温岭市肺癌筛查与全生命周期管理高质量数据集

依托沈洪兵院士工作站台州分站和温岭市重点人群肺癌筛查工程，整合筛查、影像诊断、病理确诊、临床治疗及随访等环节数据，构建覆盖“筛查—诊断—治疗—随访—预后评估”的肺癌全生命周期多模态数据集。通过统一数据标准、标签体系及AI预标注+人工精标机制，实现影像、病理、检验、电子病历等多源数据结构化治理，支撑肺癌精准防控与医学人工智能模型研发。

Built upon the Taizhou Branch of the Shen Hongbing Academician Workstation and the key population lung cancer screening project in Wenling City, this dataset integrates data from multiple links including screening, imaging diagnosis, pathological confirmation, clinical treatment and follow-up, and constructs a multimodal dataset covering the full lifecycle of lung cancer, spanning from screening, diagnosis, treatment, follow-up to prognostic assessment. Through unified data standards, labeling systems and the mechanism combining AI pre-labeling and manual refined labeling, it realizes structured governance of multi-source data including imaging, pathology, laboratory tests and electronic medical records, and supports the precise prevention and control of lung cancer and the development of medical artificial intelligence models.

搜集汇总

背景与挑战

背景概述

该数据集整合了肺癌筛查、诊断、治疗及随访等全生命周期环节的多源数据，通过统一标准与AI+人工标注机制实现结构化治理。其1TB规模支撑肺癌精准防控与医学人工智能模型研发，适用于非商业学术研究。