LUNA16
肺结节分析2016（LUNA16）是医学影像分析领域的经典基准数据集，通过对广泛使用的公开肺结节数据集LIDC-IDRI进行数据清洗和标注而获得。LIDC-IDRI包含1018例低剂量肺部CT影像。从LIDC-IDRI中剔除了层厚大于3mm以及肺结节小于3mm的影像后，形成了现在的LUNA16数据集。LUNA16挑战赛的主要目标是评估自动肺结节检测算法的性能。通过这一挑战赛，主办方希望推动计算机辅助检测（CAD, Computer-Aided Detection）系统的发展，帮助放射科医生更准确地从CT扫描中发现肺结节，从而提高肺癌早期检测和治疗的机会。
xiongbu可视化图片
LUNA16_3.webp
LUNA16_2.webp
LUNA16_1.webp
数据集元信息
| 维度 | 3D |
| 模态 | ct |
| 任务类型 | segmentation |
| 解剖结构 | 肺/肺结节 |
| 解剖区域 | 胸部 |
| 类别数 | 1 |
| 数据量 | 888 |
| 文件格式 | .mhd |
文件结构
LUNA16
├── subset0.zip
├── subset1.zip
├── ...
├── subset9.zip
├── seg-lungs-LUNA16.zip
├── annotations.csv
├── candidates.csv图像尺寸统计
| 统计类型 | 间距 (mm) | 尺寸 |
|---|---|---|
| 最小值 | (1.00, 1.00, 1.00) |
(512, 512, 95) |
| 中位值 | (1.00, 1.00, 1.00) |
(512, 512, 237) |
| 最大值 | (1.00, 1.00, 1.00) |
(512, 512, 764) |
引用
@article{SETIO20171,
title = {Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: The LUNA16 challenge},
journal = {Medical Image Analysis},
volume = {42},
pages = {1-13},
year = {2017},
issn = {1361-8415},
doi = {https://doi.org/10.1016/j.media.2017.06.015},
url = {https://www.sciencedirect.com/science/article/pii/S1361841517301020},
author = {Arnaud Arindra Adiyoso Setio and Alberto Traverso and Thomas {de Bel} and Moira S.N. Berens and Cas van den Bogaard and Piergiorgio Cerello and Hao Chen and Qi Dou and Maria Evelina Fantacci and Bram Geurts and Robbert van der Gugten and Pheng Ann Heng and Bart Jansen and Michael M.J. {de Kaste} and Valentin Kotov and Jack Yu-Hung Lin and Jeroen T.M.C. Manders and Alexander Sóñora-Mengana and Juan Carlos García-Naranjo and Evgenia Papavasileiou and Mathias Prokop and Marco Saletta and Cornelia M Schaefer-Prokop and Ernst T. Scholten and Luuk Scholten and Miranda M. Snoeren and Ernesto Lopez Torres and Jef Vandemeulebroucke and Nicole Walasek and Guido C.A. Zuidhof and Bram van Ginneken and Colin Jacobs}
}