴定T细胞亚型所需的免疫荧光染色是昂贵的，耗时的，并且在临床环境中很少进行。我们提出了一个框架，可以使用CD3和CD8使用CD3和CD8染色HOECHST图像（廉价且普遍存在），以使用生成的对抗网络识别透明细胞肾细胞癌中的T细胞亚型。我们提出的方法共同学习两个染色任务，激励网络从每个任务中融合了互惠互利的信息。我们设计了一个新颖的指标来量化虚拟染色质量，并使用它来评估我们的方法。
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.
