CNNs trained with adult data are useful in pediatrics. A pneumonia classification example.

BACKGROUND AND OBJECTIVES: The scarcity of data for training deep learning models in pediatrics has prompted questions about the feasibility of employing CNNs trained with adult images for pediatric populations. In this work, a pneumonia classification CNN was used as an exploratory example to showcase the adaptability and efficacy of such models in pediatric healthcare settings despite the inherent data constraints. METHODS: To develop a curated training dataset with reduced biases, 46,947 chest X-ray images from various adult datasets were meticulously selected. Two preprocessing approaches were tried to assess the impact of thoracic segmentation on model attention outside the thoracic area. Evaluation of our approach was carried out on a dataset containing 5,856 chest X-rays of children from 1 to 5 years old. RESULTS: An analysis of attention maps indicated that networks trained with thorax segmentation placed less attention on regions outside the thorax, thus eliminating potential bias. The ensuing network exhibited impressive performance when evaluated on an adult dataset, achieving a pneumonia discrimination AUC of 0.95. When tested on a pediatric dataset, the pneumonia discrimination AUC reached 0.82. CONCLUSIONS: The results of this study show that adult-trained CNNs can be effectively applied to pediatric populations. This could potentially shift focus towards validating adult models over pediatric population instead of training new CNNs with limited pediatric data. To ensure the generalizability of deep learning models, it is important to implement techniques aimed at minimizing biases, such as image segmentation or low-quality image exclusion.

Clinical relevance of lung function trajectory clusters in middle-aged and older adults.

Background: The determinants and health outcomes of lung function trajectories in adults among the general population are poorly understood. We aimed to identify and characterise clusters of lung function trajectories in adults aged ≥45 years. Methods: Gaussian finite-mixture modelling was applied to baseline and annualised change of forced expiratory volume in 1 s (FEV1), forced vital capacity (FVC) and FEV1/FVC ratio z-scores in participants of the Rotterdam Study, a prospective population-based cohort study, with repeated spirometry (n=3884; mean±sd age 64.7±8.9 years). Longitudinal outcomes were all-cause mortality, respiratory outcomes (symptoms, COPD (FEV1/FVC <0.7 in absence of asthma), preserved ratio impaired spirometry (PRISm; FEV1/FVC ≥0.7 and FEV1 or FVC <80%)), smoking cessation and weight changes. Independent risk factors, including genetics, were identified by multiple logistic regression. Results: We identified eight trajectory clusters, with the reference group having persistently normal spirometry (prevalence 42.8%). Three clusters showed higher mortality, adjusted for confounders: 1) the persistently low FEV1 cluster (prevalence 6.8%, hazard ratio (HR) 1.71, 95% CI 1.37-2.13); 2) rapid FEV1 decliners (prevalence 4.6%, HR 1.48, 95% CI 1.10-1.99); and 3) FVC decliners (prevalence 3.7%, HR 1.49, 95% CI 1.09-2.03). In contrast, FVC improvers (prevalence 6.7%, HR 0.61, 95% CI 0.41-0.90) and persistently high FEV1 (prevalence 29.2%, HR 0.82, 95% CI 0.69-0.98) were protective trajectory clusters. Clusters were characterised by differences in genetic predisposition (polygenic scores of FEV1 and FEV1/FVC), demographics, cigarette smoking, respiratory symptoms (chronic cough, wheezing and dyspnoea), cardiovascular factors (body mass index, hypertension and heart failure) and serum C-reactive protein levels. Frailty, weight changes and the development of respiratory symptoms, COPD and PRISm were significantly associated with trajectory clusters. Conclusions: This study reveals clinically relevant lung function trajectory clusters in older adults of the general population.

Dysanapsis is differentially related to lung function trajectories with distinct structural and functional patterns in COPD and variable risk for adverse outcomes.

