The characterization of the vasculature in the mediastinum, more specifically the pulmonary artery, is of vital importance for the evaluation of several pulmonary vascular diseases. Thus, the goal of this study is to automatically segment the pulmonary artery (PA) from computed tomography angiography images, which opens up the opportunity for more complex analysis of the evolution of the PA geometry in health and disease and can be used in complex fluid mechanics models or individualized medicine. For that purpose, a new 3D convolutional neural network architecture is proposed, which is trained on images coming from different patient cohorts. The network makes use a strong data augmentation paradigm based on realistic deformations generated by applying principal component analysis to the deformation fields obtained from the affine registration of several datasets. The network is validated on 91 datasets by comparing the automatic segmentations with semi-automatically delineated ground truths in terms of mean Dice and Jaccard coefficients and mean distance between surfaces, which yields values of 0.89, 0.80 and 1.25 mm, respectively. Finally, a comparison against a Unet architecture is also included.

Imaging continues to be the modality of choice for the diagnosis of venous thromboembolic disease, particularly when incorporated into diagnostic algorithms. Improvement in imaging techniques as well as new imaging modalities and processing methods have improved diagnostic accuracy and additionally are being leveraged in prognostication and decision making for choice of intervention. In this article, we review the role of imaging in diagnosis and prognostication of venous thromboembolism. We also discuss emerging imaging approaches that may in the near future find clinical usefulness in improving diagnosis and prognostication as well as differentiating disease phenotypes.

BACKGROUND: Chronic obstructive pulmonary disease (COPD) is characterized by airway remodeling. Characterization of airway changes on computed tomography has been challenging due to the complexity of the recurring branching patterns, and this can be better measured using fractal dimensions. METHODS: We analyzed segmented airway trees of 8,135 participants enrolled in the COPDGene cohort. The fractal complexity of the segmented airway tree was measured by the Airway Fractal Dimension (AFD) using the Minkowski-Bougliand box-counting dimension. We examined associations between AFD and lung function and respiratory morbidity using multivariable regression analyses. We further estimated the extent of peribronchial emphysema (%) within 5 mm of the airway tree, as this is likely to affect AFD. We classified participants into 4 groups based on median AFD, percentage of peribronchial emphysema, and estimated survival. RESULTS: AFD was significantly associated with forced expiratory volume in one second (FEV1; P < 0.001) and FEV1/forced vital capacity (FEV1/FVC; P < 0.001) after adjusting for age, race, sex, smoking status, pack-years of smoking, BMI, CT emphysema, air trapping, airway thickness, and CT scanner type. On multivariable analysis, AFD was also associated with respiratory quality of life and 6-minute walk distance, as well as exacerbations, lung function decline, and mortality on longitudinal follow-up. We identified a subset of participants with AFD below the median and peribronchial emphysema above the median who had worse survival compared with participants with high AFD and low peribronchial emphysema (adjusted hazards ratio [HR]: 2.72; 95% CI: 2.20-3.35; P < 0.001), a substantial number of whom were not identified by traditional spirometry severity grades. CONCLUSION: Airway fractal dimension as a measure of airway branching complexity and remodeling in smokers is associated with respiratory morbidity and lung function change, offers prognostic information additional to traditional CT measures of airway wall thickness, and can be used to estimate mortality risk. TRIAL REGISTRATION: ClinicalTrials.gov identifier: NCT00608764. FUNDING: This study was supported by NIH K23 HL133438 (SPB) and the COPDGene study (NIH Grant Numbers R01 HL089897 and R01 HL089856). The COPDGene project is also supported by the COPD Foundation through contributions made to an Industry Advisory Board comprised of AstraZeneca, Boehringer Ingelheim, Novartis, Pfizer, Siemens, Sunovion and GlaxoSmithKline.

A single-nucleotide polymorphism (rs35705950) in the mucin 5B () gene promoter is associated with pulmonary fibrosis and interstitial features on chest CT but may also have beneficial effects. In non-Hispanic whites in the COPDGene cohort with interstitial features (n=454), the promoter polymorphism was associated with a 61% lower odds of a prospectively reported acute respiratory disease event (P=0.001), a longer time-to-first event (HR=0.57; P=0.006) and 40% fewer events (P=0.016). The promoter polymorphism may have a beneficial effect on the risk of acute respiratory disease events in smokers with interstitial CT features.

