BACKGROUND:Pulmonary vascular remodeling is implicated in the pathophysiologic characteristics of pulmonary hypertension (PH) in chronic lung diseases. CT imaging metrics of pulmonary vessels may provide insight into the impact of vessel morphologic features on PH severity in chronic lung diseases (CLDs). RESEARCH QUESTION:Are CT imaging-assessed pulmonary vascular abnormalities associated with the presence and severity of PH in COPD and fibrosing interstitial lung disease (ILD), and how are they related to parenchymal damage? STUDY DESIGN AND METHODS:We evaluated 117 patients with CLD (63 patients with COPD and 54 patients with ILD), and 38 patients with idiopathic pulmonary arterial hypertension as a comparator group. Patients with COPD and ILD were stratified according to the presence and severity of PH using right heart catheterization. Pulmonary vessel volumes, stratified in arteries and veins, and the extent of emphysema and fibrosis were assessed by volumetric, noncontrast chest CT scans. RESULTS:Patients with COPD exhibited greater vascular and lung volumes (LVs) than those with ILD, although they showed lower small-vessel volume when adjusted for LV. In both diseases, severe PH was associated with a reduced volume of small arteries normalized to total arterial volume (TAV; blood volume in arteries < 5 mm2 in cross-section [BV5art] to TAV ratio) and was more pronounced in patients with COPD, who also showed larger central vessel volumes. In COPD, the extent of emphysema did not correlate with either hemodynamic impairment or small-vessel volume. In contrast, in ILD, the extent of fibrosis was unrelated to hemodynamic impairment, but was corelated inversely with the volume of small arteries and veins. INTERPRETATION:Our results show that COPD and fibrosing ILD exhibit marked differences in pulmonary vessel morphologic features and their relationship with parenchymal remodeling, suggesting distinct mechanisms underlying PH development. In lung disease, the BV5art to TAV ratio seems to be a sensitive marker of hemodynamically confirmed severe PH, particularly in COPD, reflecting intravascular volume redistribution resulting from peripheral vessel remodeling.

Purpose of review The purpose of this review is to describe the use of chest computed tomography (CT) data to expand sub-phenotyping of pulmonary hypertension associated with chronic lung disease (Group 3 pulmonary hypertension) and inform identification of effective treatment. Recent findings In the last 5 years, breakthroughs in clinical pulmonary hypertension research highlight the importance of chest CT data to inform disease trajectory and mortality risk. In presumed idiopathic pulmonary arterial hypertension (Group 1 pulmonary hypertension), a Group 1 ‘lung phenotype’ with abnormal CT chest findings such as emphysema and fibrosis, experiences a mortality risk similar to that of Group 3 disease. Post hoc analyses of Group 3 pulmonary hypertension clinical trials highlight CT abnormalities to inform adverse treatment response, with implications for additional failed clinical trials to date. In fact, pulmonary hypertension guidelines emphasize the critical role for acquisition of standardized high-resolution CT data at pulmonary hypertension diagnosis and clinical trial enrollment. Summary Chest CT imaging is critical in the clinical management of pulmonary hypertension associated with chronic lung disease. Future research will not only incorporate CT data into Group 3 pulmonary hypertension phenotyping research but also consider treatment effect visualization on the lung parenchyma and pulmonary arterial vasculature as a novel clinical trial endpoint.