Background: Abnormal lung function trajectories are associated with increased risk of chronic obstructive pulmonary disease (COPD) and premature mortality; several risk factors for following these trajectories have been identified. Airway under-sizing dysanapsis (small airway lumens relative to lung size), is associated with an increased risk for COPD. The relationship between dysanapsis and lung function trajectories at risk for adverse outcomes of COPD is largely unexplored. We test the hypothesis that dysanapsis differentially affects distinct lung function trajectories associated with adverse outcomes of COPD. Methods: To identify lung function trajectories, we applied Bayesian trajectory analysis to longitudinal FEV1 and FVC Z-scores in the COPDGene Study, an ongoing longitudinal study that collected baseline data from 2007 to 2012. To ensure clinical relevance, we selected trajectories based on risk stratification for all-cause mortality and prospective exacerbations of COPD (ECOPD). Dysanapsis was measured in baseline COPDGene CT scans as the airway lumen-to-lung volume (a/l) ratio. We compared a/l ratios between trajectories and evaluated their association with trajectory assignment, controlling for previously identified risk factors. We also assigned COPDGene participants for whom only baseline data is available to their most likely trajectory and repeated our analysis to further evaluate the relationship between trajectory assignment and a/l ratio measures. Findings: We identified seven trajectories: supranormal, reference, and five trajectories at increased risk for mortality and exacerbations. Three at-risk trajectories are characterized by varying degrees of concomitant FEV1 and FVC impairments and exhibit airway predominant COPD patterns as assessed by quantitative CT imaging. These trajectories have lower a/l ratio values and increased risk for mortality and ECOPD compared to the reference trajectory. Two at-risk trajectories are characterized by disparate levels of FEV1 and FVC impairment and exhibit mixed airway and emphysema COPD patterns on quantitative CT imaging. These trajectories have markedly lower a/l ratio values compared to both the reference trajectory and airway-predominant trajectories and are at greater risk for mortality and ECOPD compared to the airway-predominant trajectories. These findings were observed among the participants with baseline-only data as well. Interpretation: The degree of dysanapsis appears to portend patterns of progression leading to COPD. Assignment of individuals-including those without spirometric obstruction-to distinct trajectories is possible in a clinical setting and may influence management strategies. Strategies that combine CT-assessed dysanapsis together with spirometric measures of lung function and smoke exposure assessment are likely to further improve trajectory assignment accuracy, thereby improving early detection of those most at risk for adverse outcomes. Funding: United States National Institute of Health, COPD Foundation, and Brigham and Women's Hospital.

Suspected Bronchiectasis and Mortality in Adults With a History of Smoking Who Have Normal and Impaired Lung Function : A Cohort Study.

BACKGROUND: Bronchiectasis in adults with chronic obstructive pulmonary disease (COPD) is associated with greater mortality. However, whether suspected bronchiectasis-defined as incidental bronchiectasis on computed tomography (CT) images plus clinical manifestation-is associated with increased mortality in adults with a history of smoking with normal spirometry and preserved ratio impaired spirometry (PRISm) is unknown. OBJECTIVE: To determine the association between suspected bronchiectasis and mortality in adults with normal spirometry, PRISm, and obstructive spirometry. DESIGN: Prospective, observational cohort. SETTING: The COPDGene (Genetic Epidemiology of Chronic Obstructive Pulmonary Disease) study. PARTICIPANTS: 7662 non-Hispanic Black or White adults, aged 45 to 80 years, with 10 or more pack-years of smoking history. Participants who were former and current smokers were stratified into normal spirometry (n = 3277), PRISm (n = 986), and obstructive spirometry (n = 3399). MEASUREMENTS: Bronchiectasis identified by CT was ascertained using artificial intelligence-based measurements of an airway-to-artery ratio (AAR) greater than 1 (AAR >1), a measure of bronchial dilatation. The primary outcome of "suspected bronchiectasis" was defined as an AAR >1 of greater than 1% plus 2 of the following: cough, phlegm, dyspnea, and history of 2 or more exacerbations. RESULTS: Among the 7662 participants (mean age, 60 years; 52% women), 1352 (17.6%) had suspected bronchiectasis. During a median follow-up of 11 years, 2095 (27.3%) died. Ten-year mortality risk was higher in participants with suspected bronchiectasis, compared with those without suspected bronchiectasis (normal spirometry: difference in mortality probability [Pr], 0.15 [95% CI, 0.09 to 0.21]; PRISm: Pr, 0.07 [CI, -0.003 to 0.15]; obstructive spirometry: Pr, 0.06 [CI, 0.03 to 0.09]). When only CT was used to identify bronchiectasis, the differences were attenuated in the normal spirometry (Pr, 0.04 [CI, -0.001 to 0.08]). LIMITATIONS: Only 2 racial groups were studied. Only 1 measurement was used to define bronchiectasis on CT. Symptoms of suspected bronchiectasis were nonspecific. CONCLUSION: Suspected bronchiectasis was associated with a heightened risk for mortality in adults with normal and obstructive spirometry. PRIMARY FUNDING SOURCE: National Heart, Lung, and Blood Institute.

