Airway tree caliber heterogeneity and airflow obstruction among older adults.

Smaller mean airway tree caliber is associated with airflow obstruction and chronic obstructive pulmonary disease (COPD). We investigated whether airway tree caliber heterogeneity was associated with airflow obstruction and COPD. Two community-based cohorts (MESA Lung, CanCOLD) and a longitudinal case-control study of COPD (SPIROMICS) performed spirometry and computed tomography measurements of airway lumen diameters at standard anatomical locations (trachea-to-subsegments) and total lung volume. Percent-predicted airway lumen diameters were calculated using sex-specific reference equations accounting for age, height, and lung volume. The association of airway tree caliber heterogeneity, quantified as the standard deviation (SD) of percent-predicted airway lumen diameters, with baseline forced expired volume in 1-second (FEV1), FEV1/forced vital capacity (FEV1/FVC) and COPD, as well as longitudinal spirometry, were assessed using regression models adjusted for age, sex, height, race-ethnicity, and mean airway tree caliber. Among 2,505 MESA Lung participants (means ± SD age: 69 ± 9 yr; 53% female, mean airway tree caliber: 99 ± 10% predicted, airway tree caliber heterogeneity: 14 ± 5%; median follow-up: 6.1 yr), participants in the highest quartile of airway tree caliber heterogeneity exhibited lower FEV1 (adjusted mean difference: -125 mL, 95%CI: -171,-79), lower FEV1/FVC (adjusted mean difference: -0.01, 95%CI: -0.02,-0.01), and higher odds of COPD (adjusted odds ratio: 1.42, 95%CI: 1.01-2.02) when compared with the lowest quartile, whereas longitudinal changes in FEV1 and FEV1/FVC did not differ significantly. Observations in CanCOLD and SPIROMICS were consistent. Among older adults, airway tree caliber heterogeneity was associated with airflow obstruction and COPD at baseline but was not associated with longitudinal changes in spirometry.NEW & NOTEWORTHY In this study, by leveraging two community-based samples and a case-control study of heavy smokers, we show that among older adults, airway tree caliber heterogeneity quantified by CT is associated with airflow obstruction and COPD independent of age, sex, height, race-ethnicity, and dysanapsis. These observations suggest that airway tree caliber heterogeneity is a structural trait associated with low baseline lung function and normal decline trajectory that is relevant to COPD.

Pulmonary emphysema subtypes defined by unsupervised machine learning on CT scans.

BACKGROUND: Treatment and preventative advances for chronic obstructive pulmonary disease (COPD) have been slow due, in part, to limited subphenotypes. We tested if unsupervised machine learning on CT images would discover CT emphysema subtypes with distinct characteristics, prognoses and genetic associations. METHODS: New CT emphysema subtypes were identified by unsupervised machine learning on only the texture and location of emphysematous regions on CT scans from 2853 participants in the Subpopulations and Intermediate Outcome Measures in COPD Study (SPIROMICS), a COPD case-control study, followed by data reduction. Subtypes were compared with symptoms and physiology among 2949 participants in the population-based Multi-Ethnic Study of Atherosclerosis (MESA) Lung Study and with prognosis among 6658 MESA participants. Associations with genome-wide single-nucleotide-polymorphisms were examined. RESULTS: The algorithm discovered six reproducible (interlearner intraclass correlation coefficient, 0.91-1.00) CT emphysema subtypes. The most common subtype in SPIROMICS, the combined bronchitis-apical subtype, was associated with chronic bronchitis, accelerated lung function decline, hospitalisations, deaths, incident airflow limitation and a gene variant near DRD1, which is implicated in mucin hypersecretion (p=1.1 ×10-8). The second, the diffuse subtype was associated with lower weight, respiratory hospitalisations and deaths, and incident airflow limitation. The third was associated with age only. The fourth and fifth visually resembled combined pulmonary fibrosis emphysema and had distinct symptoms, physiology, prognosis and genetic associations. The sixth visually resembled vanishing lung syndrome. CONCLUSION: Large-scale unsupervised machine learning on CT scans defined six reproducible, familiar CT emphysema subtypes that suggest paths to specific diagnosis and personalised therapies in COPD and pre-COPD.

Cardiac Adipose Tissue Segmentation via Image-Level Annotations.

