Explore the vast range of titles available.

Abstract Rationale Deep learning is a powerful tool that may allow for improved outcome prediction. Objectives To determine if deep learning, specifically convolutional neural network (CNN) analysis, could detect and stage chronic obstructive pulmonary disease (COPD) and predict acute respiratory disease (ARD) events and mortality in smokers. Methods A CNN was trained using computed tomography scans from 7,983 COPDGene participants and evaluated using 1,000 nonoverlapping COPDGene participants and 1,672 ECLIPSE participants. Logistic regression (C statistic and the Hosmer-Lemeshow test) was used to assess COPD diagnosis and ARD prediction. Cox regression (C index and the Greenwood-Nam-D’Agnostino test) was used to assess mortality. Measurements and Main Results In COPDGene, the C statistic for the detection of COPD was 0.856. A total of 51.1% of participants in COPDGene were accurately staged and 74.95% were within one stage. In ECLIPSE, 29.4% were accurately staged and 74.6% were within one stage. In COPDGene and ECLIPSE, the C statistics for ARD events were 0.64 and 0.55, respectively, and the Hosmer-Lemeshow P values were 0.502 and 0.380, respectively, suggesting no evidence of poor calibration. In COPDGene and ECLIPSE, CNN predicted mortality with fair discrimination (C indices, 0.72 and 0.60, respectively), and without evidence of poor calibration (Greenwood-Nam-D’Agnostino P values, 0.307 and 0.331, respectively). Conclusions A deep-learning approach that uses only computed tomography imaging data can identify those smokers who have COPD and predict who are most likely to have ARD events and those with the highest mortality. At a population level CNN analysis may be a powerful tool for risk assessment.

Abstract Rationale The relationship between the development and/or progression of interstitial lung abnormalities (ILA) and clinical outcomes has not been previously investigated. Objectives To determine the risk factors for, and the clinical consequences of, having ILA progression in participants from the Framingham Heart Study. Methods ILA were assessed in 1,867 participants who had serial chest computed tomography (CT) scans approximately 6 years apart. Mixed effect regression (and Cox) models were used to assess the association between ILA progression and pulmonary function decline (and mortality). Measurements and Main Results During the follow-up period 660 (35%) participants did not have ILA on either CT scan, 37 (2%) had stable to improving ILA, and 118 (6%) had ILA with progression (the remaining participants without ILA were noted to be indeterminate on at least one CT scan). Increasing age and increasing copies of the MUC5B promoter polymorphism were associated with ILA progression. After adjustment for covariates, ILA progression was associated with a greater FVC decline when compared with participants without ILA (20 ml; SE, ±6 ml; P = 0.0005) and with those with ILA without progression (25 ml; SE, ±11 ml; P = 0.03). Over a median follow-up time of approximately 4 years, after adjustment, ILA progression was associated with an increase in the risk of death (hazard ratio, 3.9; 95% confidence interval, 1.3–10.9; P = 0.01) when compared with those without ILA. Conclusions These findings demonstrate that ILA progression in the Framingham Heart Study is associated with an increased rate of pulmonary function decline and increased risk of death.

Variants in the gene encoding mucin 5B ( MUC5B ) have been associated with interstitial fibrosis. This study shows a relationship between the presence of the associated variants in MUC5B and interstitial lung abnormalities in participants in a Framingham study cohort. Subclinical interstitial lung abnormalities are relatively common findings on imaging studies in smokers and elderly persons. 1 Accumulating evidence suggests that these abnormalities may precede the development of clinically relevant pulmonary fibrosis. 1 – 7 However, it is not known whether there is a genetic association between interstitial lung abnormalities and pulmonary fibrosis in the general population. Recently, a single-nucleotide polymorphism (SNP) (rs35705950) in the promoter of the gene encoding mucin 5B ( MUC5B ) was shown to be associated with both familial interstitial pneumonia and sporadic idiopathic pulmonary fibrosis. 8 In addition, the MUC5B variant was associated with increased expression of MUC5B in . . .