ABSTRACT Background The systemic immune responses associated with persistent respiratory symptoms (PRS) after exposure to airborne environmental pollutants remain poorly understood. Objective To identify immune disturbances associated with PRS, defined as persistent wheeze, cough, or breathlessness, we examined systemic immune responses and airway function in a cross-sectional cohort with detailed histories of airborne pollutant exposure. Methods Never-smoking post-deployment Veterans with PRS (n=16) or without PRS (n=24) underwent chest computed tomography, pulmonary function testing, and oscillometry to assess structural and functional airway abnormalities. Peripheral blood mononuclear cells (PBMCs) were stimulated with anti-CD3/CD28 antibodies, lipopolysaccharide, or β-glucan, and cytokine production was measured. Correlation analyses evaluated associations between cytokine responses and physiological measures of airway function. Results Oscillometry, but not conventional pulmonary function testing or chest computed tomography, detected small-airway abnormalities in participants with PRS, including significantly greater frequency dependence of resistance and higher resonant frequency. Baseline PBMC cytokine concentrations were similar between groups. After stimulation, however, PBMCs from participants with PRS showed increased IL-17A production consistent with a type 17 (T17) response; innate stimulation also increased the type 2 (T2) cytokines IL-33 and IL-4. T2/T17 cytokine responses correlated positively with oscillometric measures of small-airway dysfunction. Conclusion Individuals with PRS exhibited a stimulus-dependent systemic T2/T17 immune signature that was associated with early small-airway dysfunction. Clinical Implication Stimulus-dependent systemic immune profiling, combined with oscillometry, may help identify early respiratory abnormalities in pollutant-exposed individuals whose conventional pulmonary tests remain normal. KEY MESSAGES Oscillometry detected early small-airway dysfunction in pollutant-exposed individuals with persistent respiratory symptoms, whereas conventional pulmonary function tests and chest CT did not distinguish the groups. Immune stimulation revealed a mixed T2/T17 systemic signature in participants with persistent respiratory symptoms, including increased IL-17A and stimulus-dependent increases in IL-4 and IL-33. T2/T17 cytokine responses correlated with oscillometric abnormalities, linking systemic immune dysregulation to small-airway dysfunction and suggesting a potential approach for identifying early pollutant-associated respiratory disease. CAPSULE SUMMARY A stimulus-dependent systemic T2/T17 immune signature correlated with oscillometric evidence of small-airway dysfunction, identifying a potential early respiratory phenotype in pollutant-exposed individuals with persistent respiratory symptoms.

Dyspnea is common in smokers with or without chronic obstructive pulmonary disease. Its multifactorial nature makes it challenging to identify specific factors causing dyspnea in smokers with and without chronic obstructive pulmonary disease. The study aims to identify associations between clinical history, spirometry, and computed tomography findings related to dyspnea in smokers, and to develop and compare dyspnea models using different variable combinations. Dyspnea was defined as a self-reported modified Medical Research Council dyspnea scale score ≥ 2. Participants from the COPDGene Study dataset were utilized and split into training and testing samples (80

Background:Interstitial lung abnormalities (ILA) are radiologic findings of increased lung density or fibrosis in individuals without clinical interstitial lung disease (ILD) and are associated with increased mortality and progression to ILD. Understanding physiologic trajectories of lung function preceding ILA diagnosis may illuminate early mechanisms of lung injury. Methods:We recruited participants from the Coronary Artery Risk Development in Young Adults (CARDIA) Lung Study, a prospective cohort of adults enrolled at ages 18-30 years and followed longitudinally for 25 years. Percent predicted forced vital capacity (ppFVC) was measured at five study visits over 20 years. Individual ppFVC trajectories were estimated using random coefficient models. Person-specific slopes were incorporated into logistic regression models to examine associations with visually detected ILA on chest CT at exam year 25. Models were adjusted for age, sex, race, body mass index, pack-years of smoking, and study center. Results:Among 3,136 participants with complete data, 57 (1.8%) had ILA at mean age 51 years. In univariable and multivariable models, individuals with ILA had greater cumulative decline in ppFVC over the 20 years preceding diagnosis. Each 10% absolute decline in ppFVC was associated with more than twice the odds of ILA (adjusted OR 2.21, 95% confidence interval 1.47-3.31, p = 0.0001). Conclusions:Greater longitudinal decline in FVC from early adulthood was strongly associated with the presence of ILA at midlife. These findings suggest that physiologic impairments precede radiologic evidence of subclinical parenchymal lung abnormalities, underscoring the potential of life course lung function trajectories to identify individuals at risk for developing ILD.

