Abstract Background Sex-related differences have been consistently reported in the epidemiology of acute hypoxemic respiratory failure (AHRF) and COVID-19. However, whether computed tomography (CT)-derived measures of lung injury differ between sexes and contribute to outcome disparities remains unclear. Methods In this large multicenter retrospective cohort study, we analyzed 850 spontaneously breathing patients with COVID-19-related AHRF who underwent early chest CT at hospital admission. Quantitative CT analysis provided measures of lung density, volume, mass, and superimposed pressure (SP), a CT-derived estimate of gravitational stress. Sex-stratified analyses compared morphological, physiological, and outcome variables. Multivariable logistic regression models identified independent predictors of mortality. Results Among 850 patients (35% women), men exhibited larger lung volume (2.91 vs. 2.28 L, p < 0.001), greater lung mass (1.14 vs. 0.93 kg, p < 0.001), and higher SP (5.79 vs. 5.21 cmH₂O, p < 0.001) despite similar fractions of ground-glass opacities and consolidation. In the multivariable model, older age (OR 1.08, 95% CI 1.06–1.11; p < 0.001), lower PaO2/FiO2 (OR 0.99, 95% CI 0.98–0.99; p < 0.001), higher SOFA score (OR 2.67, 95% CI 1.43–4.98; p = 0.002 for SOFA ≥ 2), higher global SP (OR 1.18, 95% CI 1.05–1.34; p = 0.005), and male sex (OR 1.76, 95% CI 1.06–2.92; p = 0.028) were independently associated with an increased risk of mortality. In the mediation analysis, the effect of global SP on mortality does not appear to be mediated by male sex (coefficient 0.00). Conclusions Male patients with COVID-19-related AHRF exhibited higher global SP than females, reflecting greater gravitational lung load and mechanical disadvantage. Both global SP and male sex were independently associated with mortality, with no evidence of mediation of male sex on mortality. These finding suggest that, beyond anatomical and mechanical differences, biological and hormonal factors likely contribute to the increased disease severity observed in men.

Acute respiratory distress syndrome (ARDS) is a heterogeneous clinical syndrome rather than a single disease. Patients who meet the same diagnostic criteria may differ in lung morphology, mechanical properties, biological injury, and clinical course. Current classifications rely largely on the severity of hypoxemia and do not capture this variability, limiting prognostic stratification and individualized treatment. This heterogeneity has clinical consequences. Supportive interventions such as positive end-expiratory pressure (PEEP), prone positioning, and recruitment maneuvers are broadly applied, yet their effects vary substantially among patients. Increasing evidence indicates that these differences are partly explained by variation in lung structure, regional aeration, recruitability, and perfusion. Recent international guidelines have identified phenotyping as a priority in ARDS and have highlighted lung morphology as a relevant source of prognostic enrichment and treatment effect heterogeneity. Computed tomography (CT) provides regional, three-dimensional information on lung injury that is not accessible through bedside physiological measurements. It allows evaluation of aeration loss, lung density, lung weight, and perfusion abnormalities. CT has been used to describe key aspects of lung injury in ARDS and to identify imaging patterns associated with lung mechanics, gas exchange, and response to ventilatory settings. Quantitative and dual-energy CT, together with computational methods, allow a more detailed description of these patterns. This review examines the role of CT in characterizing heterogeneity in ARDS, summarizes qualitative, semi-quantitative, and quantitative approaches, and discusses their clinical relevance and limitations, as well as future directions.

