SPIE-AAPM-NCI Lung Nodule Classification Challenge Dataset

As part of the 2015 SPIE Medical Imaging Conference, SPIE – with the support of American Association of Physicists in Medicine (AAPM) and the National Cancer Institute (NCI) – conducted a “Grand Challenge” on quantitative image analysis methods for the diagnostic classification of malignant and benign lung nodules. The LUNGx Challenge provides a unique opportunity for participants to compare their algorithms to those of others from academia, industry, and government in a structured, direct way using the same data sets.
10 contrast-enhanced CT scans (5 scans with malignant nodules and 5 with benign nodules, prefix “CT-Training”) are a calibration dataset, representative of the technical properties of the test dataset (60 scans, prefix “LUNGx”). Dataset contains: Images, Nodule locations and 'truth' labels.
If you use these data outside the LUNGx Challenge please acknowledge the SPIE, the NCI, the AAPM, and The University of Chicago. An article describing the lessons learned is at https://doi.org/10.1117/1.JMI.2.2.020103. The corresponding scientific manuscript is at https://doi.org/10.1117/1.JMI.3.4.044506 . For the full data set, including the answers to the test data, see the SPIE-AAPM-NCI Lung Nodule Classification Challenge page.

2015年，国际光学工程学会（SPIE）在美国医学物理学家协会（AAPM）与美国国家癌症研究所（NCI）的支持下，于SPIE医疗成像大会期间举办了一场针对良恶性肺结节诊断分类的定量图像分析方法“大奖赛（Grand Challenge）”。本次LUNGx挑战赛为参与者提供了独特契机：可在结构化的直接对比框架下，使用统一数据集，将自身研发的算法与学术界、工业界及政府机构的同类算法进行性能对标。

本次挑战赛的数据集包含两类：其一为校准数据集，涵盖10例增强CT（contrast-enhanced CT）扫描影像，其中5例携带恶性肺结节、5例携带良性肺结节，影像前缀为"CT-Training"，该数据集的技术参数与测试数据集保持一致；测试数据集共60例扫描影像，前缀为"LUNGx"。数据集内容包含影像数据、肺结节位置标注以及“真值”标签。

若在LUNGx挑战赛范畴外使用本数据集，请务必致谢SPIE、NCI、AAPM及芝加哥大学。相关经验总结文章的DOI链接为https://doi.org/10.1117/1.JMI.2.2.020103，对应的科学研究手稿DOI链接为https://doi.org/10.1117/1.JMI.3.4.044506。如需获取包含测试集答案的完整数据集，请访问SPIE-AAPM-NCI肺结节分类挑战赛官方页面。