Computed tomography (CT) is a widely used imaging modality for screening and diagnosis. However, the deleterious effects of radiation exposure inherent in CT imaging require the development of image reconstruction methods which can reduce exposure levels. The development of iterative reconstruction techniques is now enabling the acquisition of low-dose CT images whose quality is comparable to that of CT images acquired with much higher radiation dosages. However, the characterization and calibration of the CT signal due to changes in dosage and reconstruction approaches is crucial to provide clinically relevant data. Although CT scanners are calibrated as part of the imaging workflow, the calibration is limited to select global reference values and does not consider other inherent factors of the acquisition that depend on the subject scanned (e.g. photon starvation, partial volume effect, beam hardening) and result in a non-stationary noise response. In this work, we analyze the effect of reconstruction biases caused by non-stationary noise and propose an autocalibration methodology to compensate it. Our contributions are: 1) the derivation of a functional relationship between observed bias and non-stationary noise, 2) a robust and accurate method to estimate the local variance, 3) an autocalibration methodology that does not necessarily rely on a calibration phantom, attenuates the bias caused by noise and removes the systematic bias observed in devices from different vendors. The validation of the proposed methodology was performed with a physical phantom and clinical CT scans acquired with different configurations (kernels, doses, algorithms including iterative reconstruction). The results confirmed the suitability of the proposed methods for removing the intra-device and inter-device reconstruction biases.

Introduction: The Agatston score is a well-established metric of cardiovascular disease related to clinical outcomes. It is computed from CT scans by a) measuring the volume and intensity of the atherosclerotic plaques and b) aggregating such information in an index. Objective: To generate a convolutional neural network that inputs a non-contrast chest CT scan and outputs the Agatston score associated with it directly, without a prior segmentation of Coronary Artery Calcifications (CAC). Materials and methods: We use a database of 5973 non-contrast non-ECG gated chest CT scans where the Agatston score has been manually computed. The heart of each scan is cropped automatically using an object detector. The database is split in 4973 cases for training and 1000 for testing. We train a 3D deep convolutional neural network to regress the Agatston score directly from the extracted hearts. Results: The proposed method yields a Pearson correlation coefficient of = 0.93; ≤ 0.0001 against manual reference standard in the 1000 test cases. It further stratifies correctly 72.6% of the cases with respect to standard risk groups. This compares to more complex state-of-the-art methods based on prior segmentations of the CACs, which achieve = 0.94 in ECG-gated pulmonary CT. Conclusions: A convolutional neural network can regress the Agatston score from the image of the heart directly, without a prior segmentation of the CACs. This is a new and simpler paradigm in the Agatston score computation that yields similar results to the state-of-the-art literature.

A number of chronic diseases have benefited from both imaging and personalised medicine, but unfortunately, for patients with chronic obstructive pulmonary disease (COPD), there has been little clinical uptake or recognition of the key advances in thoracic imaging that might help detect disease early, or, perhaps more importantly, might help develop and phenotype patients for novel or personalised therapies that may halt disease progression. We outline our vision for how computed tomography and magnetic resonance imaging may be used to better inform COPD patient care, and, perhaps more importantly, how these may be used to help develop new therapies directed at early disease. We think that imaging and precision medicine should be considered and used together as "precision imaging" at specific stages of COPD when the major pathologies may be more responsive to therapy. While "precision medicine" is the tailoring of medical treatment to individual patients, we define "precision imaging" as the tailoring of specific therapies and interventions to individual patients with a detailed quantitative understanding of their specific imaging phenotypes and measurements. Finally, we stress the importance of "seeing" the pathology, because without this understanding, you can neither treat nor cure patients with COPD.

Introduction: Biomarker computation using deep-learning often relies on a two-step process, where the deep learning algorithm segments the region of interest and then the biomarker is measured. We propose an alternative paradigm, where the biomarker is estimated directly using a regression network. We showcase this image-to-biomarker paradigm using two biomarkers: the estimation of bone mineral density (BMD) and the estimation of lung percentage of emphysema from CT scans. Materials and methods: We use a large database of 9,925 CT scans to train, validate and test the network for which reference standard BMD and percentage emphysema have been already computed. First, the 3D dataset is reduced to a set of canonical 2D slices where the organ of interest is visible (either spine for BMD or lungs for emphysema). This data reduction is performed using an automatic object detector. Second, The regression neural network is composed of three convolutional layers, followed by a fully connected and an output layer. The network is optimized using a momentum optimizer with an exponential decay rate, using the root mean squared error as cost function. Results: The Pearson correlation coefficients obtained against the reference standards are = 0.940 ( < 0.00001) and = 0.976 ( < 0.00001) for BMD and percentage emphysema respectively. Conclusions: The deep-learning regression architecture can learn biomarkers from images directly, without indicating the structures of interest. This approach simplifies the development of biomarker extraction algorithms. The proposed data reduction based on object detectors conveys enough information to compute the biomarkers of interest.