Machine learning to predict environmental dose rates from a radionuclide therapy service - a proof of concept study.

The Ionising Radiation Regulations 2017 requires prior risk assessment calculations and regular environmental monitoring of radiation doses. However, the accuracy of prior risk assessments is limited by assumptions and monitoring only provides retrospective evaluation. This is particularly challenging in nuclear medicine for areas surrounding radionuclide therapy patient bathroom wastewater pipework. Machine learning (ML) is a technique that could be applied to patient booking records to predict environmental radiation dose rates in these areas to aid prospective risk assessment calculations, which this proof-of-concept work investigates. 540 days of a dosimeters historical daily average dose rate measurements and the corresponding period of department therapy booking records were used to train six different ML models. Predicted versus measured daily average dose rates for the following 60 days were analysed to assess and compare model performance. A wide range in prediction errors was observed across models. The gradient boosting regressor produced the best accuracy (root mean squared error = 1.10µSv.hr-1, mean absolute error = 0.87µSv.hr-1, mean absolute percentage error = 35% and maximum error = 3.26µSv.hr-1) and goodness of fit (R2= 0.411). Methods to improve model performance and other scenarios where this approach could prove more accurate were identified. This work demonstrates that ML can predict temporal fluctuations in environmental radiation dose rates in the areas surrounding radionuclide therapy wastewater pipework and indicates that it has the potential to play a role in improving legislative compliance, the accuracy of radiation safety and use of staff time and resources.

Heterogeneity and Progression of Chronic Obstructive Pulmonary Disease: Emphysema-Predominant and Non-Emphysema-Predominant Disease.

While variation in emphysema severity between patients with chronic obstructive pulmonary disease (COPD) is well-recognized, clinically applicable definitions of the emphysema-predominant disease (EPD) and non-emphysema-predominant disease (NEPD) subtypes have not been established. To study the clinical relevance of the EPD and NEPD subtypes, we tested the association of these subtypes with prospective decline in forced expiratory volume in 1 second (FEV1) and mortality among 3,427 subjects with Global Initiative for Chronic Obstructive Lung Disease (GOLD) spirometric grade 2-4 COPD at baseline in the Genetic Epidemiology of COPD (COPDGene) Study, an ongoing national multicenter study that started in 2007. NEPD was defined as airflow obstruction with less than 5% computed tomography (CT) quantitative densitometric emphysema at -950 Hounsfield units, and EPD was defined as airflow obstruction with 10% or greater CT emphysema. Mixed-effects models for FEV1 demonstrated larger average annual FEV1 loss in EPD subjects than in NEPD subjects (-10.2 mL/year; P < 0.001), and subtype-specific associations with FEV1 decline were identified. Cox proportional hazards models showed higher risk of mortality among EPD patients versus NEPD patients (hazard ratio = 1.46, 95% confidence interval: 1.34, 1.60; P < 0.001). To determine whether the NEPD/EPD dichotomy is captured by previously described COPDGene subtypes, we used logistic regression and receiver operating characteristic (ROC) curve analysis to predict NEPD/EPD membership using these previous subtype definitions. The analysis generally showed excellent discrimination, with areas under the ROC curve greater than 0.9. The NEPD and EPD COPD subtypes capture important aspects of COPD heterogeneity and are associated with different rates of disease progression and mortality.

Quantitative Interstitial Abnormality Progression and Outcomes in the Genetic Epidemiology of COPD and Pittsburgh Lung Screening Study Cohorts.

