Panlobular emphysema is associated with COPD disease severity: A study of emphysema subtype by computed tomography

Evaluating the Cumulative Benefit of Inspiratory CT, Expiratory CT, and Clinical Data for COPD Diagnosis and Staging through Deep Learning

Purpose To measure the benefit of single-phase CT, inspiratory-expiratory CT, and clinical data for convolutional neural network (CNN)-based chronic obstructive pulmonary disease (COPD) staging. Materials and Methods This retrospective study included inspiratory and expiratory lung CT images and spirometry measurements acquired between November 2007 and April 2011 from 8893 participants (mean age, 59.6 years ± 9.0 [SD]; 53.3% [4738 of 8893] male) in the COPDGene phase I cohort (ClinicalTrials.gov: NCT00608764). CNNs were trained to predict spirometry measurements (forced expiratory volume in 1 second [FEV1], FEV1 percent predicted, and ratio of FEV1 to forced vital capacity [FEV1/FVC]) using clinical data and either single-phase or multiphase CT. Spirometry predictions were then used to predict Global Initiative for Chronic Obstructive Lung Disease (GOLD) stage. Agreement between CNN-predicted and reference standard spirometry measurements and GOLD stage was assessed using intraclass correlation coefficient (ICC) and compared using bootstrapping. Accuracy for predicting GOLD stage, within-one GOLD stage, and GOLD 0 versus 1-4 was calculated. Results CNN-predicted and reference standard spirometry measurements showed moderate to good agreement (ICC, 0.66-0.79), which improved by inclusion of clinical data (ICC, 0.70-0.85; P ≤ .04), except for FEV1/FVC in the inspiratory-phase CNN model with clinical data (P = .35) and FEV1 in the expiratory-phase CNN model with clinical data (P = .33). Single-phase CNN accuracies for GOLD stage, within-one stage, and diagnosis ranged from 59.8% to 84.1% (682-959 of 1140), with moderate to good agreement (ICC, 0.68-0.70). Accuracies of CNN models using inspiratory and expiratory images ranged from 60.0% to 86.3% (684-984 of 1140), with moderate to good agreement (ICC, 0.72). Inclusion of clinical data improved agreement and accuracy for both the single-phase CNNs (ICC, 0.72; P ≤ .001; accuracy, 65.2%-85.8% [743-978 of 1140]) and inspiratory-expiratory CNNs (ICC, 0.77-0.78; P ≤ .001; accuracy, 67.6%-88.0% [771-1003 of 1140]), except expiratory CNN with clinical data (no change in GOLD stage ICC; P = .08). Conclusion CNN-based COPD diagnosis and staging using single-phase CT provides comparable accuracy with inspiratory-expiratory CT when provided clinical data relevant to staging. Keywords: Convolutional Neural Network, Chronic Obstructive Pulmonary Disease, CT, Severity Staging, Attention Map Supplemental material is available for this article. © RSNA, 2024.

Lung imaging in COPD and asthma

Chronic obstructive pulmonary disease (COPD) and asthma are common lung diseases with heterogeneous clinical presentations. Lung imaging allows evaluations of underlying pathophysiological changes and provides additional personalized approaches for disease management. This narrative review provides an overview of recent advances in chest imaging analysis using various modalities, such as computed tomography (CT), dynamic chest radiography, and magnetic resonance imaging (MRI). Visual CT assessment localizes emphysema subtypes and mucus plugging in the airways. Dedicated software quantifies the severity and spatial distribution of emphysema and the airway tree structure, including the central airway wall thickness, branch count and fractal dimension of the tree, and airway-to-lung size ratio. Nonrigid registration of inspiratory and expiratory CT scans quantifies small airway dysfunction, local volume changes and shape deformations in specific regions. Lung ventilation and diaphragm movement are also evaluated on dynamic chest radiography. Functional MRI detects regional oxygen transfer across the alveolus using inhaled oxygen and ventilation defects and gas diffusion into the alveolar-capillary barrier tissue and red blood cells using inhaled hyperpolarized 129Xe gas. These methods have the potential to determine local functional properties in the lungs that cannot be detected by lung function tests in patients with COPD and asthma. Further studies are needed to apply these technologies in clinical practice, particularly for early disease detection and tailor-made interventions, such as the efficient selection of patients likely to respond to biologics. Moreover, research should focus on the extension of healthy life expectancy in patients at higher risk and with established diseases.

