Weikert Thomas, Friebe Liene, Wilder-Smith Adrian, Yang Shan, Sperl Jonathan I, Neumann Dominik, Balachandran Abishek, Bremerich Jens, Sauter Alexander W
Department of Radiology, University Hospital Basel, University of Basel, Petersgraben 4, 4031 Basel, Switzerland.
Department of Radiology, University Hospital Basel, University of Basel, Petersgraben 4, 4031 Basel, Switzerland.
Eur J Radiol. 2022 Oct;155:110460. doi: 10.1016/j.ejrad.2022.110460. Epub 2022 Aug 3.
Airway wall thickening is a consequence of chronic inflammatory processes and usually only qualitatively described in CT radiology reports. The purpose of this study is to automatically quantify airway wall thickness in multiple airway generations and assess the diagnostic potential of this parameter in a large cohort of patients with Chronic Obstructive Pulmonary Disease (COPD).
This retrospective, single-center study included a series of unenhanced chest CTs. Inclusion criteria were the mentioning of an explicit COPD GOLD stage in the written radiology report and time period (01/2019-12/2021). A control group included chest CTs with completely unremarkable lungs according to the report. The DICOM images of all cases (axial orientation; slice-thickness: 1 mm; soft-tissue kernel) were processed by an AI algorithm pipeline consisting of (A) a 3D-U-Net for det detection and tracing of the bronchial tree centerlines (B) extraction of image patches perpendicular to the centerlines of the bronchi, and (C) a 2D U-Net for segmentation of airway walls on those patches. The performance of centerline detection and wall segmentation was assessed. The imaging parameter average wall thickness was calculated for bronchus generations 3-8 (AWT) across the lungs. Mean AWT was compared between five groups (control, COPD Gold I-IV) using non-parametric statistics. Furthermore, the established emphysema score %LAV-950 was calculated and used to classify scans (normal vs. COPD) alone and in combination with AWT RESULTS: A total of 575 chest CTs were processed. Algorithm performance was very good (airway centerline detection sensitivity: 86.9%; airway wall segmentation Dice score: 0.86). AWT was statistically significantly greater in COPD patients compared to controls (2.03 vs. 1.87 mm, p < 0.001) and increased with COPD stage. The classifier that combined %LAV-950 and AWT was superior to the classifier using only %LAV-950 (AUC = 0.92 vs. 0.79).
Airway wall thickness increases in patients suffering from COPD and is automatically quantifiable. AWT could become a CT imaging parameter in COPD complementing the established emphysema biomarker %LAV-950.
Quantitative measurements considering the complete visible bronchial tree instead of qualitative description could enhance radiology reports, allow for precise monitoring of disease progression and diagnosis of early stages of disease.
气道壁增厚是慢性炎症过程的结果，通常仅在CT放射学报告中进行定性描述。本研究的目的是自动量化多个气道代的气道壁厚度，并评估该参数在一大群慢性阻塞性肺疾病（COPD）患者中的诊断潜力。
这项回顾性单中心研究纳入了一系列未增强的胸部CT。纳入标准为在书面放射学报告中提及明确的COPD GOLD分期以及时间段（2019年1月至2021年12月）。对照组包括根据报告肺部完全正常的胸部CT。所有病例的DICOM图像（轴向；层厚：1mm；软组织内核）由一个人工智能算法管道处理，该管道包括：（A）用于检测和追踪支气管树中心线的3D-U-Net；（B）提取垂直于支气管中心线的图像块；（C）用于在这些图像块上分割气道壁的2D U-Net。评估中心线检测和壁分割的性能。计算肺部第3-8代支气管的成像参数平均壁厚度（AWT）。使用非参数统计比较五组（对照组、COPD Gold I-IV）之间的平均AWT。此外，计算既定的肺气肿评分%LAV-950，并单独以及与AWT联合用于对扫描进行分类（正常与COPD）。结果：共处理了575例胸部CT。算法性能非常好（气道中心线检测灵敏度：86.9%；气道壁分割Dice评分：0.86）。与对照组相比，COPD患者的AWT在统计学上显著更高（2.03对1.87mm，p<0.001），并且随COPD分期增加。结合%LAV-950和AWT的分类器优于仅使用%LAV-950的分类器（AUC=0.92对0.79）。
COPD患者的气道壁厚度增加且可自动量化。AWT可能成为COPD的CT成像参数，补充既定的肺气肿生物标志物%LAV-950。
考虑整个可见支气管树的定量测量而非定性描述可以增强放射学报告，允许对疾病进展进行精确监测并诊断疾病早期阶段。
