Dataset for segmentation of multiple histopathology findings in rat liver

Dataset_HistoPathology_DILIscreening_KIT folder - Histology images from rat tox study in Korea Institute of Toxicology (KIT) - Dataset for detecting multiple findings and normal features such as infiltration, inflammation, fibrosis, necrosis, vacuolation, portal triad, or connective tissue to screen drug-induced liver injury. - Each folders include about 1000 images and a json file. - Images are 448 by 448 pixel jpg format and 20X microscopic magnification. - A json file has coordinate information about every image and prepared for segmentation algorithm training. CropSlideImages_for_Inference folder - 5 images for inference test. - Image info: 10752 by 10752 pixel, jpg format, 20X magnificationDataset_HistoPathology_DILIscreening_KIT 数据集文件夹：收录韩国毒理学研究所（Korea Institute of Toxicology, KIT）开展的大鼠毒理学研究的组织病理学图像，用于药物性肝损伤筛查，可检测浸润、炎症、纤维化、坏死、空泡变性、门管区及结缔组织等多种病变与正常组织特征。 每个子文件夹包含约1000张图像及一个JSON文件。 图像分辨率为448×448像素，格式为JPEG，显微镜放大倍数为20倍。 该JSON文件包含所有图像的坐标标注信息，可用于分割算法的模型训练。 CropSlideImages_for_Inference 数据集文件夹：包含5张用于推理测试的图像。 图像参数：分辨率为10752×10752像素，格式为JPEG，显微镜放大倍数为20倍。