BACKGROUND: The risk factors and clinical outcomes of quantitative interstitial abnormality progression over time have not been characterized. RESEARCH QUESTIONS: What are the associations of quantitative interstitial abnormality progression with lung function, exercise capacity, and mortality? What are the demographic and genetic risk factors for quantitative interstitial abnormality progression? STUDY DESIGN AND METHODS: Quantitative interstitial abnormality progression between visits 1 and 2 was assessed from 4,635 participants in the Genetic Epidemiology of COPD (COPDGene) cohort and 1,307 participants in the Pittsburgh Lung Screening Study (PLuSS) cohort. We used multivariable linear regression to determine the risk factors for progression and the longitudinal associations between progression and FVC and 6-min walk distance, and Cox regression models for the association with mortality. RESULTS: Age at enrollment, female sex, current smoking status, and the MUC5B minor allele were associated with quantitative interstitial abnormality progression. Each percent annual increase in quantitative interstitial abnormalities was associated with annual declines in FVC (COPDGene: 8.5 mL/y; 95% CI, 4.7-12.4 mL/y; P < .001; PLuSS: 9.5 mL/y; 95% CI, 3.7-15.4 mL/y; P = .001) and 6-min walk distance, and increased mortality (COPDGene: hazard ratio, 1.69; 95% CI, 1.34-2.12; P < .001; PLuSS: hazard ratio, 1.28; 95% CI, 1.10-1.49; P = .001). INTERPRETATION: The objective, longitudinal measurement of quantitative interstitial abnormalities may help identify people at greatest risk for adverse events and most likely to benefit from early intervention.

The role of serial 99mTc-DPD scintigraphy in monitoring cardiac transthyretin amyloidosis.

PURPOSE: Cardiac transthyretin amyloidosis is a usually fatal form of restrictive cardiomyopathy for which clinical trials of treatments are ongoing. It is anticipated that quantitative nuclear medicine scintigraphy, which is experiencing growing interest, will soon be used to evaluate treatment efficacy. We investigated its utility for monitoring changes in disease load over a significant time period. METHODS: Sixty-two treatment-naive patients underwent 99mTc-labelled 3,3-diphosphono-1,2propanodicarboxylic acid (99mTc-DPD) scintigraphy two to four times each over a five-year period. Quantitation of cardiac 99mTc-DPD retention was performed according to two established methods: measurement of heart-to-contralateral ratio (H/CL) in the anterior view (planar) and percentage of administered activity in the myocardium (SPECT). RESULTS: In total 170 datasets were analysed. Increased myocardial retention of 99mTc-DPD was demonstrable as early as 12 months from baseline. Year-on-year progression across the cohort was observed using SPECT-based quantitation, though on 30 occasions (27.8%) the change in our estimate was negative. CONCLUSIONS: The spread of our results was notably high compared to the year-on-year increases. If left unaccounted for, variance may draw fallacious conclusions about changes in disease load. We therefore urge caution in drawing conclusions solely from nuclear medicine scintigraphy on a patient-by-patient basis, particularly across a short time period.

Quantification of Arterial and Venous Morphologic Markers in Pulmonary Arterial Hypertension Using CT Imaging.

BACKGROUND: Pulmonary hypertension is a heterogeneous disease, and a significant portion of patients at risk for it have CT imaging available. Advanced automated processing techniques could be leveraged for early detection, screening, and development of quantitative phenotypes. Pruning and vascular tortuosity have been previously described in pulmonary arterial hypertension (PAH), but the extent of these phenomena in arterial vs venous pulmonary vasculature and in exercise pulmonary hypertension (ePH) have not been described. RESEARCH QUESTION: What are the arterial and venous manifestations of pruning and vascular tortuosity using CT imaging in PAH, and do they also occur in ePH? STUDY DESIGN AND METHODS: A cohort of patients with PAH and ePH and control subjects with available CT angiograms were retrospectively identified to examine the differential arterial and venous presence of pruning and tortuosity in patients with precapillary pulmonary hypertension not confounded by lung or thromboembolic disease. The pulmonary vasculature was reconstructed, and an artificial intelligence method was used to separate arteries and veins and to compute arterial and venous vascular volumes and tortuosity. RESULTS: A total of 42 patients with PAH, 12 patients with ePH, and 37 control subjects were identified. There was relatively lower (median [interquartile range]) arterial small vessel volume in subjects with PAH (PAH 14.7 [11.7-16.5; P < .0001]) vs control subjects (16.9 [15.6-19.2]) and venous small vessel volume in subjects with PAH and ePH (PAH 8.0 [6.5-9.6; P < .0001]; ePH, 7.8 [7.5-11.4; P = .004]) vs control subjects (11.5 [10.6-12.2]). Higher large arterial volume, however, was only observed in the pulmonary arteries (PAH 17.1 [13.6-23.4; P < .0001] vs control subjects 11.4 [8.1-15.4]). Similarly, tortuosity was higher in the pulmonary arteries in the PAH group (PAH 3.5 [3.3-3.6; P = .0002] vs control 3.2 [3.2-3.3]). INTERPRETATION: Lower small distal pulmonary vascular volume, higher proximal arterial volume, and higher arterial tortuosity were observed in PAH. These can be quantified by using automated techniques from clinically acquired CT scans of patients with ePH and resting PAH.

