Intravital microscopic optical coherence tomography imaging to assess mucus-mobilizing interventions for muco-obstructive lung disease in mice.

Airway mucus obstruction is a hallmark of chronic lung diseases such as cystic fibrosis, asthma, and COPD, and the development of more effective mucus-mobilizing therapies remains an important unmet need for patients with these muco-obstructive lung diseases. However, methods for sensitive visualization and quantitative assessment of immediate effects of therapeutic interventions on mucus clearance in vivo are lacking. In this study, we determined whether newly developed high-speed microscopic optical coherence tomography (mOCT) is sensitive to detect and compare in vivo effects of inhaled isotonic saline, hypertonic saline, and bicarbonate on mucus mobilization and clearance in Scnn1b-transgenic mice with muco-obstructive lung disease. In vivo mOCT imaging showed that inhaled isotonic saline-induced rapid mobilization of mucus that was mainly transported as chunks from the lower airways of Scnn1b-transgenic mice. Hypertonic saline mobilized a significantly greater amount of mucus that showed a more uniform distribution compared with isotonic saline. The addition of bicarbonate-to-isotonic saline had no effect on mucus mobilization, but also led to a more uniform mucus layer compared with treatment with isotonic saline alone. mOCT can detect differences in response to mucus-mobilizing interventions in vivo, and may thus support the development of more effective therapies for patients with muco-obstructive lung diseases.

Pulmonary function and high-resolution computed tomography in outdoor rock drillers exposed to crystalline silica.

OBJECTIVES: Chronic obstructive pulmonary disease and silicosis are associated with exposure to crystalline silica. We determined the exposure to respirable crystalline silica and estimated exposure-response relationships between cumulative exposure and pulmonary function in outdoor rock drillers. METHODS: 136 rock drillers and 48 referents were recruited from three heavy construction companies. 98 air samples were collected by personal sampling for determination of respirable particulate matter and crystalline silica. Information about individual job tasks, type of drilling equipment and years of exposure in different job categories was obtained by interview. Cumulative exposure to crystalline silica was calculated for all workers. Pulmonary function was assessed by spirometry. A subgroup of 39 subjects with high cumulative exposure to crystalline silica underwent high-resolution computed tomography (HRCT). RESULTS: Cumulative exposure (mean (min-max)) to crystalline silica was 0.69 mgÙ years m-3 (0.01-5.89) in the exposed group. Mean time of exposure among rock drillers was 10.7 years (1-42). Compared with referents, the rock drillers had a lower forced expiratory volume in one second/forced vital capacity ratio (79.4 vs 81.4, p<0.05) and maximal mid-expiratory flow% (85.6 vs 93.9, p<0.05). Further, by stratifying the exposed workers into three equally large groups, a dose-response relationship was demonstrated in the highest exposed group, also in never smokers, at a mean cumulative exposure of 21.7 years at 0.08 mgÙ m-3/years. Silicosis was not detected in HRCT, but other patterns of fibrosis and emphysema were seen. CONCLUSIONS: Outdoor rock drillers exposed to crystalline silica had significantly lower pulmonary function than referents, and signs of airflow obstruction. Silicosis was not detected.

Advances in Optical Coherence Tomography and Confocal Laser Endomicroscopy in Pulmonary Diseases.

Diagnosing and monitoring pulmonary diseases is highly dependent on imaging, physiological function tests and tissue sampling. Optical coherence tomography (OCT) and confocal laser endomicroscopy (CLE) are novel imaging techniques with near-microscopic resolution that can be easily and safely combined with conventional bronchoscopy. Disease-related pulmonary anatomical compartments can be visualized, real time, using these techniques. In obstructive lung diseases, airway wall layers and related structural remodelling can be identified and quantified. In malignant lung disease, normal and malignant areas of the central airways, lung parenchyma, lymph nodes and pleura can be discriminated. A growing number of interstitial lung diseases (ILDs) have been visualized using OCT or CLE. Several ILD-associated structural changes can be imaged: fibrosis, cellular infiltration, bronchi(ol)ectasis, cysts and microscopic honeycombing. Although not yet implemented in clinical practice, OCT and CLE have the potential to improve detection and monitoring pulmonary diseases and can contribute in unravelling the pathophysiology of disease and mechanism of action of novel treatments. Indeed, assessment of the airway wall layers with OCT might be helpful when evaluating treatments targeting airway remodelling. By visualizing individual malignant cells, CLE has the potential as a real-time lung cancer detection tool. In the future, both techniques could be combined with laser-enhanced fluorescent-labelled tracer detection. This review discusses the value of OCT and CLE in pulmonary medicine by summarizing the current evidence and elaborating on future perspectives.