Automatically identifying the structural substrates underlying cardiac abnormalities can potentially provide real-time guidance for interventional procedures. With the knowledge of cardiac tissue substrates, the treatment of complex arrhythmias such as atrial fibrillation and ventricular tachycardia can be further optimized by detecting arrhythmia substrates to target for treatment (i.e., adipose) and identifying critical structures to avoid. Optical coherence tomography (OCT) is a real-time imaging modality that aids in addressing this need. Existing approaches for cardiac image analysis mainly rely on fully supervised learning techniques, which suffer from the drawback of workload on labor-intensive annotation process of pixel-wise labeling. To lessen the need for pixel-wise labeling, we develop a two-stage deep learning framework for cardiac adipose tissue segmentation using image-level annotations on OCT images of human cardiac substrates. In particular, we integrate class activation mapping with superpixel segmentation to solve the sparse tissue seed challenge raised in cardiac tissue segmentation. Our study bridges the gap between the demand on automatic tissue analysis and the lack of high-quality pixel-wise annotations. To the best of our knowledge, this is the first study that attempts to address cardiac tissue segmentation on OCT images via weakly supervised learning techniques. Within an in-vitro human cardiac OCT dataset, we demonstrate that our weakly supervised approach on image-level annotations achieves comparable performance as fully supervised methods trained on pixel-wise annotations.

Fibrosis severity scoring on Sirius red histology with multiple-instance deep learning.

Non-alcoholic fatty liver disease (NAFLD) is now the leading cause of chronic liver disease, affecting approximately 30% of people worldwide. Histopathology reading of fibrosis patterns is crucial to diagnosing NAFLD. In particular, separating mild from severe stages corresponds to a critical transition as it correlates with clinical outcomes. Deep Learning for digitized histopathology whole-slide images (WSIs) can reduce high inter- and intra-rater variability. We demonstrate a novel solution to score fibrosis severity on a retrospective cohort of 152 Sirius-Red WSIs, with fibrosis stage annotated at slide level by an expert pathologist. We exploit multiple instance learning and multiple-inferences to address the sparsity of pathological signs. We achieved an accuracy of , an F1 score of and an AUC of . These results set new state-of-the-art benchmarks for this application.

Quantification of lung ventilation defects on hyperpolarized MRI: The Multi-Ethnic Study of Atherosclerosis (MESA) COPD study.

PURPOSE: To develop an end-to-end deep learning (DL) framework to segment ventilation defects on pulmonary hyperpolarized MRI. MATERIALS AND METHODS: The Multi-Ethnic Study of Atherosclerosis Chronic Obstructive Pulmonary Disease (COPD) study is a nested longitudinal case-control study in older smokers. Between February 2016 and July 2017, 56 participants (age, mean ± SD, 74 ± 8 years; 34 men) underwent same breath-hold proton (1H) and helium (3He) MRI, which were annotated for non-ventilated, hypo-ventilated, and normal-ventilated lungs. In this retrospective DL study, 820 1H and 3He slices from 42/56 (75%) participants were randomly selected for training, with the remaining 14/56 (25%) for test. Full lung masks were segmented using a traditional U-Net on 1H MRI and were imported into a cascaded U-Net, which were used to segment ventilation defects on 3He MRI. Models were trained with conventional data augmentation (DA) and generative adversarial networks (GAN)-DA. RESULTS: Conventional-DA improved 1H and 3He MRI segmentation over the non-DA model (P = 0.007 to 0.03) but GAN-DA did not yield further improvement. The cascaded U-Net improved non-ventilated lung segmentation (P < 0.005). Dice similarity coefficients (DSC) between manually and DL-segmented full lung, non-ventilated, hypo-ventilated, and normal-ventilated regions were 0.965 ± 0.010, 0.840 ± 0.057, 0.715 ± 0.175, and 0.883 ± 0.060, respectively. We observed no statistically significant difference in DCSs between participants with and without COPD (P = 0.41, 0.06, and 0.18 for non-ventilated, hypo-ventilated, and normal-ventilated regions, respectively). CONCLUSION: The proposed cascaded U-Net framework generated fully-automated segmentation of ventilation defects on 3He MRI among older smokers with and without COPD that is consistent with our reference method.

Suggestive annotation of brain MR images with gradient-guided sampling.

