Duke Lung Cancer Screening Dataset 2024

Note - This is part 1 of the dataset.Part 1 can be found at : https://zenodo.org/records/13799069 Part 2 can be found at : https://zenodo.org/records/12784601Part 3 can be found at : https://zenodo.org/records/14659131

Background: Lung cancer risk classification is an increasingly important area of research as low-dose thoracic CT screening programs have become standard of care for patients at high risk for lung cancer. There is limited availability of large, annotated public databases for the training and testing of algorithms for lung nodule classification.

Methods: Screening chest CT scans done between January 1, 2015 and June 30, 2021 at Duke University Health System were considered for this study. Efficient nodule annotation was performed semi-automatically by using a publicly available deep learning nodule detection algorithm trained on the LUNA16 dataset to identify initial candidates, which were then accepted based on nodule location in the radiology text report or manually annotated by a medical student and a fellowship-trained cardiothoracic radiologist.

Results: The dataset contains 1613 CT volumes with 2487 annotated nodules, selected from a total dataset of 2061 patients, with the remaining data reserved for future testing. Radiologist spot-checking confirmed the semi-automated annotation had an accuracy rate of >90%.

Conclusions: The Duke Lung Cancer Screening Dataset 2024 is the first large dataset for CT screening for lung cancer reflecting the use of current CT technology. This represents a useful resource of lung cancer risk classification research, and the efficient annotation methods described for its creation may be used to generate similar databases for research in the future.Dataset part Details:Part 1: DLCS subset 1 to 7 and, metadata and Annotations.Part 2: DLCS subset 8,9 and CT image info metadata.Part 3: DLCS subset 10.

Updates and Versions:

Part 1, Version 1.0 (Published on [03/05/2024]): Released initial dataset, including partial data subsets 1 to 7 and 3D bounding box annotations of the lung nodules.

Part 1, Version 1.1 (Published on [09/19/2024]): Added metadata file (DLCSD24_metadata_v1.1.xlsx) and updated the dataset description and title. 10.5281/zenodo.13799069

Part 2, Version 1.0 (Published on [02/04/2025]): Released DLCS subset 8,9, CT image info metadata (DLCSD24_CT_ImageInfo_v1.csv and metadata documentation).

Part 3, Version 1.0 (Published on [02/04/2025]): Released DLCS subset 10.

Code Repository:To support reproducible open-access research and benchmarking, we have shared several pre-trained models and baseline results in a GitHub and GitLab repository.

GitLab: https://gitlab.oit.duke.edu/cvit-public/ai_lung_health_benchmarkingGitHub: https://github.com/fitushar/AI-in-Lung-Health-Benchmarking-Detection-and-Diagnostic-Models-Across-Multiple-CT-Scan-Datasets

Funding:This work was supported by the Duke Department of Radiology Charles E. Putman Vision Award, NIH/NIBIB P41-EB028744, and NIH/NCI R01-CA261457.

注意：本数据集为第一部分。第一部分获取链接：https://zenodo.org/records/13799069；第二部分获取链接：https://zenodo.org/records/12784601；第三部分获取链接：https://zenodo.org/records/14659131

研究背景：随着低剂量胸部CT筛查方案成为肺癌高危患者的标准诊疗手段，肺癌风险分类研究的重要性日益凸显。当前用于肺结节分类算法训练与测试的大规模标注公共数据库仍较为匮乏。

研究方法：本研究纳入2015年1月1日至2021年6月30日期间，杜克大学健康系统完成的胸部CT筛查扫描影像。本研究采用半自动化方式高效完成结节标注：首先依托在LUNA16数据集（LUNA16 dataset）上训练的公开深度学习肺结节检测算法，生成初始候选结节；随后结合放射科文本报告中的结节位置信息对候选结节进行筛选，或由医学生及接受过心胸放射专科进修培训的放射科医师进行手动标注。

研究结果：本数据集从2061例患者的整体数据集中筛选得到1613例CT容积数据，共计2487个标注肺结节，剩余数据将留待后续测试使用。经放射科医师现场抽验确认，半自动化标注的准确率超过90%。

研究结论：杜克大学肺癌筛查数据集2024（Duke Lung Cancer Screening Dataset 2024）是首个反映当前CT技术应用情况的大规模肺癌CT筛查数据集。该数据集可为肺癌风险分类研究提供宝贵的研究资源，其构建过程中采用的高效标注方法，未来可用于生成同类研究所需的相似数据库。
数据集分卷详情：
第一部分：DLCS子集1至7，以及元数据与标注文件；
第二部分：DLCS子集8、9，以及CT影像信息元数据；
第三部分：DLCS子集10。

更新与版本信息：
第一部分 版本1.0（发布于2024年3月5日）：发布初始数据集，包含子集1至7的部分数据以及肺结节的三维边界框标注信息。
第一部分 版本1.1（发布于2024年9月19日）：新增元数据文件（DLCSD24_metadata_v1.1.xlsx），并更新了数据集描述与标题，DOI：10.5281/zenodo.13799069。
第二部分 版本1.0（发布于2025年2月4日）：发布DLCS子集8、9，以及CT影像信息元数据（DLCSD24_CT_ImageInfo_v1.csv与元数据文档）。
第三部分 版本1.0（发布于2025年2月4日）：发布DLCS子集10。

代码仓库：为支持可复现的开放获取研究与基准测试，我们在GitHub与GitLab仓库中共享了多个预训练模型与基准测试结果。
GitLab：https://gitlab.oit.duke.edu/cvit-public/ai_lung_health_benchmarking
GitHub：https://github.com/fitushar/AI-in-Lung-Health-Benchmarking-Detection-and-Diagnostic-Models-Across-Multiple-CT-Scan-Datasets

资助信息：本研究得到杜克大学放射科Charles E. Putman视觉奖、美国国立卫生研究院/国家生物医学成像与生物工程研究所（National Institutes of Health/National Institute of Biomedical Imaging and Bioengineering, NIH/NIBIB）P41-EB028744以及美国国立卫生研究院/国家癌症研究所（National Institutes of Health/National Cancer Institute, NIH/NCI）R01-CA261457的支持。