Ventilation inhomogeneity in obstructive lung diseases measured by electrical impedance tomography: a simulation study.

Electrical impedance tomography (EIT) has mostly been used in the Intensive Care Unit (ICU) to monitor ventilation distribution but is also promising for the diagnosis in spontaneously breathing patients with obstructive lung diseases. Beside tomographic images, several numerical measures have been proposed to quantitatively assess the lung state. In this study two common measures, the 'Global Inhomogeneity Index' and the 'Coefficient of Variation' were compared regarding their capability to reflect the severity of lung obstruction. A three-dimensional simulation model was used to simulate obstructed lungs, whereby images were reconstructed on a two-dimensional domain. Simulations revealed that minor obstructions are not adequately recognized in the reconstructed images and that obstruction above and below the electrode plane may result in misleading values of inhomogeneity measures. EIT measurements on several electrode planes are necessary to apply these measures in patients with obstructive lung diseases in a promising manner.

A multiscale analytical model of bronchial airway acoustics.

Sound transmission and resulting airway wall vibration in a complex multiscale viscoelastic model of the subglottal bronchial tree was calculated using a modified one-dimensional (1D) branching acoustic waveguide approach. This is an extension of previous work to enable use of complex airway trees that are partially derived from subject-specific medical images, without the need for self-similarity in the geometric structure. The approach was validated numerically for simplified airway geometries, as well as experimentally by comparison to previous studies. A comprehensive conducting airway tree with about 60 000 branches was then modified to create fibrotic, bronchoconstrictive, and pulmonary infiltrate conditions. The fibrotic case-systemic increase in soft tissue stiffness-increased the Helmholtz resonance frequency due to the increased acoustic impedance. Bronchoconstriction, with geometric changes in small conducting airways, decreased acoustic energy transmission to the peripheral airways due in part to the increased impedance mismatch between airway orders. Pulmonary infiltrate significantly altered the local acoustic field in the affected lobe. Calculation of acoustic differences between healthy versus pathologic cases can be used to enhance the understanding of vibro-acoustic changes correlated to pathology, and potentially provide improved tools for the diagnosis of pulmonary diseases that uniquely alter the acoustics of the airways.

Clinical Significance of Forced Oscillation Technique for Evaluation of Small Airway Disease in Interstitial Lung Diseases.

PURPOSE: Small airway disease (SAWD) in patients with interstitial lung disease (ILD) is often assessed by high-resolution computed tomography (HRCT). However, frequent HRCT examinations result in a high level of radiographic exposure. This study investigated the utility of the forced oscillation technique (FOT) to evaluate SAWD in patients with ILD. METHODS: Broadband FOT using a commercially available device (MostGraph-01) and pulmonary function tests (PFT) were performed in 90 patients with ILD. HRCT images taken within 3 months were reviewed. The patients were divided into two groups according to the presence or absence of SAWD findings detected by HRCT. Clinical characteristics, PFT, and FOT between the two groups were compared. RESULTS: Of the 90 patients with ILD, 19 were classified as having SAWD findings (the presence group) and 71 as not having SAWD findings (the absence group). There were no significant differences in parameters of PFT between the two groups. The presence group had higher absolute values of reactance at 5 Hz (X5), resonant frequency (Fres), and low-frequency reactance area (ALX) than did the absence group. A within-breath change analysis demonstrated that the change in X5, Fres, and ALX between expiration and inspiration (ΔX5, ΔFres, ΔALX, respectively) was significantly different between the groups. A univariate analysis revealed that X5, Fres, ALX, ΔX5, ΔFres, ΔALX were significantly associated with the presence of SAWD findings. Multivariate analysis validated that Fres was related to the presence of SAWD findings. CONCLUSIONS: The FOT may be useful in detecting and evaluating SAWD in patients with ILD. TRIAL REGISTRATION: UMIN 000020733.

Toward automatic regional analysis of pulmonary function using inspiration and expiration thoracic CT.