Machine learning has been widely adopted for medical image analysis in recent years given its promising performance in image segmentation and classification tasks. The success of machine learning, in particular supervised learning, depends on the availability of manually annotated datasets. For medical imaging applications, such annotated datasets are not easy to acquire, it takes a substantial amount of time and resource to curate an annotated medical image set. In this paper, we propose an efficient annotation framework for brain MR images that can suggest informative sample images for human experts to annotate. We evaluate the framework on two different brain image analysis tasks, namely brain tumour segmentation and whole brain segmentation. Experiments show that for brain tumour segmentation task on the BraTS 2019 dataset, training a segmentation model with only 7% suggestively annotated image samples can achieve a performance comparable to that of training on the full dataset. For whole brain segmentation on the MALC dataset, training with 42% suggestively annotated image samples can achieve a comparable performance to training on the full dataset. The proposed framework demonstrates a promising way to save manual annotation cost and improve data efficiency in medical imaging applications.

QU-BraTS: MICCAI BraTS 2020 Challenge on Quantifying Uncertainty in Brain Tumor Segmentation - Analysis of Ranking Scores and Benchmarking Results.

Deep learning (DL) models have provided state-of-the-art performance in various medical imaging benchmarking challenges, including the Brain Tumor Segmentation (BraTS) challenges. However, the task of focal pathology multi-compartment segmentation (e.g., tumor and lesion sub-regions) is particularly challenging, and potential errors hinder translating DL models into clinical workflows. Quantifying the reliability of DL model predictions in the form of uncertainties could enable clinical review of the most uncertain regions, thereby building trust and paving the way toward clinical translation. Several uncertainty estimation methods have recently been introduced for DL medical image segmentation tasks. Developing scores to evaluate and compare the performance of uncertainty measures will assist the end-user in making more informed decisions. In this study, we explore and evaluate a score developed during the BraTS 2019 and BraTS 2020 task on uncertainty quantification (QU-BraTS) and designed to assess and rank uncertainty estimates for brain tumor multi-compartment segmentation. This score (1) rewards uncertainty estimates that produce high confidence in correct assertions and those that assign low confidence levels at incorrect assertions, and (2) penalizes uncertainty measures that lead to a higher percentage of under-confident correct assertions. We further benchmark the segmentation uncertainties generated by 14 independent participating teams of QU-BraTS 2020, all of which also participated in the main BraTS segmentation task. Overall, our findings confirm the importance and complementary value that uncertainty estimates provide to segmentation algorithms, highlighting the need for uncertainty quantification in medical image analyses. Finally, in favor of transparency and reproducibility, our evaluation code is made publicly available at https://github.com/RagMeh11/QU-BraTS.

Changes in neonatal admissions, care processes and outcomes in England and Wales during the COVID-19 pandemic: a whole population cohort study.

OBJECTIVES: The COVID-19 pandemic instigated multiple societal and healthcare interventions with potential to affect perinatal practice. We evaluated population-level changes in preterm and full-term admissions to neonatal units, care processes and outcomes. DESIGN: Observational cohort study using the UK National Neonatal Research Database. SETTING: England and Wales. PARTICIPANTS: Admissions to National Health Service neonatal units from 2012 to 2020. MAIN OUTCOME MEASURES: Admissions by gestational age, ethnicity and Index of Multiple Deprivation, and key care processes and outcomes. METHODS: We calculated differences in numbers and rates between April and June 2020 (spring), the first 3 months of national lockdown (COVID-19 period), and December 2019-February 2020 (winter), prior to introduction of mitigation measures, and compared them with the corresponding differences in the previous 7 years. We considered the COVID-19 period highly unusual if the spring-winter difference was smaller or larger than all previous corresponding differences, and calculated the level of confidence in this conclusion. RESULTS: Marked fluctuations occurred in all measures over the 8 years with several highly unusual changes during the COVID-19 period. Total admissions fell, having risen over all previous years (COVID-19 difference: -1492; previous 7-year difference range: +100, +1617; p<0.001); full-term black admissions rose (+66; -64, +35; p<0.001) whereas Asian (-137; -14, +101; p<0.001) and white (-319; -235, +643: p<0.001) admissions fell. Transfers to higher and lower designation neonatal units increased (+129; -4, +88; p<0.001) and decreased (-47; -25, +12; p<0.001), respectively. Total preterm admissions decreased (-350; -26, +479; p<0.001). The fall in extremely preterm admissions was most marked in the two lowest socioeconomic quintiles. CONCLUSIONS: Our findings indicate substantial changes occurred in care pathways and clinical thresholds, with disproportionate effects on black ethnic groups, during the immediate COVID-19 period, and raise the intriguing possibility that non-healthcare interventions may reduce extremely preterm births.

Birthweight and patterns of postnatal weight gain in very and extremely preterm babies in England and Wales, 2008-19: a cohort study.