Advancements in automated classification of chronic obstructive pulmonary disease based on computed tomography imaging features through deep learning approaches

Chronic Obstructive Pulmonary Disease (COPD) represents a global public health issue that significantly impairs patients' quality of life and overall health. As one of the primary causes of chronic respiratory diseases and global mortality, effective diagnosis and classification of COPD are crucial for clinical management. Pulmonary function tests (PFTs) are standard for diagnosing COPD, yet their accuracy is influenced by patient compliance and other factors, and they struggle to detect early disease pathologies. Furthermore, the complexity of COPD pathological changes poses additional challenges for clinical diagnosis, increasing the difficulty for physicians in practice. Recently, deep learning (DL) technologies have demonstrated significant potential in medical image analysis, particularly for the diagnosis and classification of COPD. By analyzing key radiological features such as airway alterations, emphysema, and vascular characteristics in Computed Tomography (CT) scan images, DL enhances diagnostic accuracy and efficiency, providing more precise treatment plans for COPD patients. This article reviews the latest research advancements in DL methods based on principal radiological features of COPD for its classification and discusses the advantages, challenges, and future research directions of DL in this field, aiming to provide new perspectives for the personalized management and treatment of COPD.

Association of bronchial disease on CT imaging and clinical definitions of chronic bronchitis in a single-center COPD phenotyping study

INTRODUCTION

Chronic Bronchitis (CB) represents a phenotype of chronic obstructive pulmonary disease (COPD). While several definitions have been used for diagnosis, the relationship between clinical definitions and radiologic assessment of bronchial disease (BD) has not been well studied. The aim of this study was to evaluate the relationship between three clinical definitions of CB and radiographic findings of BD in spirometry-defined COPD patients.

METHODS

A cross-sectional analysis was performed from a COPD phenotyping study. It was a prospective observational cohort. Participants had spirometry-defined COPD and available chest CT imaging. Comparison between CB definitions, Medical Research Council (CBMRC), St. George's Respiratory Questionnaire (CBSGRQ), COPD Assessment Test (CBCAT) and CT findings were performed using Cohen's Kappa, univariate and multivariate logistic regressions.

RESULTS

Of 112 participants, 83 met inclusion criteria. Demographics included age of 70.1 ± 7.0 years old, predominantly male (59.0 %), 45.8 ± 30.8 pack-year history, 21.7 % actively smoking, and mean FEV1 61.5 ± 21.1 %. With MRC, SGRQ and CAT definitions, 22.9 %, 36.6 % and 28.0 % had CB, respectively. BD was more often present in CB compared to non-CB patients; however, it did not have a statistically significant relationship between any of the CB definitions. CBSGRQ had better agreement with radiographically assessed BD compared to the other two definitions.

CONCLUSION

Identification of BD on CT was associated with the diagnoses of CB. However, agreement between imaging and definitions were not significant, suggesting radiologic findings of BD and criteria defining CB may not identify the same COPD phenotype. Research to standardize imaging and clinical methods is needed for more objective identification of COPD phenotypes.

Analysis of Airway Thickening and Serum Cytokines in COPD Patients with Frequent Exacerbations: A Heart of the Matter

Background

Differences in lung function for Chronic Obstructive Pulmonary Disease (COPD) cause bias in the findings when identifying frequent exacerbator phenotype-related causes. The aim of this study was to determine whether computed tomographic (CT) biomarkers and circulating inflammatory biomarkers were associated with the COPD frequent exacerbator phenotype after eliminating the differences in lung function between a frequent exacerbator (FE) group and a non-frequent exacerbator (NFE) group.

Methods

A total of 212 patients with stable COPD were divided into a FE group (n=106) and a NFE group (n=106) according to their exacerbation history. These patients were assessed by spirometry, quantitative CT measurements and blood sample measurements during their stable phase. Univariate and multivariate logistic regression were used to assess the association between airway thickening or serum cytokines and the COPD frequent exacerbator phenotype. Receiver operating characteristic (ROC) curves were calculated for Pi10, WA%, IL-1β and IL-4 to identify frequent exacerbators.

Results

Compared with NFE group, FE group had a greater inner perimeter wall thickness of a 10 mm diameter bronchiole (Pi10), a greater airway wall area percentage (WA%) and higher concentrations of IL-1β and IL-4 (p<0.001). After adjusting for sex, age, BMI, FEV1%pred and smoking pack-years, Pi10, WA%, IL-β and IL-4 were independently associated with a frequent exacerbator phenotype (p<0.001). Additionally, there was an increase in the odds ratio of the frequent exacerbator phenotype with increasing Pi10, WA%, IL-4, and IL-1β (p for trend <0.001). The ROC curve demonstrated that IL-1β had a significantly larger calculated area under the curve (p < 0.05) than Pi10, WA% and IL-4.

