Lung cancer segmentation dataset with Lung-RADS class

The lung cancer segmentation dataset comprises CT images paired with corresponding lung cancer masks, meticulously labeled by radiologists according to the Lung-RADS System. This dataset is a fusion of original Kazakhstani local data from the Kazakh Research Institute of Oncology and Radiology, and the openly available LIDC-IDRI dataset [1], which has been re-labeled. The entire dataset has been divided into training and testing sets, with the training set consisting of 708 CT images and the test set containing 264 CT images. All images share a standardized labeling format: • label1 – class according to Lung-RADS System • mask – binary mask of lung cancer area • hu_array_old – CT image converted standardized in Hounsfield Units • hu_array – CT image with dropped non-lung area via thresholding-based algorithm Important! Fields label1 and mask have been manually labeled by the doctor-radiologist, hu_array has been labeled via automated thresholding-based algorithm and was not additionally checked by the human eye. [1] Armato III, S. G., McLennan, G., Bidaut, L., McNitt-Gray, M. F., Meyer, C. R., Reeves, A. P., Zhao, B., Aberle, D. R., Henschke, C. I., Hoffman, E. A., Kazerooni, E. A., MacMahon, H., Van Beek, E. J. R., Yankelevitz, D., Biancardi, A. M., Bland, P. H., Brown, M. S., Engelmann, R. M., Laderach, G. E., Max, D., Pais, R. C. , Qing, D. P. Y. , Roberts, R. Y., Smith, A. R., Starkey, A., Batra, P., Caligiuri, P., Farooqi, A., Gladish, G. W., Jude, C. M., Munden, R. F., Petkovska, I., Quint, L. E., Schwartz, L. H., Sundaram, B., Dodd, L. E., Fenimore, C., Gur, D., Petrick, N., Freymann, J., Kirby, J., Hughes, B., Casteele, A. V., Gupte, S., Sallam, M., Heath, M. D., Kuhn, M. H., Dharaiya, E., Burns, R., Fryd, D. S., Salganicoff, M., Anand, V., Shreter, U., Vastagh, S., Croft, B. Y., Clarke, L. P. (2015). Data From LIDC-IDRI [Data set]. The Cancer Imaging Archive, doi: https://doi.org/10.7937/K9/TCIA.2015.LO9QL9SX

本肺癌分割数据集由成对CT（Computed Tomography）图像与对应肺癌掩码组成，所有标注均由放射科医师依据肺影像报告和数据系统（Lung-RADS System）完成，标注过程严谨精细。本数据集融合了哈萨克斯坦肿瘤与放射学研究所（Kazakh Research Institute of Oncology and Radiology）的本土原始临床数据，以及经重新标注的公开可用LIDC-IDRI数据集[1]。全数据集已划分为训练集与测试集：其中训练集包含708张CT图像，测试集包含264张CT图像。所有图像采用统一的标注格式，具体如下：
• label1：依据Lung-RADS系统划分的病变类别
• mask：肺癌区域的二值掩码
• hu_array_old：经标准化转换为亨氏单位（Hounsfield Units）的CT图像
• hu_array：通过基于阈值的算法剔除非肺区域后的CT图像
重要提示：label1与mask字段均由放射科医师手动标注；hu_array字段通过自动化阈值算法完成标注，未经过人工额外核验。
[1] Armato III, S. G., McLennan, G., Bidaut, L., McNitt-Gray, M. F., Meyer, C. R., Reeves, A. P., Zhao, B., Aberle, D. R., Henschke, C. I., Hoffman, E. A., Kazerooni, E. A., MacMahon, H., Van Beek, E. J. R., Yankelevitz, D., Biancardi, A. M., Bland, P. H., Brown, M. S., Engelmann, R. M., Laderach, G. E., Max, D., Pais, R. C., Qing, D. P. Y., Roberts, R. Y., Smith, A. R., Starkey, A., Batra, P., Caligiuri, P., Farooqi, A., Gladish, G. W., Jude, C. M., Munden, R. F., Petkovska, I., Quint, L. E., Schwartz, L. H., Sundaram, B., Dodd, L. E., Fenimore, C., Gur, D., Petrick, N., Freymann, J., Kirby, J., Hughes, B., Casteele, A. V., Gupte, S., Sallam, M., Heath, M. D., Kuhn, M. H., Dharaiya, E., Burns, R., Fryd, D. S., Salganicoff, M., Anand, V., Shreter, U., Vastagh, S., Croft, B. Y., Clarke, L. P. (2015). LIDC-IDRI数据集[数据集]. 癌症影像档案库, doi: https://doi.org/10.7937/K9/TCIA.2015.LO9QL9SX

搜集汇总

背景与挑战

背景概述

该数据集是一个用于肺癌分割的CT影像数据集，包含972张CT图像（训练集708张、测试集264张），每张图像均配有由放射科医生根据Lung-RADS系统手动标注的肺癌区域掩码和类别标签。数据集融合了哈萨克斯坦本地数据和公开的LIDC-IDRI数据集，并提供了标准化预处理（如Hounsfield单位转换和去除非肺区域），适用于肺癌自动分割和分类模型的开发与评估。