Abstract Rationale Cor pulmonale (right ventricular [RV] dilation) and cor pulmonale parvus (RV shrinkage) are both described in chronic obstructive pulmonary disease (COPD). The identification of emphysema as a shared risk factor suggests that additional disease characterization is needed to understand these widely divergent cardiac processes. Objectives To explore the relationship between computed tomography measures of emphysema and distal pulmonary arterial morphology with RV volume, and their association with exercise capacity and mortality in ever-smokers with COPD enrolled in the COPDGene Study. Methods Epicardial (myocardium and chamber) RV volume (RVEV), distal pulmonary arterial blood vessel volume (arterial BV5: vessels <5 mm2 in cross-section), and objective measures of emphysema were extracted from 3,506 COPDGene computed tomography scans. Multivariable linear and Cox regression models and the log-rank test were used to explore the association between emphysema, arterial BV5, and RVEV with exercise capacity (6-min-walk distance) and all-cause mortality. Measurements and Main Results The RVEV was approximately 10% smaller in Global Initiative for Chronic Obstructive Lung Disease stage 4 versus stage 1 COPD (P < 0.0001). In multivariable modeling, a 10-ml decrease in arterial BV5 (pruning) was associated with a 1-ml increase in RVEV. For a given amount of emphysema, relative preservation of the arterial BV5 was associated with a smaller RVEV. An increased RVEV was associated with reduced 6-minute-walk distance and in those with arterial pruning an increased mortality. Conclusions Pulmonary arterial pruning is associated with clinically significant increases in RV volume in smokers with COPD and is related to exercise capacity and mortality in COPD. Clinical trial registered with www.clinicaltrials.gov (NCT 00608764).

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. 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. 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. 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.

Loss of the peripheral pulmonary vasculature, termed vascular pruning, is associated with disease severity in patients with chronic obstructive pulmonary disease. To determine if pulmonary vascular pruning is associated with asthma severity and exacerbations. We measured the total pulmonary blood vessel volume (TBV) and the blood vessel volume of vessels less than 5 mm in cross-sectional area (BV5) and of vessels less than 10 mm (BV10) in cross-sectional area on noncontrast computed tomographic scans of participants from the Severe Asthma Research Program. Lower values of the BV5 to TBV ratio (BV5/TBV) and the BV10 to TBV ratio (BV10/TBV) represented vascular pruning (loss of the peripheral pulmonary vasculature). Compared with healthy control subjects, patients with severe asthma had more pulmonary vascular pruning. Among those with asthma, those with poor asthma control had more pruning than those with well-controlled disease. Pruning of the pulmonary vasculature was also associated with lower percent predicted FEV and FVC, greater peripheral and sputum eosinophilia, and higher BAL serum amyloid A/lipoxin A ratio but not with low-attenuation area or with sputum neutrophilia. Compared with individuals with less pruning, individuals with the most vascular pruning had 150% greater odds of reporting an asthma exacerbation (odds ratio, 2.50; confidence interval, 1.05-5.98; P = 0.039 for BV10/TBV) and reported 45% more asthma exacerbations during follow-up (incidence rate ratio, 1.45; confidence interval, 1.02-2.06; P = 0.036 for BV10/TBV). Pruning of the peripheral pulmonary vasculature is associated with asthma severity, control, and exacerbations, and with lung function and eosinophilia.

Background Low muscle mass is associated with increased mortality in the general population but its prognostic value in at-risk smokers, those without expiratory airflow obstruction, is unknown. We aimed to test the hypothesis that reduced muscle mass is associated with increased mortality in at-risk smokers. Methods Measures of both pectoralis and paravertebral erector spinae muscle cross-sectional area (PMA and PVMA, respectively) as well as emphysema on chest computed tomography (CT) scans were performed in 3705 current and former at-risk smokers (≥10 pack-years) aged 45–80 years enrolled into the COPDGene Study between 2008 and 2013. Vital status was ascertained through death certificate. The association between low muscle mass and mortality was assessed using Cox regression analysis. Results During a median of 6.5 years of follow-up, 212 (5.7%) at-risk smokers died. At-risk smokers in the lowest (vs. highest) sex-specific quartile of PMA but not PVMA had 84% higher risk of death in adjusted models for demographics, smoking, dyspnea, comorbidities, exercise capacity, lung function, emphysema on CT, and coronary artery calcium content (hazard ratio [HR] 1.85 95% Confidence interval [1.14–3.00] P  = 0.01). Results were consistent when the PMA index (PMA/height 2 ) was used instead of quartiles. The association between PMA and death was modified by smoking status ( P  = 0.04). Current smokers had a significantly increased risk of death (lowest vs. highest PMA quartile, HR 2.25 [1.25–4.03] P  = 0.007) while former smokers did not. Conclusions Low muscle mass as measured on chest CT scans is associated with increased mortality in current smokers without airflow obstruction. Trial registration NCT00608764