BACKGROUND: Intrauterine and postnatal weight are widely regarded as biomarkers of fetal and neonatal wellbeing, but optimal weight gain following preterm birth is unknown. We aimed to describe changes over time in birthweight and postnatal weight gain in very and extremely preterm babies, in relation to major morbidity and healthy survival. METHODS: In this cohort study, we used whole-population data from the UK National Neonatal Research Database for infants below 32 weeks gestation admitted to neonatal units in England and Wales between Jan 1, 2008, and Dec 31, 2019. We used non-linear Gaussian process to estimate monthly trends, and Bayesian multilevel regression to estimate unadjusted and adjusted coefficients. We evaluated birthweight; weight change from birth to 14 days; weight at 36 weeks postmenstrual age; associated Z scores; and longitudinal weights for babies surviving to 36 weeks postmenstrual age with and without major morbidities. We adjusted birthweight for antenatal, perinatal, and demographic variables. We additionally adjusted change in weight at 14 days and weight at 36 weeks postmenstrual age, and their Z scores, for postnatal variables. FINDINGS: The cohort comprised 90 817 infants. Over the 12-year period, mean differences adjusted for antenatal, perinatal, demographic, and postnatal variables were 0 g (95% compatibility interval -7 to 7) for birthweight (-0·01 [-0·05 to 0·03] for change in associated Z score); 39 g (26 to 51) for change in weight from birth to 14 days (0·14 [0·08 to 0·19] for change in associated Z score); and 105 g (81 to 128) for weight at 36 weeks postmenstrual age (0·27 [0·21 to 0·33] for change in associated Z score). Greater weight at 36 weeks postmenstrual age was robust to additional adjustment for enteral nutritional intake. In babies surviving without major morbidity, weight velocity in all gestational age groups stabilised at around 34 weeks postmenstrual age at 16-25 g per day along parallel percentile lines. INTERPRETATION: The birthweight of very and extremely preterm babies has remained stable over 12 years. Early postnatal weight loss has decreased, and subsequent weight gain has increased, but weight at 36 weeks postmenstrual age is consistently below birth percentile. In babies without major morbidity, weight velocity follows a consistent trajectory, offering opportunity to construct novel preterm growth curves despite lack of knowledge of optimal postnatal weight gain. FUNDING: UK Medical Research Council.

Novel Subtypes of Pulmonary Emphysema Based on Spatially-Informed Lung Texture Learning: The Multi-Ethnic Study of Atherosclerosis (MESA) COPD Study.

Pulmonary emphysema overlaps considerably with chronic obstructive pulmonary disease (COPD), and is traditionally subcategorized into three subtypes previously identified on autopsy. Unsupervised learning of emphysema subtypes on computed tomography (CT) opens the way to new definitions of emphysema subtypes and eliminates the need of thorough manual labeling. However, CT-based emphysema subtypes have been limited to texture-based patterns without considering spatial location. In this work, we introduce a standardized spatial mapping of the lung for quantitative study of lung texture location and propose a novel framework for combining spatial and texture information to discover spatially-informed lung texture patterns (sLTPs) that represent novel emphysema subtype candidates. Exploiting two cohorts of full-lung CT scans from the MESA COPD (n = 317) and EMCAP (n = 22) studies, we first show that our spatial mapping enables population-wide study of emphysema spatial location. We then evaluate the characteristics of the sLTPs discovered on MESA COPD, and show that they are reproducible, able to encode standard emphysema subtypes, and associated with physiological symptoms.

Using Artificial Intelligence in Fungal Lung Disease: CPA CT Imaging as an Example.

This positioning paper aims to discuss current challenges and opportunities for artificial intelligence (AI) in fungal lung disease, with a focus on chronic pulmonary aspergillosis and some supporting proof-of-concept results using lung imaging. Given the high uncertainty in fungal infection diagnosis and analyzing treatment response, AI could potentially have an impactful role; however, developing imaging-based machine learning raises several specific challenges. We discuss recommendations to engage the medical community in essential first steps towards fungal infection AI with gathering dedicated imaging registries, linking with non-imaging data and harmonizing image-finding annotations.

Identification of variation in nutritional practice in neonatal units in England and association with clinical outcomes using agnostic machine learning.

