AI-Ready Multiplex Staining Dataset

AI-Ready Multiplex Staining Dataset是由纪念斯隆-凯特琳癌症中心和莫菲特癌症中心创建的，用于可重复和准确表征肿瘤免疫微环境的首个公共数据集。该数据集包含来自8名头颈鳞状细胞癌患者的重染色和共注册数字化图像，通过昂贵的多重免疫荧光（mIF）和更便宜的多重免疫组织化学（mIHC）两种染色方法进行。数据集的创建过程涉及使用酒精可溶性氨基乙酰苯（AEC）色原进行多次剥离、重染色和扫描，以及使用开源Fiji软件进行图像注册。该数据集的应用领域包括免疫治疗中的肿瘤免疫微环境表征，以及通过风格转移、虚拟染色到染色翻译和虚拟肿瘤/免疫细胞表型分析等多种用例。

The AI-Ready Multiplex Staining Dataset is the first public dataset developed by Memorial Sloan Kettering Cancer Center and Moffitt Cancer Center for the reproducible and accurate characterization of the tumor immune microenvironment. It contains re-stained and co-registered digital images from 8 patients with head and neck squamous cell carcinoma (HNSCC), generated using two staining modalities: costly multiplex immunofluorescence (mIF) and more affordable multiplex immunohistochemistry (mIHC). The dataset creation process involves multiple rounds of stripping, re-staining, and scanning using alcohol-soluble 3-amino-9-ethylcarbazole (AEC) chromogen, as well as image registration via the open-source Fiji software. This dataset supports applications including characterization of the tumor immune microenvironment in immunotherapy, as well as diverse use cases such as style transfer, virtual staining-to-staining translation, and virtual phenotyping of tumor and immune cells.