Gastric Cancer Histopathology Tissue Image Dataset (GCHTID)

This dataset represents a collection of tissue types in histological images of human gastric cancer, containing 31,096 non-overlapping images of 224x224 pixels each, extracted from H&E-stained pathological slides at Harbin Medical University Cancer Hospital. The dataset was generated by predicting tissue components in gastric cancer using annotations from a publicly available colorectal cancer dataset to create tissue heatmaps. Professional pathologists then selected 300 whole slide images with high prediction accuracy. Finally, a substantial number of images, each belonging to one of eight tissue categories (Adipose (ADI), Background (BACK), Debris (DEB), Lymphocytes (LYM), Mucus (MUC), Smooth Muscle (MUS), Normal Colon Mucosa (NORM), Cancer-associated Stroma (STR), Tumor (TUM)), were extracted from these slides.

本数据集收录了人类胃癌组织学图像中的各类组织类型，共包含31,096张单张尺寸为224×224像素的非重叠图像，所有图像均提取自哈尔滨医科大学附属肿瘤医院的苏木精-伊红（Hematoxylin-Eosin, H&E）染色病理切片。本数据集的构建流程如下：首先利用公开结直肠癌数据集的标注信息预测胃癌组织成分，以生成组织热图；随后由专业病理学家筛选出300张预测准确率较高的全切片图像；最终从上述切片中提取出大量图像，所有图像共分为8类组织：脂肪组织（Adipose, ADI）、背景（Background, BACK）、碎屑（Debris, DEB）、淋巴细胞（Lymphocytes, LYM）、黏液（Mucus, MUC）、平滑肌（Smooth Muscle, MUS）、正常结肠黏膜（Normal Colon Mucosa, NORM）、癌相关基质（Cancer-associated Stroma, STR）与肿瘤组织（Tumor, TUM）。