BACKGROUND: In smokers, the lung parenchyma is characterized by inflammation and emphysema, processes that can result in local gain and loss of lung tissue. CT measures of lung density might reflect lung tissue changes; however, longitudinal data regarding the effects of CT lung tissue on FEV in smokers with and without COPD are scarce. METHODS: The 15th percentile of CT lung density was obtained from the scans of 3,390 smokers who completed baseline and 5-year follow-up of the Genetic Epidemiology of COPD (COPDGene) study visits. The longitudinal relationship between total lung capacity-adjusted lung density (TLC-PD15) and FEV was assessed by using multivariable mixed models. Separate models were performed in smokers at risk, smokers with preserved ratio and impaired spirometry (PRISm), and smokers with COPD according to the Global Initiative for Chronic Obstructive Lung Disease (GOLD) staging system. RESULTS: The direction of the relationship between lung density and lung function was GOLD stage dependent. In smokers with PRISm, a 1-g/L decrease in TLC-PD15 was associated with an increase of 2.8 mL FEV (P = .02). In contrast, among smokers with GOLD III to IV COPD, a 1-g/L decrease in TLC-PD15 was associated with a decrease of 4.1 mL FEV (P = .002). CONCLUSIONS: A decline in TLC-PD15 was associated with an increase or decrease in FEV depending on disease severity. The associations are GOLD stage specific, and their presence might influence the interpretation of future studies that use CT lung density as an intermediate study end point for a decline in lung function. TRIAL REGISTRY: ClinicalTrials.gov; No.: NCT00608764; URL: www.clinicaltrials.gov.

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.

BACKGROUND: Genome-wide association studies (GWAS) have identified single nucleotide polymorphisms (SNPs) significantly associated with chronic obstructive pulmonary disease (COPD). However, many genetic variants show suggestive evidence for association but do not meet the strict threshold for genome-wide significance. Integrative analysis of multiple omics datasets has the potential to identify novel genes involved in disease pathogenesis by leveraging these variants in a functional, regulatory context. RESULTS: We performed expression quantitative trait locus (eQTL) analysis using genome-wide SNP genotyping and gene expression profiling of lung tissue samples from 86 COPD cases and 31 controls, testing for SNPs associated with gene expression levels. These results were integrated with a prior COPD GWAS using an ensemble statistical and network methods approach to identify relevant genes and observe them in the context of overall genetic control of gene expression to highlight co-regulated genes and disease pathways. We identified 250,312 unique SNPs and 4997 genes in the cis(local)-eQTL analysis (5% false discovery rate). The top gene from the integrative analysis was MAPT, a gene recently identified in an independent GWAS of lung function. The genes HNRNPAB and PCBP2 with RNA binding activity and the gene ACVR1B were identified in network communities with validated disease relevance. CONCLUSIONS: The integration of lung tissue gene expression with genome-wide SNP genotyping and subsequent intersection with prior GWAS and omics studies highlighted candidate genes within COPD loci and in communities harboring known COPD genes. This integration also identified novel disease genes in sub-threshold regions that would otherwise have been missed through GWAS.