PURPOSE: To analyze pulmonary function using a fully automatic technique which processes pairs of thoracic CT scans acquired at breath-hold inspiration and expiration, respectively. The following research objectives are identified to: (a) describe and systematically analyze the processing pipeline and its results; (b) verify that the quantitative, regional ventilation measurements acquired through CT are meaningful for pulmonary function analysis; (c) identify the most effective of the calculated measurements in predicting pulmonary function; and (d) demonstrate the potential of the system to deliver clinically important information not available through conventional spirometry. METHODS: A pipeline of automatic segmentation and registration techniques is presented and demonstrated on a database of 216 subjects well distributed over the various stages of COPD (chronic obstructive pulmonary disorder). Lungs, fissures, airways, lobes, and vessels are automatically segmented in both scans and the expiration scan is registered with the inspiration scan using a fully automatic nonrigid registration algorithm. Segmentations and registrations are examined and scored by expert observers to analyze the accuracy of the automatic methods. Quantitative measures representing ventilation are computed at every image voxel and analyzed to provide information about pulmonary function, both globally and on a regional basis. These CT derived measurements are correlated with results from spirometry tests and used as features in a kNN classifier to assign COPD global initiative for obstructive lung disease (GOLD) stage. RESULTS: The steps of anatomical segmentation (of lungs, lobes, and vessels) and registration in the workflow were shown to perform very well on an individual basis. All CT-derived measures were found to have good correlation with spirometry results, with several having correlation coefficients, r, in the range of 0.85-0.90. The best performing kNN classifier succeeded in classifying 67% of subjects into the correct COPD GOLD stage, with a further 29% assigned to a class neighboring the correct one. CONCLUSIONS: Pulmonary function information can be obtained from thoracic CT scans using the automatic pipeline described in this work. This preliminary demonstration of the system already highlights a number of points of clinical importance such as the fact that an inspiration scan alone is not optimal for predicting pulmonary function. It also permits measurement of ventilation on a per lobe basis which reveals, for example, that the condition of the lower lobes contributes most to the pulmonary function of the subject. It is expected that this type of regional analysis will be instrumental in advancing the understanding of multiple pulmonary diseases in the future.

Pulmonary abnormalities on high-resolution computed tomography in ankylosing spondylitis: relationship to disease duration and pulmonary function testing.

The aim of this study was to identify the pulmonary abnormalities on high-resolution computed tomography (HRCT) in patients with ankylosing spondylitis (AS) and to examine the relationship with the duration of disease and pulmonary function test (PFT) results. Twenty male AS patients with a mean age of 37.1 ± 9.4 years were enrolled in this study. The patients were assigned into 2 groups according to disease duration: patients with disease duration <10 years (n = 10) and ≥ 10 years (n = 10). All patients underwent clinical examination, PFT and HRCT. HRCT revealed abnormalities in 14 patients (70%). The most common findings were apical fibrosis (45%) and emphysema (25%). HRCT findings were more prominent in late AS patients (disease duration ≥ 10 years) (P = 0.015). PFT were considered as abnormal in 4 patients (20%). While 3 patients had a restrictive type pulmonary deficiency, one patient had a mild obstructive pattern. Three of these patients had concomitant HRCT abnormalities. On the other hand, 10 patients with normal PFT had abnormalities on HRCT. These findings suggest that pulmonary involvement in AS patients without respiratory symptoms could be sensitively detected by HRCT. However, the clinical significance of these radiological abnormalities should be examined in further prospective studies.

Persistent pneumocystis colonization leads to the development of chronic obstructive pulmonary disease in a nonhuman primate model of AIDS.

Human immunodeficiency virus (HIV)-infected patients are at increased risk for development of pulmonary complications, including chronic obstructive pulmonary disease (COPD). Inflammation associated with subclinical infection has been postulated to promote COPD. Persistence of Pneumocystis is associated with HIV infection and COPD, although a causal relationship has not been established. We used a simian/human immunodeficiency virus model of HIV infection to study pulmonary effects of Pneumocystis colonization. Simian/human immunodeficiency virus-infected/Pneumocystis-colonized monkeys developed progressive obstructive pulmonary disease characterized by increased emphysematous tissue and bronchial-associated lymphoid tissue. Increased levels of T helper type 2 cytokines and proinflammatory mediators in bronchoalveolar lavage fluid coincided with Pneumocystis colonization and a decline in pulmonary function. These results support the concept that an infectious agent contributes to the development of HIV-associated lung disease and suggest that Pneumocystis colonization may be a risk factor for the development of HIV-associated COPD. Furthermore, this model allows examination of early host responses important to disease progression, thus identifying potential therapeutic targets for COPD.

Parenchymal and airway diseases caused by asbestos.

