胃癌胃镜活检病理与术前 CT 分期匹配高质量数据集

本数据集聚焦胃癌胃镜活检病理与术前CT分期匹配核心方向，原始数据均从合作三甲医院合规采集，经专业团队完成数据脱敏与文件校对全流程处理，最终形成高质量、标准化的专业医疗数据集，数据总量级达1TB，可直接对接医疗算法研发、模型训练、临床研究等各类应用场景，为胃癌相关人工智能技术开发、临床诊疗研究、医疗产品创新提供高价值、高可靠性的数据支撑。 数据集整体为多模态结构化医疗数据，单条数据围绕胃癌胃镜活检病理与术前CT分期匹配临床诊疗全维度构建，核心包含影像类数据与临床诊疗文本标注类数据两大类别。影像类数据为dicom格式原始影片，保留临床采集原始影像信息，格式标准化、信息完整度高；临床诊疗文本标注类数据涵盖住院病程、住院/出院记录、病理检验报告、放射及化验图文报告等核心医疗文件，字段信息完整覆盖胃癌胃镜活检病理与术前CT分期匹配临床诊疗的影像采集、病情诊断、检查分析、分期评估全流程，标注内容精准规范，与影像数据一一匹配，真实还原胃癌胃镜活检病理与术前CT分期匹配临床诊疗的实际场景与数据特征。This dataset centers on the core task of matching gastroscopic biopsy pathology results with preoperative CT staging for gastric cancer. All raw data were collected compliantly from cooperating tertiary hospitals, and underwent full-process processing including data de-identification and document proofreading by a professional team. Finally, a high-quality, standardized professional medical dataset was formed, with a total data volume of 1 TB. It can be directly applied to various scenarios such as medical algorithm development, model training, and clinical research, providing high-value and highly reliable data support for the development of AI-related technologies for gastric cancer, clinical diagnosis and treatment research, and medical product innovation. The dataset is overall multi-modal structured medical data. Each data entry is constructed based on the full dimensions of clinical diagnosis and treatment for matching gastroscopic biopsy pathology with preoperative CT staging for gastric cancer, and mainly includes two categories: imaging data and clinical diagnosis and treatment text annotation data. The imaging data are original DICOM-format images, which retain the original clinical imaging information, with standardized format and high information integrity. The clinical diagnosis and treatment text annotation data cover core medical documents such as hospital course records, inpatient/discharge summaries, pathological examination reports, and radiological and laboratory report documents. The field information fully covers the entire clinical diagnosis and treatment process for matching gastroscopic biopsy pathology with preoperative CT staging for gastric cancer, including image collection, disease diagnosis, examination analysis, and staging evaluation. The annotation content is accurate and standardized, and is one-to-one matched with the imaging data, truly restoring the actual clinical scenarios and data characteristics of matching gastroscopic biopsy pathology with preoperative CT staging for gastric cancer.

搜集汇总

背景与挑战

背景概述

该数据集聚焦胃癌胃镜活检病理与术前CT分期匹配，数据源自合作三甲医院，经脱敏和标准化处理后形成1TB规模的多模态结构化医疗数据。数据集包含DICOM格式影像和临床诊疗文本标注，完整覆盖诊疗全流程，适用于医疗AI模型训练和临床研究等场景。