Association between Cardiorespiratory Fitness and Bronchiectasis at CT: A Long-term Population-based Study of Healthy Young Adults Aged 18-30 Years in the CARDIA Study.

Background Protective factors against the risk of bronchiectasis are unknown. A high level of cardiorespiratory fitness is associated with a lower risk of chronic obstructive pulmonary disease. But whether fitness relates to bronchiectasis remains, to the knowledge of the authors, unknown. Purpose To examine the association between cardiorespiratory fitness and bronchiectasis. Materials and Methods This was a secondary analysis of a prospective observational study: the Coronary Artery Risk Development in Young Adults cohort (from 1985-1986 [year 0] to 2015-2016 [year 30]). During a 30-year period, healthy participants (age at enrollment 18-30 years) underwent treadmill exercise testing at year 0 and year 20 visits. Cardiorespiratory fitness was determined according to the treadmill exercise duration. The 20-year difference in cardiorespiratory fitness was used as the fitness measurement. At year 25, chest CT was performed to assess bronchiectasis and was used as the primary outcome. Multivariable logistic models were performed to determine the association between cardiorespiratory fitness changes and bronchiectasis. Results Of 2177 selected participants (at year 0: mean age, 25 years ± 4 [standard deviation]; 1224 women), 209 (9.6%) had bronchiectasis at year 25. After adjusting for age, race-sex group, study site, body mass index, pack-years smoked, history of tuberculosis, pneumonia, asthma and myocardial infarction, peak lung function, and cardiorespiratory fitness at baseline, preservation of cardiorespiratory fitness was associated with lower odds of bronchiectasis at CT at year 25 (per 1-minute-longer treadmill duration from year 0 to year 20: odds ratio [OR], 0.88; 95% CI: 0.80, 0.98; P = .02). A consistent strong association was found when cough and phlegm were included in bronchiectasis (OR, 0.72; 95% CI: 0.59, 0.87; P < .001). Conclusion In a long-term follow-up, the preservation of cardiorespiratory fitness was associated with lower odds of bronchiectasis at CT. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Stojanovska in this issue.

Distinguishing Smoking-Related Lung Disease Phenotypes Via Imaging and Molecular Features.

BACKGROUND: Chronic tobacco smoke exposure results in a broad range of lung pathologies including emphysema, airway disease and parenchymal fibrosis as well as a multitude of extra-pulmonary comorbidities. Prior work using CT imaging has identified several clinically relevant subgroups of smoking related lung disease, but these investigations have generally lacked organ specific molecular correlates. RESEARCH QUESTION: Can CT imaging be used to identify clinical phenotypes of smoking related lung disease that have specific bronchial epithelial gene expression patterns to better understand disease pathogenesis? STUDY DESIGN AND METHODS: Using K-means clustering, we clustered participants from the COPDGene study (n = 5,273) based on CT imaging characteristics and then evaluated their clinical phenotypes. These clusters were replicated in the Detection of Early Lung Cancer Among Military Personnel (DECAMP) cohort (n = 360), and were further characterized using bronchial epithelial gene expression. RESULTS: Three clusters (preserved, interstitial predominant and emphysema predominant) were identified. Compared to the preserved cluster, the interstitial and emphysema clusters had worse lung function, exercise capacity and quality of life. In longitudinal follow-up, individuals from the emphysema group had greater declines in exercise capacity and lung function, more emphysema, more exacerbations, and higher mortality. Similarly, genes involved in inflammatory pathways (tumor necrosis factor-α, interferon-ß) are more highly expressed in bronchial epithelial cells from individuals in the emphysema cluster, while genes associated with T-cell related biology are decreased in these samples. Samples from individuals in the interstitial cluster generally had intermediate levels of expression of these genes. INTERPRETATION: Using quantitative CT imaging, we identified three groups of individuals in older ever-smokers that replicate in two cohorts. Airway gene expression differences between the three groups suggests increased levels of inflammation in the most severe clinical phenotype, possibly mediated by the tumor necrosis factor-α and interferon-ß pathways. CLINICAL TRIAL REGISTRATION: COPDGene (NCT00608764), DECAMP-1 (NCT01785342), DECAMP-2 (NCT02504697).