ABSTRACT CTEPH remains underdiagnosed and can be difficult to differentiate on routine CTPA from acute PE and from patients without pulmonary thromboembolism. We developed and evaluated a fully automated CTPA‐based machine learning algorithm combining vascular blood volume metrics with clot and periclot imaging features. In this retrospective multicenter study, intraparenchymal pulmonary vessels were segmented using a scale‐space particle approach, deep learning models estimated vessel radius, clot probability, and clot area from cross‐sectional patches along the vessel axis, and subject‐level radiomic and blood volume features were used to train an XGBoost classifier on a Northwestern University (NU) cohort (89 CTEPH; 176 controls). The trained model was then applied (without retraining) to held‐out NU data, an independent acute PE cohort (152 patients) as an exploratory generalization test, and an external cohort from Brigham and Women's Hospital (23 CTEPH; 34 controls). Among 474 participants (mean age, 51 years ± 16; 299 men), the model achieved an AUC of 0.87 (95% CI: 0.79, 0.94) for CTEPH versus controls in internal testing, 0.74 (95% CI: 0.61–0.86) in external testing, and 0.89 (95% CI 0.83–0.93) for CTEPH versus acute PE. Excluding periclot features reduced discrimination, particularly for CTEPH versus acute PE (AUC 0.71; 95% CI: 0.63, 0.79). These findings support the feasibility of automated CTPA‐derived vascular, clot, and periclot features for differentiating CTEPH from acute PE and controls without evidence of pulmonary thromboembolism, with further validation needed to assess generalizability across institutions.

This study investigates the variability of radiomic features in longitudinal CT scans from a multi-institutional NSCLC cohort and introduces a harmonization pipeline to improve predictive modeling of immunotherapy response. Baseline and follow-up CT scans from NSCLC patients treated with anti-PD-1/PD-L1 agents were analyzed, with two institutions combined for model training and internal testing, and a third institution serving as an external test set. To address variability from imaging parameters—such as scanner manufacturer, slice thickness, and noise—we applied image harmonization followed by feature harmonization using NestedComBat. This approach substantially reduced feature dependence on acquisition confounders (from 78.8% to 12.8%) and improved feature robustness across institutions. We further assessed the temporal consistency of radiomic features across longitudinal scans using the intraclass correlation coefficient (ICC). Image harmonization yielded the largest gains in stability (mean ΔICC = +0.021, p < 0.001), while the combined approach also enhanced longitudinal reliability (ΔICC = +0.014, p < 0.001). Finally, harmonization improved predictive performance for 6-month immunotherapy response, increasing the AUC from 0.695 to 0.768 in the internal test and from 0.692 to 0.802 in the external test. These results demonstrate that combining image- and feature-level harmonization enhances the robustness and temporal consistency of radiomic features, potentially supporting more reliable and generalizable predictive modeling across diverse datasets and clinical settings.

BACKGROUND:Chronic lung disease and heart failure (HF) commonly co-occur, share modifiable risk factors, and are preceded by a prolonged, heterogeneous, and subclinical phase that is poorly defined. RESEARCH QUESTION:Does the use of unsupervised machine learning identify distinct lung phenogroups, and are these phenogroups associated with cardiac structure and function? STUDY DESIGN AND METHODS:Participants from the Coronary Artery Risk Development in Young Adults study who completed CT imaging of the lung, spirometry, and echocardiography were included. Gaussian mixture models were used to cluster 10 lung features from CT imaging and spirometry over 30 years into mutually exclusive phenogroups. Multivariable-adjusted linear and logistic regression estimated associations between lung phenogroups and cardiac structure and function parameters from year 30 echocardiograms. RESULTS:Among 2,302 participants (mean [SD] age, 25.1 [3.6] years; 58% female; 44% Black race), 4 lung-heart phenogroups at year 30 were identified: (1) ideal, (2) emphysema-predominant with obstructive physiologic features, (3) mild interstitial or lung injury, and (4) substantial interstitial or lung injury with restrictive physiologic features. Compared with the ideal phenogroup, the substantial interstitial or lung injury group showed higher CT imaging-measured lung injury (39% vs 1%) and interstitial change (12% vs 0.6%), worse cardiac remodeling, including higher left ventricular mass or height (mean difference, 4.4 [95% CI, 2.8-6.1]) and global longitudinal strain (mean difference, 0.7% [95% CI, 0.2%-1.2%]), and higher odds of stage B heart failure (OR, 1.18 [95% CI, 1.08-1.29]; P < .05 for all). These findings were consistent among those who had never smoked. INTERPRETATION:Our results show that machine learning identified 4 distinct lung phenogroups in midlife, each defined by diverse subclinical lung and associated with different patterns of cardiac remodeling. Early subclinical lung features are associated with adverse cardiac remodeling and may increase the risk of development of cardiopulmonary diseases.

