Department of Biostatistics and Informatics, Colorado School of Public Health, 13001 E 17th Pl, Aurora, CO 80045.
Center for Genes, Environment, and Health, National Jewish Health, Denver, Colorado.
Acad Radiol. 2020 Aug;27(8):e204-e215. doi: 10.1016/j.acra.2019.10.030. Epub 2019 Dec 13.
A standard lung template could improve population-level analyses for computed tomography (CT) scans of the lung. We develop a fully automated preprocessing pipeline for image analysis of the lungs using updated methodologies and R software that results in the creation of a standard lung template. We apply this pipeline to CT scans from a sarcoidosis population, exploring the influence of registration on radiomic analyses.
Using 65 high-resolution CT scans from healthy adults, we create a standard lung template by segmenting the left and right lungs, nonlinearly registering lung masks to an initial template mask, and using an unbiased, iterative procedure to converge to a standard lung shape (Dice similarity coefficient ≥0.99). We compare three-dimensional radiomic features between control and sarcoidosis patients, before and after registration to a study-specific lung template.
The final lung template had a right lung volume of 2967 cm and left lung volume of 2623 cm, with a median HU = -862. Registration significantly affected radiomic features, shifting the HU distribution to the left, decreasing variability, and increasing smoothness (p < 0.0001). The registration improved detective ability of radiomics; for contrast, autocorrelation, energy, and homogeneity, the group effect was significant postregistration (p < 0.05), but was not significant preregistration.
The final lung template and software used for its creation are publicly available via the lungct R package to facilitate its use in practice. This study advances lung imaging by developing tools to improve population-level analyses for various lung diseases.
标准肺模板可以提高针对肺部 CT 扫描的人群水平分析。我们使用更新的方法和 R 软件，为肺部图像分析开发了一个完全自动化的预处理流水线，从而生成标准肺模板。我们将该流水线应用于结节病人群的 CT 扫描，探索配准对放射组学分析的影响。
我们使用 65 例健康成年人的高分辨率 CT 扫描，通过对左右肺进行分割、将肺掩模非线性配准到初始模板掩模，以及使用无偏、迭代的方法收敛到标准肺形状（Dice 相似系数≥0.99），来创建标准肺模板。我们比较了在注册到特定于研究的肺模板之前和之后，对照组和结节病患者之间的三维放射组学特征。
最终的肺模板右侧肺容积为 2967 cm，左侧肺容积为 2623 cm，中位数 HU 值为-862。配准显著影响放射组学特征，使 HU 分布向左移动，降低变异性，增加平滑度（p<0.0001）。配准提高了放射组学的检测能力；相比之下，自相关、能量和同质性的组间效应在配准后具有统计学意义（p<0.05），而在配准前则没有统计学意义。
最终的肺模板及其创建所使用的软件可通过 lungct R 包公开获得，以促进其在实践中的使用。本研究通过开发用于各种肺部疾病的人群水平分析的工具来推进肺部成像。