PURPOSE OF REVIEW: The extensive industrial use of asbestos for many decades has been linked to development of benign and malignant pleuropulmonary disease. This review summarizes newer evidence and ongoing controversies that exist in the literature regarding asbestos-related parenchymal and airway diseases. RECENT FINDINGS: Asbestosis represents a significant respiratory problem despite the improvement in the workplace hygiene and a decrease in use of asbestos. The management of asbestosis remains challenging as currently there is no specific treatment. The role of asbestos exposure alone as a cause of chronic airway obstruction remains uncertain. The relationship between lung cancer and asbestos exposure alone and in combination with smoking has also been investigated. The benefit of screening for asbestos-related pleuropulmonary disease remains uncertain as does the use of computed tomography scanning for the purpose of screening. SUMMARY: Future studies will help clarify the clinical issues and shape screening strategies for asbestos-exposed individuals.

[Echocardiography with physical exercise in patients with stable angina pectoris concurrent with chronic obstructive pulmonary disease: safety, informative value, and performance conditions].

AIM: To define the safety, informative value, and performance conditions of exercise echocardiography (EchoCG) in patients with stable angina (SA) concurrent with chronic obstructive pulmonary disease (COPD). SUBJECTS AND METHODS: Forty patients aged 45 to 66 years (mean age 54.8 +/- 4.9 years) with Functional Class (FC) II-III SA concurrent with COPD and 40 patients aged 46 to 65 years (mean 56.6 +/- 4.9 years) with FC II-III SA without COPD were examined. All the patients underwent exercise EchoCG during the chosen therapy. RESULTS: Exercise EchoCG is safe in patients with SA with COPD. To enhance the informative value of this test and to achieve the ischemic threshold in patients of this category require the use of adequate bronchodilator therapy. In this case, the informative value of the technique is 75%. CONCLUSION: Exercise EchoCG in patients with SA concurrent with COPD may serve as a reliable tool in determining exercise endurance during antianginal, bronchodilator therapy and in assessing its adequacy.

Quantification of muco-obstructive lung disease variability in mice via laboratory X-ray velocimetry.

To effectively diagnose, monitor and treat respiratory disease clinicians should be able to accurately assess the spatial distribution of airflow across the fine structure of lung. This capability would enable any decline or improvement in health to be located and measured, allowing improved treatment options to be designed. Current lung function assessment methods have many limitations, including the inability to accurately localise the origin of global changes within the lung. However, X-ray velocimetry (XV) has recently been demonstrated to be a sophisticated and non-invasive lung function measurement tool that is able to display the full dynamics of airflow throughout the lung over the natural breathing cycle. In this study we present two developments in XV analysis. Firstly, we show the ability of laboratory-based XV to detect the patchy nature of cystic fibrosis (CF)-like disease in ß-ENaC mice. Secondly, we present a technique for numerical quantification of CF-like disease in mice that can delineate between two major modes of disease symptoms. We propose this analytical model as a simple, easy-to-interpret approach, and one capable of being readily applied to large quantities of data generated in XV imaging. Together these advances show the power of XV for assessing local airflow changes. We propose that XV should be considered as a novel lung function measurement tool for lung therapeutics development in small animal models, for CF and for other muco-obstructive diseases.

Regional air trapping in acute exacerbation of obstructive lung diseases measured with electrical impedance tomography: a feasibility study.

BACKGROUND: Since bronchial abnormalities often exhibit spatial non-uniformity which may be not correctly assessed by conventional global lung function measures, regional information may help to characterize the disease progress. We hypothesized that regional air trapping during mechanical ventilation could be characterized by regional end-expiratory flow (EEF) derived from electrical impedance tomography (EIT). METHODS: Twenty-five patients suffering from chronic obstructive pulmonary disease (COPD grade 3 or 4) or severe asthma with acute exacerbation were examined prospectively. Patients were ventilated under assist-control mode. EIT measurements were conducted before and one hour after inhaled combined corticosteroid and long-acting ß2 agonist, on two consecutive days. Regional EEF was calculated as derivative of relative impedance for every image pixel in the lung regions. The results were normalized to global flow values measured by the ventilator. RESULTS: Regional and global EEF were highly correlated (P<0.00001) and regional effects of medication and disease progression were visible in the regional EEF maps. The sums of regional EEF in lung regions were 3.8 [2.0, 5.1] and 3.6 [1.9, 4.5] L/min in COPD patients before and after medication (median [lower, upper quartiles]; P=0.37). The corresponding values in asthma patients were 3.0 [2.5, 4.2] and 2.2 [1.7, 3.2] L/min (P<0.05). Histograms of regional EEF showed high spatial heterogeneity of EEF before medication. After one day of treatment, the histograms exhibited less heterogeneous and a decrease in EEF level. CONCLUSIONS: Regional EEF characterizes air trapping and intrinsic PEEP, which could provide diagnostic information for monitoring the disease progress during treatment.