Bronchoscopic navigation relies on registering endoscopic video to a preoperative CT scan, but respiratory motion deforms the airway by 5-20 mm, creating CT-to-body divergence that limits localization accuracy. In practice, this is mitigated through breath-hold protocols, which attempt to match the intraoperative anatomy to a static CT, but are difficult to reproduce and disrupt clinical workflow. We propose to eliminate the need for breath-hold protocols by leveraging patient-specific respiratory modeling. Paired inhale-exhale CT scans, already acquired for planning, implicitly define the patient-specific deformation space of the breathing airway. By registering these scans, we reduce respiratory motion to a single scalar breathing phase per frame, constraining all reconstructions to anatomically observed configurations. We embed this representation within a mesh-anchored Gaussian splatting framework, where a lightweight estimator infers breathing phase directly from endoscopic RGB, enabling continuous, deformation-aware reconstruction throughout the respiratory cycle without breath-holds or external sensing. To enable quantitative evaluation, we introduce RESPIRE, a physically grounded bronchoscopy simulation pipeline with per-frame ground truth for geometry, pose, breathing phase, and deformation. Experiments on RESPIRE show that our approach achieves geometrically faithful reconstruction, over 20x faster training, and 1.22 mm target localization accuracy (within the 3mm clinically relevant tolerances) outperforming unconstrained single-CT baselines. Please check out our website for additional visuals: https://asdunnbe.github.io/RESPIRE/

Brown adipose tissue (BAT) plays a key role in energy metabolism and cardiometabolic health. Its detection typically relies on 18F-FDG PET, which is costly, radiation-intensive, and impractical for large-scale screening. We propose a deep learning model to estimate regional metabolic activity in adipose tissue from standard non-contrast CT, enabling PET-like insights without radiotracers. Using paired PET/CT data from two independent cohorts, we trained a conditional Generative Adversarial Network (cGAN) to predict standardized uptake values (SUV) within adipose regions identified on CT. The network included a fat-focused loss function to enhance metabolic signal estimation. Predicted activations showed strong agreement with PET-derived values and were reproducible across anatomical regions and datasets. This method provides a radiation-sparing alternative for assessing adipose metabolic activity in clinical and research settings and it could support population-based studies of BAT, metabolic health, and disease progression using routine chest CT scans without additional imaging burden.

RATIONALE:In smokers with and without chronic obstructive pulmonary disease (COPD), the differential strengths of association between chest computed tomography (CT)-based metrics of pulmonary vascular disease and adverse outcomes are unknown. OBJECTIVES:We aimed to quantify the differential strengths of association of CT features, from the distal pulmonary arteries to the central great vessels and cardiac chambers, with acute respiratory exacerbations (AREs) and mortality in smokers with and without COPD. METHODS:Smokers with and without COPD with pulmonary vascular morphology and outcomes data were identified in COPDGene. Negative binominal and multivariable Cox proportional hazard models were used to investigate the association of CT features, including volume of the distal pulmonary arterial vasculature or pruning (<5 mm2 normalized to total arterial blood vessel volume [aBV5/aTBV]), preacinar vessels (5-20 mm2), and pulmonary artery to aorta (PA/Ao) and right to left ventricular epicardial volume (RV/LV) ratios, with outcomes. Kaplan-Meier curves were used to describe pruning risk on mortality. RESULTS:A total of 3169 smokers with COPD and 2530 smokers without COPD were analyzed. Among smokers with COPD, PA/Ao was the only imaging feature significantly associated with AREs (incidence rate ratio, 1.08 [95% CI, 1.04-1.12]), even after adjusting for aBV5/aTBV. Conversely, pruning demonstrated the strongest association with mortality, even in smokers without COPD (hazard ratio, 1.22 [95% CI, 1.14-1.30] and 1.26 [95% CI, 1.11-1.42], respectively). The association of preacinar vessels with mortality in smokers with COPD and in those without COPD, but with significant emphysema on imaging (≥5%), was novel. CONCLUSIONS:Pruning is significantly associated with mortality risk in smokers with and without COPD; however, PA/Ao selectively associates with AREs in COPD, even when accounting for distal vasculopathy.

