Artificial Intelligence-based CT Assessment of Bronchiectasis: The COPDGene Study

Abstract

Background CT is the standard method used to assess bronchiectasis. A higher airway-to-artery diameter ratio (AAR) is typically used to identify enlarged bronchi and bronchiectasis; however, current imaging methods are limited in assessing the extent of this metric in CT scans. Purpose To determine the extent of AARs using an artificial intelligence-based chest CT and assess the association of AARs with exacerbations over time. Materials and Methods In a secondary analysis of ever-smokers from the prospective, observational, multicenter COPDGene study, AARs were quantified using an artificial intelligence tool. The percentage of airways with AAR greater than 1 (a measure of airway dilatation) in each participant on chest CT scans was determined. Pulmonary exacerbations were prospectively determined through biannual follow-up (from July 2009 to September 2021). Multivariable zero-inflated regression models were used to assess the association between the percentage of airways with AAR greater than 1 and the total number of pulmonary exacerbations over follow-up. Covariates included demographics, lung function, and conventional CT parameters. Results Among 4192 participants (median age, 59 years; IQR, 52-67 years; 1878 men [45%]), 1834 had chronic obstructive pulmonary disease (COPD). During a 10-year follow-up and in adjusted models, the percentage of airways with AARs greater than 1 (quartile 4 vs 1) was associated with a higher total number of exacerbations (risk ratio [RR], 1.08; 95% CI: 1.02, 1.15; P = .01). In participants meeting clinical and imaging criteria of bronchiectasis (ie, clinical manifestations with ≥3% of AARs >1) versus those who did not, the RR was 1.37 (95% CI: 1.31, 1.43; P < .001). Among participants with COPD, the corresponding RRs were 1.10 (95% CI: 1.02, 1.18; P = .02) and 1.32 (95% CI: 1.26, 1.39; P < .001), respectively. Conclusion In ever-smokers with chronic obstructive pulmonary disease, artificial intelligence-based CT measures of bronchiectasis were associated with more exacerbations over time. Clinical trial registration no. NCT00608764 © RSNA, 2022 Supplemental material is available for this article. See also the editorial by Schiebler and Seo in this issue.

Graphical abstract

Figure 1:

Flowchart of COPDGene participant selection. A percentage of airway-to-artery diameter ratio (AAR) greater than 1 is the percentage of artificial intelligence (AI)–based AARs greater than 1.

Figure 2:

Three-dimensional CT reconstructions of the pulmonary arterial and bronchial trees. (A, C) The pulmonary arterial tree is color-coded, with cyan and blue indicating large and small branches, respectively, and the bronchial tree is color-coded, with red and orange indicating large and small branches, respectively. (A, B) Images in a 66-year-old woman with chronic obstructive pulmonary disease (COPD) without bronchiectasis. (C, D) Images in an 80-year-old woman with COPD with bronchiectasis (arrowheads in D). (B, D) Images show the percentage of artificial intelligence–based airway-to-artery diameter ratios (AARs) greater than 1.

Figure 3:

Matching process to compute artificial intelligence-based CT measurements of the airway-to-artery diameter ratios (AARs). (A) An airway with an accompanying pulmonary artery selected (green rectangle) to illustrate the process. (B) Particles in the airway lumen and accompanying artery. Dashed lines indicate airway and artery particles that match each other (ie, matching candidate pairs). The green ellipse depicts the airway-to-artery particle pair used to compute an AAR. The technique calculates thousands of AARs per CT image.

Figure 4:

(A, B) Forest plots of the association of the percentage of airway-to-artery diameter ratios (AAR) greater than 1 at CT (quartile 4 vs 1) alone (A) and a high percentage of AAR greater than 1 (≥3%) and clinical manifestations (B) with exacerbations over time, according to spirometric and phenotypic groups. The estimates represent the risk ratio (RRs) of the total number of exacerbations during the follow-up time and 95% CIs from multivariable Poisson zero-inflated models. The model included all quartiles, and the figure reported estimates for quartile 4 only, using quartile 1 as a reference. COPD = chronic obstructive pulmonary disease, PRISm = preserved ratio impaired spirometry.