Conclusion

Pi10, WA%, IL-4, and IL-1β were independently associated with the frequent exacerbator phenotype among patients with stable COPD, suggesting that chronic airway and systemic inflammation contribute to the frequent exacerbator phenotype.

Trial Registration

This trial was registered in Chinese Clinical Trial Registry (https://www.chictr.org.cn). Its registration number is ChiCTR2000038700, and date of registration is September 29, 2020.

Three-Month Variability of Commonly Evaluated Biomarkers in Clinically Stable COPD

Introduction

Clinical decisions in chronic obstructive pulmonary disease (COPD) treatment often utilize serially assessed physiologic parameters and biomarkers. To better understand the reliability of these tests, we evaluated changes in commonly assessed biomarkers over 3 months in patients with clinically stable COPD.

Methods

We performed an observational prospective cohort study of 89 individuals with clinically stable COPD, defined as no exacerbation history within 3 months of enrollment. Biomarkers included lung function and functional performance status, patient-reported outcomes of symptoms and health status, and blood markers of inflammation. The correlation between testing at baseline and at 3-month follow-up was reported as the intraclass correlation coefficient (ICC). "Outliers" had significant variability between tests, defined as >1.645 standard deviations between the two measurements. Differences in clinical features between outliers and others were compared.

Results

Participants with COPD (n = 89) were 70.5 ± 6.7 years old, 54 (61%) male, had a 40 pack-year smoking history with 24.7% being current smokers, and postbronchodilator forced expiratory volume in one second (FEV1) 62.3 ± 22.7% predicted. The biomarkers with excellent agreement between the initial and the follow-up measurements were FEV1 (ICC = 0.96), Saint George's Respiratory Questionnaire (SGRQ) (ICC = 0.98), COPD Assessment Test (CAT) (ICC = 0.93) and C-reactive protein (CRP) (ICC = 0.90). By contrast, parameters showing less robust agreement were 6-minute walking distance (ICC = 0.75), eosinophil count (ICC = 0.77), erythrocyte sedimentation rate (ICC = 0.75) and white blood cell count (ICC = 0.48). Individuals with greater variability in biomarkers reported chronic bronchitis more often and had higher baseline SGRQ and CAT scores.

Conclusion

Our study evaluated the stability of commonly assessed biomarkers in clinically stable COPD and showed excellent agreement between baseline and three-month follow-up values for FEV1, SGRQ, CAT and CRP. Individuals with chronic bronchitis and more symptomatic disease at baseline demonstrated greater variability in 3-month interval biomarkers.

CT-based emphysema characterization per lobe: A proof of concept

PURPOSE

The Fleischner society criteria are global criteria to visually evaluate and classify pulmonary emphysema on CT. It may group heterogeneous disease severity within the same category, potentially obscuring clinically relevant differences in emphysema severity. This proof-of-concept study proposes to split emphysema into more categories and to assess each lobe separately, and applies this to two general population-based cohort samples to assess what information such an extension adds.

METHOD

From a consecutive sample in two general population-based cohorts with low-dose chest CT, 117 participants with more than a trace of emphysema were included. Two independent readers performed an extended per-lobe classification and assessed overall severity semi-quantitatively. An emphysema sum score was determined by adding the severity score of all lobes. Inter-reader agreement was quantified with Krippendorff Alpha.

RESULTS

Based on Fleischner society criteria, 69 cases had mild to severe centrilobular emphysema, and 90 cases had mild or moderate paraseptal emphysema (42 had both types of emphysema). The emphysema sum score was significantly different between mild (10.7 ± 4.3, range 2-22), moderate (20.1 ± 3.1, range: 15-24), and severe emphysema (23.6 ± 3.4, range: 17-28, p < 0.001), but ranges showed significant overlap. Inter-reader agreement for the extended classification and sum score was substantial (alpha 0.79 and 0.85, respectively). Distribution was homogenous across lobes in never-smokers, yet heterogenous in current smokers, with upper-lobe predominance.

CONCLUSIONS

The proposed emphysema evaluation method adds information to the original Fleischner society classification. Individuals in the same Fleischner category have diverse emphysema sum scores, and lobar emphysema distribution differs between smoking groups.