Codatta/Refined-TCGA-PRAD-Prostate-Cancer-Pathology-Dataset

该数据集提供了对TCGA PRAD前列腺癌数据集的增强Gleason分级注释，并包含区域兴趣（ROI）级别的空间注释。数据集由Codatta和DPath.ai合作开发，旨在通过全球病理学家的协作提高标签的可靠性，从而改进AI模型的训练和病理学研究。数据集包含两个主要文件：Slide-Level Labels（PRAD.csv）和ROI-Level Annotations（.geojson），分别提供了全面的元数据和诊断细节以及肿瘤区域的空间坐标。数据集还详细描述了重新注释和标签过程，包括案例的筛选、初级病理学家的初始注释、高级病理学家的验证和细化等步骤。此外，README文件还提供了数据集的使用方法、改进点、许可信息、贡献者和联系方式。

This dataset provides enhanced Gleason grading annotations for the TCGA PRAD prostate cancer dataset, supported by Region of Interest (ROI)-level spatial annotations. Developed in collaboration with Codatta and DPath.ai, where DPath.ai launched a dedicated community via Codatta to assemble a network of pathologists, this dataset improved accuracies and granularity of information in the original TCGA-PRAD dataset. The dataset includes two primary files: slide-level labels and ROI-level annotations. The motivation for the dataset is to improve the quality of diagnostic labels, particularly by introducing ROI annotations and detailed pathologist reasoning to differentiate Gleason tumor grades. The improvements include enhanced accuracy, granularity, and transparency. The dataset is used for AI training pipelines and pathology research. The dataset is licensed under OpenRAIL-M for non-commercial use, with commercial use requiring a separate license.