Somatotypes trajectories during adulthood and their association with COPD phenotypes.

RATIONALE: Chronic obstructive pulmonary disease (COPD) comprises distinct phenotypes, all characterised by airflow limitation. OBJECTIVES: We hypothesised that somatotype changes - as a surrogate of adiposity - from early adulthood follow different trajectories to reach distinct phenotypes. METHODS: Using the validated Stunkard's Pictogram, 356 COPD patients chose the somatotype that best reflects their current body build and those at ages 18, 30, 40 and 50 years. An unbiased group-based trajectory modelling was used to determine somatotype trajectories. We then compared the current COPD-related clinical and phenotypic characteristics of subjects belonging to each trajectory. MEASUREMENTS AND MAIN RESULTS: At 18 years of age, 88% of the participants described having a lean or medium somatotype (estimated body mass index (BMI) between 19 and 23 kg·m-2) while the other 12% a heavier somatotype (estimated BMI between 25 and 27 kg·m-2). From age 18 onwards, five distinct trajectories were observed. Four of them demonstrating a continuous increase in adiposity throughout adulthood with the exception of one, where the initial increase was followed by loss of adiposity after age 40. Patients with this trajectory were primarily females with low BMI and D LCO (diffusing capacity of the lung for carbon monoxide). A persistently lean trajectory was seen in 14% of the cohort. This group had significantly lower forced expiratory volume in 1 s (FEV1), D LCO, more emphysema and a worse BODE (BMI, airflow obstruction, dyspnoea and exercise capacity) score thus resembling the multiple organ loss of tissue (MOLT) phenotype. CONCLUSIONS: COPD patients have distinct somatotype trajectories throughout adulthood. Those with the MOLT phenotype maintain a lean trajectory throughout life. Smoking subjects with this lean phenotype in early adulthood deserve particular attention as they seem to develop more severe COPD.

Smaller Left Ventricle Size at Noncontrast CT Is Associated with Lower Mortality in COPDGene Participants.

Background Smokers with chronic obstructive pulmonary disease (COPD) have smaller left ventricles (LVs) due to reduced preload. Skeletal muscle wasting is also common in COPD, but less is known about its contribution to LV size. Purpose To explore the relationships between CT metrics of emphysema, venous vascular volume, and sarcopenia with the LV epicardial volume (LVEV) (myocardium and chamber) estimated from chest CT images in participants with COPD and then to determine the clinical relevance of the LVEV in multivariable models, including sex and anthropomorphic metrics. Materials and Methods The COPDGene study (ClinicalTrials.gov identifier: NCT00608764) is an ongoing prospective longitudinal observational investigation that began in 2006. LVEV, distal pulmonary venous blood volume for vessels smaller than 5 mm2 in cross section (BV5), CT emphysema, and pectoralis muscle area were retrospectively extracted from 3318 nongated, unenhanced COPDGene CT scans. Multivariable linear and Cox regression models were used to explore the association between emphysema, venous BV5, pectoralis muscle area, and LVEV as well as the association of LVEV with health status using the St George's Respiratory Questionnaire, 6-minute walk distance, and all-cause mortality. Results The median age of the cohort was 64 years (interquartile range, 57-70 years). Of the 2423 participants, 1806 were men and 617 were African American. The median LVEV between Global Initiative for Chronic Obstructive Lung Disease (GOLD) 1 and GOLD 4 COPD was reduced by 13.9% in women and 17.7% in men (P < .001 for both). In fully adjusted models, higher emphysema percentage (ß = -4.2; 95% confidence interval [CI]: -5.0, -3.4; P < .001), venous BV5 (ß = 7.0; 95% CI: 5.7, 8.2; P < .001), and pectoralis muscle area (ß = 2.7; 95% CI: 1.2, 4.1; P < .001) were independently associated with reduced LVEV. Reductions in LVEV were associated with improved health status (ß = 0.3; 95% CI: 0.1, 0.4) and 6-minute walk distance (ß = -12.2; 95% CI: -15.2, -9.3). These effects were greater in women than in men. The effect of reduced LVEV on mortality (hazard ratio: 1.07; 95% CI: 1.05, 1.09) did not vary by sex. Conclusion In women more than men with chronic obstructive pulmonary disease, a reduction in the estimated left ventricle epicardial volume correlated with a loss of pulmonary venous vasculature, greater pectoralis muscle sarcopenia, and lower all-cause mortality. © RSNA, 2020 Online supplemental material is available for this article.