BACKGROUND: Exposure to ambient air pollution has been associated with lower lung function in adults, but few studies have investigated associations with radiographic lung and airway measures. METHODS: We ascertained lung volume, mass, density, visual emphysema, airway size, and airway wall area by computed tomography (CT) among 2,545 nonsmoking Framingham CT substudy participants. We examined associations of home distance to major road and PM2.5 (2008 average from a spatiotemporal model using satellite data) with these outcomes using linear and logistic regression models adjusted for age, sex, height, weight, census tract median household value and population density, education, pack-years of smoking, household tobacco exposure, cohort, and date. We tested for differential susceptibility by sex, smoking status (former vs. never), and cohort. RESULTS: The mean participant age was 60.1 years (standard deviation 11.9 years). Median PM2.5 level was 9.7 µg/m (interquartile range, 1.6). Living <100 m from a major road was associated with a 108 ml (95% CI = 8, 207) higher lung volume compared with ≥400 m away. There was also a log-linear association between proximity to road and higher lung volume. There were no convincing associations of proximity to major road or PM2.5 with the other pulmonary CT measures. In subgroup analyses, road proximity was associated with lower lung density among men and higher odds of emphysema among former smokers. CONCLUSIONS: Living near a major road was associated with higher average lung volume, but otherwise, we found no association between ambient pollution and radiographic measures of emphysema or airway disease.

RATIONALE: Lung function and chronic obstructive pulmonary disease (COPD) are heritable traits. Genome-wide association studies (GWAS) have identified numerous pulmonary function and COPD loci, primarily in cohorts of European ancestry. OBJECTIVES: Perform a GWAS of COPD phenotypes in Hispanic/Latino populations to identify loci not previously detected in European populations. METHODS: GWAS of lung function and COPD in Hispanic/Latino participants from a population-based cohort. We performed replication studies of novel loci in independent studies. MEASUREMENTS AND MAIN RESULTS: Among 11,822 Hispanic/Latino participants, we identified eight novel signals; three replicated in independent populations of European Ancestry. A novel locus for FEV in ZSWIM7 (rs4791658; P = 4.99 × 10) replicated. A rare variant (minor allele frequency = 0.002) in HAL (rs145174011) was associated with FEV/FVC (P = 9.59 × 10) in a region previously identified for COPD-related phenotypes; it remained significant in conditional analyses but did not replicate. Admixture mapping identified a novel region, with a variant in AGMO (rs41331850), associated with Amerindian ancestry and FEV, which replicated. A novel locus for FEV identified among ever smokers (rs291231; P = 1.92 × 10) approached statistical significance for replication in admixed populations of African ancestry, and a novel SNP for COPD in PDZD2 (rs7709630; P = 1.56 × 10) regionally replicated. In addition, loci previously identified for lung function in European samples were associated in Hispanic/Latino participants in the Hispanic Community Health Study/Study of Latinos at the genome-wide significance level. CONCLUSIONS: We identified novel signals for lung function and COPD in a Hispanic/Latino cohort. Including admixed populations when performing genetic studies may identify variants contributing to genetic etiologies of COPD.

Chronic obstructive pulmonary disease (COPD) is a syndrome caused by damage to the lungs that results in decreased pulmonary function and reduced structural integrity. Pulmonary function testing (PFT) is used to diagnose and stratify COPD into severity groups, and computed tomography (CT) imaging of the chest is often used to assess structural changes in the lungs. We hypothesized that the combination of PFT and CT phenotypes would provide a more powerful tool for assessing underlying morphologic differences associated with pulmonary function in COPD than does PFT alone. We used factor analysis of 26 variables to classify 8,157 participants recruited into the COPDGene cohort between January 2008 and June 2011 from 21 clinical centers across the United States. These factors were used as predictors of all-cause mortality using Cox proportional hazards modeling. Five factors explained 80% of the covariance and represented the following domains: factor 1, increased emphysema and decreased pulmonary function; factor 2, airway disease and decreased pulmonary function; factor 3, gas trapping; factor 4, CT variability; and factor 5, hyperinflation. After more than 46,079 person-years of follow-up, factors 1 through 4 were associated with mortality and there was a significant synergistic interaction between factors 1 and 2 on death. Considering CT measures along with PFT in the assessment of COPD can identify patients at particularly high risk for death.

The clinical manifestations of chronic obstructive pulmonary disease (COPD) reflect an aggregate of multiple pulmonary and extrapulmonary processes. It is increasingly clear that full assessment of these processes is essential to characterize disease burden and to tailor therapy. Medical imaging has advanced such that it is now possible to obtain in vivo insight in the presence and severity of lung disease-associated features. In this review, we have assembled data from multiple disciplines of medical imaging research to review the role of imaging in characterization of COPD. Topics include imaging of the lungs, body composition, and extrapulmonary tissue metabolism. The primary focus is on imaging modalities that are widely available in clinical care settings and that potentially contribute to describing COPD heterogeneity and enhance our insight in underlying pathophysiological processes and their structural and functional effects.