RATIONALE:Mucus plug formation and chronic bronchitis are manifestations of mucus pathology in chronic obstructive pulmonary disease. Identifying gene expression changes related to mucus pathology could provide insight into its pathogenesis. OBJECTIVES:To investigate gene expression changes in individuals with mucus plugs, identify related biological pathways, and assess whether mucus plug-related gene expression associates with clinical features of other mucus pathologies. METHODS:We studied 290 participants from the Detection of Early Lung Cancer Among Military Personnel 2 study with mainstem bronchial brush bulk RNA-sequencing data (n = 204 discovery, n = 86 validation). We scored mucus plugging based on the number of lung segments with mucus plugs identified on chest computed tomography scans and used correlative analysis to identify differentially expressed genes and examine their association with chronic bronchitis symptoms. MEASUREMENTS AND MAIN RESULTS:Seventy-six participants (37%) in the discovery set had mucus plugs. Differentially expressed genes were broadly epithelial- or immune-related. Epithelial-related genes show decreased expression of genes involved in cilia maintenance and microtubule function and increased expression of genes related to epithelial maintenance and protection. Expression patterns of epithelial-related genes are associated with chronic bronchitis symptoms. Immune-related genes are enriched for innate and adaptive pathways. Expression of immune genes varies by lung function and was more weakly associated with mucus plugs than that of epithelial-related genes. Findings were replicated in an independent validation set. CONCLUSION:Several distinct gene expression patterns are linked to the presence of mucus plugs, highlighting biological -pathways involved in mucus pathophysiology. Variability in gene expression suggests a spectrum of mucus pathophysiology contributes to mucus plugs and chronic bronchitis symptoms.

INTRODUCTION:We have demonstrated diverging FEV1 trajectories in WTC workers on longitudinal health surveillance. We performed a cohort study to investigate the association of those FEV1 trajectories with novel QCT markers of subtle lung parenchymal injury. METHODS:We included WTC responders with CT scans with quantitative measurements (all as percentage of the CT-measured lung volume) of five different metrics: normal parenchyma (Norm%), high attenuation normal parenchyma (NormHA%), interstitial lung abnormality features (ILAV%), honeycombing pattern (HcV%), and emphysema. We used linear regression to calculate each subject's FEV1 slope and classified them into three distinct trajectories: 1) accelerated decline (ACCEL): < -62.5 mL/year; 2) normal decline (NORM): 0 to -30 ml/year, baseline FEV1%predicted>70% and no significant dyspnea; 3) improved: >0 mL/year. RESULTS:Among 446 participants, 211 had ACCEL, 142 NORM, and 93 improved FEV1 trajectory. On chest CTs at an average of 7.5 years after 11-September-2001 and compared to the NORM subgroup, ACCEL and improved trajectory subgroups both had less normal lung tissue (Norm%), with ACCEL having more emphysema, and improved participants higher ILAV% and NormHA%. The values of HcV% were very low and not significantly different across groups. ACCEL had a significantly higher all-cause mortality. CONCLUSION:In this occupational cohort on longitudinal surveillance, accelerated lung function decline appears primarily associated with emphysema and airway disease, while lung function improvement is associated with subtle quantitative CT findings suggestive of interstitial inflammatory processes. The latter appeared largely nonprogressive at the time, as honeycombing was very infrequent and not different across trajectory subgroups.

Background Echocardiography is widely used to screen for pulmonary hypertension and guide referral for right heart catheterization (RHC). Right ventricular systolic pressure (RVSP) estimates pulmonary arterial systolic pressure (PASP), yet their agreement in a large real-world cohort remains uncertain. Question How well do echocardiographic right ventricular systolic pressure (RVSP) and tricuspid regurgitation (TR) jet velocity correlate with invasive pulmonary hemodynamics, and how do they compare in detecting elevated mean pulmonary arterial pressure (mPAP)? Study Design and Methods Retrospective, multicenter cohort study of 14,084 adult patients undergoing RHC and echocardiography at two academic hospitals in Boston, Massachusetts. Diagnostic comparison was performed on a subset of 7,652 patients in which both RVSP and TR jet were available. Correlation and calibration were assessed using Spearman correlation, linear regression, and Bland–Altman analyses. Diagnostic performance for mPAP >20 mmHg and ≥35 mmHg was evaluated using sensitivity, specificity, predictive values, and area under the curve (AUC). Results Mean (SD) age was 66.6 (14.7) years. RVSP and PASP were moderately correlated (ρ=0.59; P<.001). Regression showed dynamic range compression (slope 0.63; intercept 16.6 mmHg), reflecting overestimation at lower and underestimation at higher PASP. Mean bias was minimal (0.08 mmHg), but limits of agreement were wide (±30 mmHg). For mPAP >20 mmHg, RVSP ≥35 mmHg was more sensitive than TR velocity ≥2.8 m/s (72% vs 61%) but less specific (66% vs 78%). For mPAP ≥35 mmHg, RVSP ≥50 mmHg and TR velocity ≥3.2 m/s performed similarly (AUC 0.76 vs 0.75). Interpretation RVSP showed moderate correlation but calibration error and limited precision relative to invasive PASP. Although RVSP and TR velocity demonstrated fair discrimination for elevated mPAP, RHC remains essential for definitive diagnosis.