Severe Cardiopulmonary Disease in a Parturient With Noonan Syndrome.

Noonan syndrome is a relatively common genetic disorder and the second most common cause of congenital heart disease after trisomy 21. The spectrum of cardiac anomalies in Noonan syndrome typically involves pulmonary valve stenosis occasionally in conjunction with hypertrophic cardiomyopathy. Mitral valve involvement is a rare finding in Noonan syndrome and is most commonly associated with either mitral valve prolapse or abnormal valvular insertion causing left ventricular outflow tract obstruction. Patients with Noonan syndrome typically have preserved fertility and, given the success of cardiac surgery and medical management of heart failure in this population, are beginning to present more commonly as parturients in adulthood. Maternal physiologic changes during pregnancy introduce an added complexity to hemodynamic management and anesthetic considerations during labor and delivery. In this article, we present a case of a patient with Noonan syndrome with severe mitral stenosis, pulmonary valve insufficiency, and severe restrictive and obstructive pulmonary disease who presented preterm for delivery due to increased dyspnea at rest. Here we review the pathophysiology behind Noonan syndrome and peripartum management strategies in a patient with severe combined cardiac and pulmonary disease.

Obstructive bronchiolar disease identified by CT in the non-transplant population: analysis of 29 consecutive cases.

BACKGROUND AND OBJECTIVE: Obstructive bronchiolar disease or constrictive bronchiolitis, particularly in non-transplant patients, is poorly understood. This study identified the associated diseases, presenting features, and clinical course of obstructive bronchiolar disease identified by CT in the non-transplant adult population. METHODS: Retrospective single-centre study of 29 consecutive patients clinically diagnosed to have an obstructive bronchiolar disease based on the presence of respiratory symptoms and abnormal CT findings consisting of mosaic perfusion pattern with air trapping. RESULTS: The median age was 54 years (range, 25-80 years); 20 were women (69%) and four patients (14%) had a smoking history. All 29 patients presented with respiratory symptoms, predominantly dyspnoea. The most common cause of obstructive bronchiolar disease was rheumatoid arthritis (34%). Other causes included hypersensitivity pneumonitis, multiple carcinoid tumorlets, Sjögren's syndrome, paraneoplastic pemphigus, inflammatory bowel disease and Swyer-James syndrome. The underlying cause was not identifiable in nine patients (31%), that is, cryptogenic constrictive bronchiolitis. An obstructive pattern was seen on pulmonary function testing in most patients (86%) with the exception of those with hypersensitivity pneumonitis and extreme obesity. Management usually included corticosteroid therapy, inhaled and oral, and bronchodilator therapy. Additional medications included macrolides, cytotoxic agents and other immunomodulator therapy. Pharmacologic therapy did not provide improvement in pulmonary function in the majority of patients but the follow-up data were limited. CONCLUSIONS: Diverse causes and underlying diseases are associated with obstructive bronchiolar disease diagnosed radiologically in the non-transplant adult population. Rheumatoid arthritis-associated and cryptogenic constrictive bronchiolitis are found in over one-half of these patients. Most patients with obstructive bronchiolar disease do not appear to improve with currently available therapy.

Obstructive endo-bronchial pseudotumour due to herpes simplex type 2 infection in an HIV-infected man.

We report a 31-year-old man with an obstructive bronchial lesion due to herpes simplex type 2 infection, who responded promptly to endoscopic resection and oral treatment with acyclovir. Exophytic lesions of the respiratory tract are rare, potentially life-threatening, but readily treated complication of herpes simplex virus infection in HIV-infected individuals.

Development of an automatic classification system for differentiation of obstructive lung disease using HRCT.