We used agnostic, unsupervised machine learning to cluster a large clinical database of information on infants admitted to neonatal units in England. Our aim was to obtain insights into nutritional practice, an area of central importance in newborn care, utilising the UK National Neonatal Research Database (NNRD). We performed clustering on time-series data of daily nutritional intakes for very preterm infants born at a gestational age less than 32 weeks (n = 45,679) over a six-year period. This revealed 46 nutritional clusters heterogeneous in size, showing common interpretable clinical practices alongside rarer approaches. Nutritional clusters with similar admission profiles revealed associations between nutritional practice, geographical location and outcomes. We show how nutritional subgroups may be regarded as distinct interventions and tested for associations with measurable outcomes. We illustrate the potential for identifying relationships between nutritional practice and outcomes with two examples, discharge weight and bronchopulmonary dysplasia (BPD). We identify the well-known effect of formula milk on greater discharge weight as well as support for the plausible, but insufficiently evidenced view that human milk is protective against BPD. Our framework highlights the potential of agnostic machine learning approaches to deliver clinical practice insights and generate hypotheses using routine data.

Simultaneous left atrium anatomy and scar segmentations via deep learning in multiview information with attention.

Three-dimensional late gadolinium enhanced (LGE) cardiac MR (CMR) of left atrial scar in patients with atrial fibrillation (AF) has recently emerged as a promising technique to stratify patients, to guide ablation therapy and to predict treatment success. This requires a segmentation of the high intensity scar tissue and also a segmentation of the left atrium (LA) anatomy, the latter usually being derived from a separate bright-blood acquisition. Performing both segmentations automatically from a single 3D LGE CMR acquisition would eliminate the need for an additional acquisition and avoid subsequent registration issues. In this paper, we propose a joint segmentation method based on multiview two-task (MVTT) recursive attention model working directly on 3D LGE CMR images to segment the LA (and proximal pulmonary veins) and to delineate the scar on the same dataset. Using our MVTT recursive attention model, both the LA anatomy and scar can be segmented accurately (mean Dice score of 93% for the LA anatomy and 87% for the scar segmentations) and efficiently ( ∼ 0.27 s to simultaneously segment the LA anatomy and scars directly from the 3D LGE CMR dataset with 60-68 2D slices). Compared to conventional unsupervised learning and other state-of-the-art deep learning based methods, the proposed MVTT model achieved excellent results, leading to an automatic generation of a patient-specific anatomical model combined with scar segmentation for patients in AF.

Heterogeneity Measurement of Cardiac Tissues Leveraging Uncertainty Information from Image Segmentation.

Identifying arrhythmia substrates and quantifying their heterogeneity has great potential to provide critical guidance for radio frequency ablation. However, quantitative analysis of heterogeneity on cardiac optical coherence tomography (OCT) images is lacking. In this paper, we conduct the first study on quantifying cardiac tissue heterogeneity from human OCT images. Our proposed method applies a dropout-based Monte Carlo sampling technique to measure the model uncertainty. The heterogeneity information is extracted by decoupling the intra/inter-tissue heterogeneity and tissue boundary uncertainty from the uncertainty measurement. We empirically demonstrate that our model can highlight the subtle features from OCT images, and the heterogeneity information extracted is positively correlated with the tissue heterogeneity information from corresponding histology images.

Characterizing Alzheimer's Disease With Image and Genetic Biomarkers Using Supervised Topic Models.

Neuroimaging and genetic biomarkers have been widely studied from discriminative perspectives towards Alzheimer's disease (AD) classification, since neuroanatomical patterns and genetic variants are jointly critical indicators for AD diagnosis. Generative methods, designed to model common occurring patterns, could potentially advance the understanding of this disease, but have not been fully explored for AD characterization. Moreover, the introduction of a supervised component into the generative process can constrain the model for more discriminative characterization. In this study, we propose an original method based on supervised topic modeling to characterize AD from a generative perspective, yet maintaining discriminative power at differentiating disease populations. Our topic modeling jointly exploits discretized image features and categorical genetic features. Diagnostic information - cognitively normal (CN), mild cognitive impairment (MCI) and AD - is introduced as a supervision variable. Experimental results on the ADNI cohort demonstrate that our model, while achieving competitive discriminative performance, can discover topics revealing both well-known and novel neuroanatomical patterns including temporal, parietal and frontal regions; as well as associations between genetic factors and neuroanatomical patterns.

Vertebral rotation estimation from frontal X-rays using a quasi-automated pedicle detection method.