Generative-based airway and vessel morphology quantification on chest CT images.

Accurately and precisely characterizing the morphology of small pulmonary structures from Computed Tomography (CT) images, such as airways and vessels, is becoming of great importance for diagnosis of pulmonary diseases. The smaller conducting airways are the major site of increased airflow resistance in chronic obstructive pulmonary disease (COPD), while accurately sizing vessels can help identify arterial and venous changes in lung regions that may determine future disorders. However, traditional methods are often limited due to image resolution and artifacts. We propose a Convolutional Neural Regressor (CNR) that provides cross-sectional measurement of airway lumen, airway wall thickness, and vessel radius. CNR is trained with data created by a generative model of synthetic structures which is used in combination with Simulated and Unsupervised Generative Adversarial Network (SimGAN) to create simulated and refined airways and vessels with known ground-truth. For validation, we first use synthetically generated airways and vessels produced by the proposed generative model to compute the relative error and directly evaluate the accuracy of CNR in comparison with traditional methods. Then, in-vivo validation is performed by analyzing the association between the percentage of the predicted forced expiratory volume in one second (FEV1%) and the value of the Pi10 parameter, two well-known measures of lung function and airway disease, for airways. For vessels, we assess the correlation between our estimate of the small-vessel blood volume and the lungs' diffusing capacity for carbon monoxide (DLCO). The results demonstrate that Convolutional Neural Networks (CNNs) provide a promising direction for accurately measuring vessels and airways on chest CT images with physiological correlates.

An open-source framework for pulmonary fissure completeness assessment.

We present an open-source framework for pulmonary fissure completeness assessment. Fissure incompleteness has been shown to associate with emphysema treatment outcomes, motivating the development of tools that facilitate completeness estimation. Generally, the task of fissure completeness assessment requires accurate detection of fissures and definition of the boundary surfaces separating the lung lobes. The framework we describe acknowledges a) the modular nature of fissure detection and lung lobe segmentation (lobe boundary detection), and b) that methods to address these challenges are varied and continually developing. It is designed to be readily deployable on existing lung lobe segmentation and fissure detection data sets. The framework consists of multiple components: a flexible quality control module that enables rapid assessment of lung lobe segmentations, an interactive lobe segmentation tool exposed through 3D Slicer for handling challenging cases, a flexible fissure representation using particles-based sampling that can handle fissure feature-strength or binary fissure detection images, and a module that performs fissure completeness estimation using voxel counting and a novel surface area estimation approach. We demonstrate the usage of the proposed framework by deploying on 100 cases exhibiting various levels of fissure completeness. We compare the two completeness level approaches and also compare to visual reads. The code is available to the community via github as part of the Chest Imaging Platform and a 3D Slicer extension module.

Estimated Ventricular Size, Asthma Severity, and Exacerbations: The Severe Asthma Research Program III Cohort.

