Lippitt William L, Maier Lisa A, Fingerlin Tasha E, Lynch David A, Yadav Ruchi, Rieck Jared, Hill Andrew C, Liao Shu-Yi, Mroz Margaret M, Barkes Briana Q, Ju Chae Kum, Jeon Hwang Hye, Carlson Nichole E
Dept of Biostatistics and Informatics, Uni. of Colorado Anschutz Medical Campus, Aurora, CO, United States of America.
Dept of Medicine, National Jewish Health, Denver, CO, United States of America.
Phys Med Biol. 2025 Jan 13;70(2):025004. doi: 10.1088/1361-6560/ada19c.
. Sarcoidosis is a granulomatous disease affecting the lungs in over 90% of patients. Qualitative assessment of chest CT by radiologists is standard clinical practice and reliable quantification of disease from CT would support ongoing efforts to identify sarcoidosis phenotypes. Standard imaging feature engineering techniques such as radiomics suffer from extreme sensitivity to image acquisition and processing, potentially impeding generalizability of research to clinical populations. In this work, we instead investigate approaches to engineering variogram-based features with the intent to identify a robust, generalizable pipeline for image quantification in the study of sarcoidosis.. For a cohort of more than 300 individuals with sarcoidosis, we investigated 24 feature engineering pipelines differing by decisions for image registration to a template lung, empirical and model variogram estimation methods, and feature harmonization for CT scanner model, and subsequently 48 sets of phenotypes produced through unsupervised clustering. We then assessed sensitivity of engineered features, phenotypes produced through unsupervised clustering, and sarcoidosis disease signal strength to pipeline.. We found that variogram features had low to mild association with scanner model and associations were reduced by image registration. For each feature type, features were also typically robust to all pipeline decisions except image registration. Strength of disease signal as measured by association with pulmonary function testing and some radiologist visual assessments was strong (optimistic AUC ≈ 0.9,p≪0.0001in models for architectural distortion, conglomerate mass, fibrotic abnormality, and traction bronchiectasis) and fairly consistent across engineering approaches regardless of registration and harmonization for CT scanner.. Variogram-based features appear to be a suitable approach to image quantification in support of generalizable research in pulmonary sarcoidosis.
结节病是一种肉芽肿性疾病，超过90%的患者肺部会受到影响。放射科医生对胸部CT进行定性评估是标准的临床实践，而从CT中对疾病进行可靠量化将有助于正在进行的识别结节病表型的工作。诸如放射组学等标准成像特征工程技术对图像采集和处理极其敏感，这可能会阻碍研究向临床人群的推广。在这项工作中，我们转而研究基于变异函数的特征工程方法，旨在为结节病研究中的图像量化确定一个稳健、可推广的流程。对于一个由300多名结节病患者组成的队列，我们研究了24种特征工程流程，这些流程在将图像配准到模板肺、经验和模型变异函数估计方法以及CT扫描仪模型的特征协调方面存在差异，随后通过无监督聚类产生了48组表型。然后，我们评估了工程特征、通过无监督聚类产生的表型以及结节病疾病信号强度对流程的敏感性。我们发现变异函数特征与扫描仪模型的关联较低至中等，并且通过图像配准可以降低这种关联。对于每种特征类型，除了图像配准外，特征通常对所有流程决策都具有稳健性。通过与肺功能测试和一些放射科医生的视觉评估的关联来衡量的疾病信号强度很强（在用于结构扭曲、团块、纤维化异常和牵拉性支气管扩张的模型中，乐观的AUC≈0.9，p≪0.0001），并且无论CT扫描仪的配准和协调如何，在各种工程方法中都相当一致。基于变异函数的特征似乎是一种适合图像量化的方法，以支持肺部结节病的可推广研究。