Abstract Rationale Muscle wasting in chronic obstructive pulmonary disease (COPD) is associated with a poor prognosis and is not readily assessed by measures of body mass index (BMI). BMI does not discriminate between relative proportions of adipose tissue and lean muscle and may be insensitive to early pathologic changes in body composition. Computed tomography (CT)–based assessments of the pectoralis muscles may provide insight into the clinical significance of skeletal muscles in smokers. Objectives We hypothesized that objective assessment of the pectoralis muscle area on chest CT scans provides information that is clinically relevant and independent of BMI. Methods Data from the ECLIPSE (Evaluation of COPD Longitudinally to Identify Predictive Surrogate Endpoints) Study (n = 73) were used to assess the relationship between pectoralis muscle area and fat-free mass. We then used data in a subset (n = 966) of a larger cohort, the COPDGene (COPD Genetic Epidemiology) Study, to explore the relationship between pectoralis muscle area and COPD-related traits. Measurements and Main Results We first investigated the correlation between pectoralis muscle area and fat-free mass, using data from a subset of participants in the ECLIPSE Study. We then further investigated pectoralis muscle area in COPDGene Study participants and found that higher pectoralis muscle area values were associated with greater height, male sex, and younger age. On subsequent clinical correlation, compared with BMI, pectoralis muscle area was more significantly associated with COPD-related traits, including spirometric measures, dyspnea, and 6-minute-walk distance (6MWD). For example, on average, each 10-cm2 increase in pectoralis muscle area was associated with a 0.8-unit decrease in the BODE (Body mass index, Obstruction, Dyspnea, Exercise) index (95% confidence interval, –1.0 to –0.6; P < 0.001). Furthermore, statistically significant associations between pectoralis muscle area and COPD-related traits remained even after adjustment for BMI. Conclusions CT-derived pectoralis muscle area provides relevant indices of COPD morbidity that may be more predictive of important COPD-related traits than BMI. However, the relationship with clinically relevant outcomes such as hospitalization and death requires additional investigation. Pectoralis muscle area is a convenient measure that can be collected in the clinical setting in addition to BMI.

Abstract Rationale The role of 3-hydroxy-3-methylglutaryl-coenzyme A reductase inhibitors (statins) in the development or progression of interstitial lung disease (ILD) is controversial. Objectives To evaluate the association between statin use and ILD. Methods We used regression analyses to evaluate the association between statin use and interstitial lung abnormalities (ILA) in a large cohort of smokers from COPDGene. Next, we evaluated the effect of statin pretreatment on bleomycin-induced fibrosis in mice and explored the mechanism behind these observations in vitro. Measurements and Main Results In COPDGene, 38% of subjects with ILA were taking statins compared with 27% of subjects without ILA. Statin use was positively associated in ILA (odds ratio, 1.60; 95% confidence interval, 1.03–2.50; P = 0.04) after adjustment for covariates including a history of high cholesterol or coronary artery disease. This association was modified by the hydrophilicity of statin and the age of the subject. Next, we demonstrate that statin administration aggravates lung injury and fibrosis in bleomycin-treated mice. Statin pretreatment enhances caspase-1–mediated immune responses in vivo and in vitro; the latter responses were abolished in bone marrow–derived macrophages isolated from Nlrp3−/− and Casp1−/− mice. Finally, we provide further insights by demonstrating that statins enhance NLRP3-inflammasome activation by increasing mitochondrial reactive oxygen species generation in macrophages. Conclusions Statin use is associated with ILA among smokers in the COPDGene study and enhances bleomycin-induced lung inflammation and fibrosis in the mouse through a mechanism involving enhanced NLRP3-inflammasome activation. Our findings suggest that statins may influence the susceptibility to, or progression of, ILD. Clinical trial registered with www.clinicaltrials.gov (NCT 00608764).

Routinely, there is a visual basis to nuclear medicine reporting: a reporter subjectively places a patient’s condition into one of multiple discrete classes based on what they see. The addition of a quantitative result, such as a standardised uptake value (SUV), would provide a numerical insight into the nature of uptake, delivering greater objectivity, and perhaps improved patient management.For bone scintigraphy in particular quantification could increase the accuracy of diagnosis by helping to differentiate normal from abnormal uptake. Access to quantitative data might also enhance our ability to characterise lesions, stratify and monitor patients’ conditions, and perform reliable dosimetry for radionuclide therapies. But is there enough evidence to suggest that we, as a community, should be making more effort to implement quantitative bone SPECT in routine clinical practice?We carried out multiple queries through the PubMed search engine to facilitate a cross-sectional review of the current status of bone SPECT quantification. Highly cited papers were assessed in more focus to scrutinise their conclusions.An increasing number of authors are reporting findings in terms of metrics such as SUVmax. Although interest in the field in general remains high, the rate of clinical implementation of quantitative bone SPECT remains slow and there is a significant amount of validation required before we get carried away.