PURPOSE: Measurement of vertebral axial rotation (VAR) is relevant for the assessment of scoliosis. Stokes method allows estimating VAR in frontal X-rays from the relative position of the pedicles and the vertebral body. This method requires identifying these landmarks for each vertebral level, which is time-consuming. In this work, a quasi-automated method for pedicle detection and VAR estimation was proposed. METHOD: A total of 149 healthy and adolescent idiopathic scoliotic (AIS) subjects were included in this retrospective study. Their frontal X-rays were collected from multiple sites and manually annotated to identify the spinal midline and pedicle positions. Then, an automated pedicle detector was developed based on image analysis, machine learning and fast manual identification of a few landmarks. VARs were calculated using the Stokes method in a validation dataset of 11 healthy (age 6-33 years) and 46 AIS subjects (age 6-16 years, Cobb 10°-46°), both from detected pedicles and those manually annotated to compare them. Sensitivity of pedicle location to the manual inputs was quantified on 20 scoliotic subjects, using 10 perturbed versions of the manual inputs. RESULTS: Pedicles centers were localized with a precision of 84% and mean difference of 1.2 ± 1.2 mm, when comparing with manual identification. Comparison of VAR values between automated and manual pedicle localization yielded a signed difference of - 0.2 ± 3.4°. The uncertainty on pedicle location was smaller than 2 mm along each image axis. CONCLUSION: The proposed method allowed calculating VAR values in frontal radiographs with minimal user intervention and robust quasi-automated pedicle localization. These slides can be retrieved under Electronic Supplementary Material.

Association Between Long-term Exposure to Ambient Air Pollution and Change in Quantitatively Assessed Emphysema and Lung Function.

Importance: While air pollutants at historical levels have been associated with cardiovascular and respiratory diseases, it is not known whether exposure to contemporary air pollutant concentrations is associated with progression of emphysema. Objective: To assess the longitudinal association of ambient ozone (O3), fine particulate matter (PM2.5), oxides of nitrogen (NOx), and black carbon exposure with change in percent emphysema assessed via computed tomographic (CT) imaging and lung function. Design, Setting, and Participants: This cohort study included participants from the Multi-Ethnic Study of Atherosclerosis (MESA) Air and Lung Studies conducted in 6 metropolitan regions of the United States, which included 6814 adults aged 45 to 84 years recruited between July 2000 and August 2002, and an additional 257 participants recruited from February 2005 to May 2007, with follow-up through November 2018. Exposures: Residence-specific air pollutant concentrations (O3, PM2.5, NOx, and black carbon) were estimated by validated spatiotemporal models incorporating cohort-specific monitoring, determined from 1999 through the end of follow-up. Main Outcomes and Measures: Percent emphysema, defined as the percent of lung pixels less than -950 Hounsfield units, was assessed up to 5 times per participant via cardiac CT scan (2000-2007) and equivalent regions on lung CT scans (2010-2018). Spirometry was performed up to 3 times per participant (2004-2018). Results: Among 7071 study participants (mean [range] age at recruitment, 60 [45-84] years; 3330 [47.1%] were men), 5780 were assigned outdoor residential air pollution concentrations in the year of their baseline examination and during the follow-up period and had at least 1 follow-up CT scan, and 2772 had at least 1 follow-up spirometric assessment, over a median of 10 years. Median percent emphysema was 3% at baseline and increased a mean of 0.58 percentage points per 10 years. Mean ambient concentrations of PM2.5 and NOx, but not O3, decreased substantially during follow-up. Ambient concentrations of O3, PM2.5, NOx, and black carbon at study baseline were significantly associated with greater increases in percent emphysema per 10 years (O3: 0.13 per 3 parts per billion [95% CI, 0.03-0.24]; PM2.5: 0.11 per 2 µg/m3 [95% CI, 0.03-0.19]; NOx: 0.06 per 10 parts per billion [95% CI, 0.01-0.12]; black carbon: 0.10 per 0.2 µg/m3 [95% CI, 0.01-0.18]). Ambient O3 and NOx concentrations, but not PM2.5 concentrations, during follow-up were also significantly associated with greater increases in percent emphysema. Ambient O3 concentrations, but not other pollutants, at baseline and during follow-up were significantly associated with a greater decline in forced expiratory volume in 1 second per 10 years (baseline: 13.41 mL per 3 parts per billion [95% CI, 0.7-26.1]; follow-up: 18.15 mL per 3 parts per billion [95% CI, 1.59-34.71]). Conclusions and Relevance: In this cohort study conducted between 2000 and 2018 in 6 US metropolitan regions, long-term exposure to ambient air pollutants was significantly associated with increasing emphysema assessed quantitatively using CT imaging and lung function.