BACKGROUND: Relative enlargement of the pulmonary artery (PA) on chest CT imaging is associated with respiratory exacerbations in patients with COPD or cystic fibrosis. We sought to determine whether similar findings were present in patients with asthma and whether these findings were explained by differences in ventricular size. METHODS: We measured the PA and aorta diameters in 233 individuals from the Severe Asthma Research Program III cohort. We also estimated right, left, and total epicardial cardiac ventricular volume indices (eERVVI, eELVVI, and eETVVI, respectively). Associations between the cardiac and PA measures (PA-to-aorta [PA/A] ratio, eERVVI-to-eELVVI [eRV/eLV] ratio, eERVVI, eELVVI, eETVVI) and clinical measures of asthma severity were assessed by Pearson correlation, and associations with asthma severity and exacerbation rate were evaluated by multivariable linear and zero-inflated negative binomial regression. RESULTS: Asthma severity was associated with smaller ventricular volumes. For example, those with severe asthma had 36.1 mL/m2 smaller eETVVI than healthy control subjects (P = .003) and 14.1 mL/m2 smaller eETVVI than those with mild/moderate disease (P = .011). Smaller ventricular volumes were also associated with a higher rate of asthma exacerbations, both retrospectively and prospectively. For example, those with an eETVVI less than the median had a 57% higher rate of exacerbations during follow-up than those with eETVVI greater than the median (P = .020). Neither PA/A nor eRV/eLV was associated with asthma severity or exacerbations. CONCLUSIONS: In patients with asthma, smaller cardiac ventricular size may be associated with more severe disease and a higher rate of asthma exacerbations. TRIAL REGISTRY: ClinicalTrials.gov; No.: NCT01761630; URL: www.clinicaltrials.gov.

Machine Learning Characterization of COPD Subtypes: Insights From the COPDGene Study.

COPD is a heterogeneous syndrome. Many COPD subtypes have been proposed, but there is not yet consensus on how many COPD subtypes there are and how they should be defined. The COPD Genetic Epidemiology Study (COPDGene), which has generated 10-year longitudinal chest imaging, spirometry, and molecular data, is a rich resource for relating COPD phenotypes to underlying genetic and molecular mechanisms. In this article, we place COPDGene clustering studies in context with other highly cited COPD clustering studies, and summarize the main COPD subtype findings from COPDGene. First, most manifestations of COPD occur along a continuum, which explains why continuous aspects of COPD or disease axes may be more accurate and reproducible than subtypes identified through clustering methods. Second, continuous COPD-related measures can be used to create subgroups through the use of predictive models to define cut-points, and we review COPDGene research on blood eosinophil count thresholds as a specific example. Third, COPD phenotypes identified or prioritized through machine learning methods have led to novel biological discoveries, including novel emphysema genetic risk variants and systemic inflammatory subtypes of COPD. Fourth, trajectory-based COPD subtyping captures differences in the longitudinal evolution of COPD, addressing a major limitation of clustering analyses that are confounded by disease severity. Ongoing longitudinal characterization of subjects in COPDGene will provide useful insights about the relationship between lung imaging parameters, molecular markers, and COPD progression that will enable the identification of subtypes based on underlying disease processes and distinct patterns of disease progression, with the potential to improve the clinical relevance and reproducibility of COPD subtypes.

Pulmonary vascular density: comparison of findings on computed tomography imaging with histology.

BACKGROUND: Exposure to cigarette smoke has been shown to lead to vascular remodelling. Computed tomography (CT) imaging measures of vascular pruning have been associated with pulmonary vascular disease, an important morbidity associated with smoking. In this study we compare CT-based measures of distal vessel loss to histological vascular and parenchymal changes. METHODS: A retrospective review of 80 patients who had undergone lung resection identified patients with imaging appropriate for three-dimensional (3D) vascular reconstruction (n=18) and a second group for two-dimensional (2D) analysis (n=19). Measurements of the volume of the small vessels (3D) and the cross-sectional area of the small vessels (<5 mm2 cross-section) were computed. Histological measures of cross-sectional area of the vasculature and loss of alveoli septa were obtained for all subjects. RESULTS: The 2D cross-sectional area of the vasculature on CT imaging was associated with the histological vascular cross-sectional area (r=0.69; p=0.001). The arterial small vessel volume assessed by CT correlated with the histological vascular cross-sectional area (r=0.50; p=0.04), a relationship that persisted even when adjusted for CT-derived measures of emphysema in a regression model. CONCLUSIONS: Loss of small vessel volume in CT imaging of smokers is associated with histological loss of vascular cross-sectional area. Imaging-based quantification of pulmonary vasculature provides a noninvasive method to study the multiscale effects of smoking on the pulmonary circulation.