Objective: To investigate associations between rheumatoid arthritis (RA), chronic lung diseases, and acute respiratory exacerbations.Methods: Using the multicenter prospective COPDGene cohort of current and former people who smoke, RA cases were identified using self-report and disease-modifying antirheumatic drug use. Interstitial lung abnormalities (ILA), bronchiectasis (BR), chronic obstructive pulmonary disease (COPD), and mucus plugging (MP) were identified via high-resolution computed tomography scans and spirometry and prevalences were compared among participants with and without RA. Risk of acute respiratory exacerbation over 10 years of follow-up was compared for those with and without RA and stratified by lung abnormality using multivariable Cox regression, accounting for competing mortality risk.Results: We analyzed 76 RA cases (mean age 64.0 years, 67.1% female) and 8,175 non-RA comparators (mean age 59.4 years, 46.2% female). RA cases vs non-RA comparators had higher prevalences of ILA (17.3% vs 7.1%, p=0.0002) and BR (35.5% vs 24.6%, p=0.027), but prevalences of COPD (46.1% vs 43.7%, p=0.69) and MP (36.8% vs 29.6%, p=0.17) were similar. RA was associated with higher risk of acute respiratory exacerbation than non-RA (adjusted HR 1.68, 95%CI 1.25 to 2.26), and those with RA and COPD had the highest risk (adjusted HR 3.57, 95%CI 2.15 to 5.94) compared to non-RA without COPD.Conclusion: In this large prospective study, people who smoke with RA were more likely to have ILA and BR than those without RA, but had similar prevalences of COPD and MP. Participants with RA, particularly those with COPD, had higher risk of acute respiratory exacerbation.

Objective:Quantitative computed tomography (QCT) can automatically quantify parenchymal abnormalities on chest CT imaging using deep learning. We leveraged QCT to detect pulmonary abnormalities in patients with early rheumatoid arthritis (RA) compared to healthy controls. Methods:We analyzed high-resolution CT chest imaging from participants with early RA in the prospective, multicenter, SAIL-RA study and healthy non-smoking controls from the COPDGene study. A deep learning classifier quantified the percentage of normal lung, interstitial abnormalities, and emphysema for each participant. We compared the percentage of QCT features between early RA participants and healthy comparators and examined associations using multivariable linear regression. Results:We analyzed 200 participants with early RA (median RA duration 8.3 months, mean age 55.7 years, 74.5% female) and 104 healthy controls (mean age 62.0 years, 68.3% female). The median percentage of interstitial abnormalities on QCT was 3.7% (IQR 2.1, 6.1%) for early RA and 1.6% (IQR 0.8, 2.4%) for healthy controls (p<0.0001). Early RA was associated with 9.3% less normal lung on QCT than healthy controls, adjusted for age and sex (p<0.0001). Among RA participants, QCT interstitial abnormalities were associated with older age (multivariable β=0.1 per year, 95%CI 0.07-0.2, p<0.0001) and higher DAS28-ESR (multivariable β=0.6 per unit, 95%CI 0.01-1.3, p=0.046). Conclusion:Participants with early RA had less normal lung and more interstitial abnormalities on a deep learning-derived QCT measure than healthy controls. These results suggest that loss of normal lung is already present in early RA and emphasizes the urgent need for strategies to preserve lung health in RA.