The motivation is to introduce new shape features and optimize the classifier to improve performance of differentiating obstructive lung diseases, based on high-resolution computerized tomography (HRCT) images. Two hundred sixty-five HRCT images from 82 subjects were selected. On each image, two experienced radiologists selected regions of interest (ROIs) representing area of severe centrilobular emphysema, mild centrilobular emphysema, bronchiolitis obliterans, or normal lung. Besides 13 textural features, additional 11 shape features were employed to evaluate the contribution of shape features. To optimize the system, various ROI size (16 x 16, 32 x 32, and 64 x 64 pixels) and other classifier parameters were tested. For automated classification, the Bayesian classifier and support vector machine (SVM) were implemented. To assess cross-validation of the system, a five-folding method was used. In the comparison of methods employing only the textural features, adding shape features yielded the significant improvement of overall sensitivity (7.3%, 6.1%, and 4.1% in the Bayesian and 9.1%, 7.5%, and 6.4% in the SVM, in the ROI size 16 x 16, 32 x 32, 64 x 64 pixels, respectively; t test, P < 0.01). After feature selection, most of cluster shape features were survived ,and the feature selected set shows better performance of the overall sensitivity (93.5 +/- 1.0% in the SVM in the ROI size 64 x 64 pixels; t test, P < 0.01). Adding shape features to conventional texture features is much useful to improve classification performance of obstructive lung diseases in both Bayesian and SVM classifiers. In addition, the shape features contribute more to overall sensitivity in smaller ROI.

Diagnostic values of bronchodilator response versus 9-question questionnaire for asthma.

INTRODUCTION: Several studies have investigated different tools for asthma diagnosis in order to reduce the cost and improve its early recognition. The goal of this study is to establish ashort questionnaire to be used in practice for asthma screening and compare diagnostic values between this method and spirometric response to bronchodilators. MATERIAL AND METHOD: 208 patients presenting with chronic stable dyspnea (> 6 months) and definite clinical diagnosis of chronic obstructive pulmonary disease, bronchiectasis, pulmonary fibrosis or asthma, were enrolled. 9 questions out of 43 based on the literature search were selected by regression analysis. Patients were asked to complete the questionnaire and then their spirometric responses to bronchodilators were evaluated. RESULTS: Of all, 53.8% of cases were diagnosed clinically to have asthma. For establishing diagnosis of asthma, the bronchodilator test had 48.2% sensitivity, 78.1% specificity, 72% positive, 56.4% negative predictive values, 2.2 positive, 0.66 negative likeli-hood ratios, and false positive, false negative and accuracy of 21.9%, 51.8% and 62.01%, respectively. The revised 9 questions from the questionnaire had 97.3% sensitivity, 77.1% specificity, 83.2% positive, 96.1% negative predictive values, 4.24 positive, 0.03 negative likelihood ratios, 22.9% false positive, 2.7% false negative and 87.98% accuracy. CONCLUSIONS: The 9-question questionnaire had better diagnostic values in defining asthma in patients with chronic dyspnea than reversibility of airway obstruction to salbutamol and can be used as auseful screening test for diagnosis of asthma in clinical practice and for investigational purposes.

Correlating exhaled aerosol images to small airway obstructive diseases: A study with dynamic mode decomposition and machine learning.

BACKGROUND: Exhaled aerosols from lungs have unique patterns, and their variation can be correlated to the underlying lung structure and associated abnormities. However, it is challenging to characterize such aerosol patterns and differentiate their difference because of their complexity. This challenge is even greater for small airway diseases, where the disturbance signals are weak. OBJECTIVES AND METHODS: The objective of this study is exploiting different feature extraction algorithms to develop a practical classifier to diagnose obstructive lung diseases using exhaled aerosol images. These include proper orthogonal decomposition (POD), principal component analysis (PCA), dynamic mode decomposition (DMD), and DMD with control (DMDC). Aerosol images were generated via physiology-based simulations in one normal and four diseased airway models in G7-9 bronchioles. The image data were classified using both the support vector machine (SVM) and random forest (RF) algorithms. The effectiveness of different features was evaluated by classification accuracy and misclassification rate. FINDINGS: Results show a significantly higher performance using dynamic feature extractions (DMD and DMDC) than static algorithms (POD and PCA). Adding the control variables to DMD further improved classification accuracy. Comparing the classification methods, RF persistently outperformed SVM for all types of features considered. While the performance of RF constantly increased with the number of features retained, the performance of SVM peaked at 50 and decreased thereafter. The 5-class classification accuracy was 94.8% using the DMDC-RF model and 93.0% using the DMD-RF model, both of which were higher than 87.0% in the previous study that used fractal dimension features. CONCLUSION: Considering that disease progression is inherently a dynamic process, DMD(C)-based feature extraction preserves temporal information and is preferred over POD and PCA. Compared with hand-crafted features like fractals, feature extraction by DMD and DMDC is automatic and more accurate.