RATIONAL:Emphysema is a hallmark of chronic obstructive pulmonary disease (COPD), yet its presumed coexistence with small airway disease remains debated. OBJECTIVE:To investigate the clinical significance of a novel CT-feature, "emptying emphysema," characterized by preserved expiratory density despite inspiratory attenuation consistent with emphysematous changes. METHODS:We analyzed data from 8,171 COPDGene participants with paired inspiratory-expiratory CT scans. Emptying emphysema was quantified using Parametric Response Mapping (%PRMEE) as the percentage of lung voxels with attenuation < -950 HU on inspiration and ≥ -856 HU on expiration. Multivariable models assessed associations between %PRMEE and clinical, functional, and radiographic outcomes. MEASUREMENTS AND MAIN RESULTS:Each one standard deviation (SD) higher in baseline %PRMEE was independently associated with less dyspnea (OR = 0.89; 95%CI: 0.94 to 0.95; P < .001) and impaired quality of life (OR = 0.87; 95%CI 0.83 to 0.93; P < .001). Each SD higher in %PRMEE was associated with a 11.2-meter increase in 6-minute walk distance (95%CI 8.7 to 13.6; P < .001). Higher %PRMEE was associated with lower FRC/TLC. Given the correlation between %PRMEE and traditional emphysema, we performed stratified analyses. Within each traditional emphysema quartile, higher %PRMEE was generally associated with higher FEV1% predicted and FEV1/FVC. Longitudinally, higher baseline %PRMEE was associated with attenuated lung density decline, and reduced mortality (HR = 0.90 per SD increase; 95%CI 0.86 to 0.95; P < .001). CONCLUSIONS:Emptying emphysema represents a CT-defined feature associated with preserved lung function and favorable clinical outcomes. Although it remains unclear whether this reflects a true pathological entity, these findings raise the possibility that emptying emphysema reflects alveolar-predominant changes occurring without significant airway disease, warranting further investigation.

A tool for automated pulmonary characterization using chest computed tomography (CT) would need to understand both healthy structures and abnormal findings, requiring the joint segmentation of healthy parenchyma, lesion involvement, and neighboring anatomical structures. Yet existing open-source tools focus on only part of this problem, or require setting up complex interactions between multiple heavyweight models. We introduce MEDPSeg, a lightweight method that leverages novel hierarchical polymorphic multitask learning strategies to learn from heterogeneous labels and deliver six segmentation masks: lung; lung lesion; ground-glass opacity (GGO), consolidation, airway tree, and pulmonary artery. All in a single forward pass. Its development took into consideration future distribution in lightweight and offline environments, allowing for execution in low resource infrastructure without needing internet access or the sharing of sensitive data. MEDPSeg ' s Python package (https://github.com/MICLab-Unicamp/medpseg) offers both a graphical user interface (GUI) and a command-line interface (CLI). We also host an online demo (https://medpseg.neuralmind.ai). Trained on 6000 CT volumes aggregated from COVID-19, Cancer, COPD, airway tree, pulmonary vessel and lung datasets, MEDPSeg attains better or comparable results to the state-of-the-art in multiple tasks. It outperforms or matches recent specialized methods in the segmentation of lung, lung opacity, airway, pulmonary vessel, GGO and consolidation. Prediction for a high resolution scan takes less than 1 min on a budget GPU, using less than 8 GB of VRAM to generate comprehensive quantification reports and multiple segmentation masks. The open-source tool has been validated by other internal and external independent studies. The MEDPSeg tool delivers comprehensive pulmonary assessment with commodity hardware, bridging the gap between research prototypes and practical understanding of thoracic CT imaging.

Tidal changes in esophageal pressure (ΔPes) are used as a surrogate for pleural pressure changes (ΔPpl) to assess chest wall mechanics. The Baydur ratio evaluates pressure transmission and guides catheter positioning. The effects of correcting ΔPes using the Baydur ratio on the accuracy of ΔPpl estimation and its dependence on ventilation mode, spontaneous inspiratory effort, and body position remain unclear. In 10 pigs, ΔPpl was measured using intrapleural balloon catheters, whereas Pes was recorded at three esophageal locations in supine and prone positions. Animals underwent controlled and assisted ventilation. Baydur ratios were derived during assisted ventilation and from external chest compressions during controlled ventilation. ΔPes before and after correction was compared with ΔPpl using mixed-effects models and Bland-Altman analysis. In addition, we quantified the proportion of values with (ΔPes - ΔPpl) ≤ 1 cmH2O. During assisted ventilation, ΔPes showed good agreement with posterior ΔPpl. Baydur correction improved scaling and association (slope: 0.76 vs. 0.50; r = 0.81 vs. 0.79, P < 0.01) and increased values within ±1 cmH2O from 29% to 45% when the Baydur ratio fell outside the accepted range. During controlled ventilation, ΔPes showed weaker association and wider limits of agreement, without improvement after correction. Similar patterns were observed in the prone position. ΔPes more accurately reflected posterior ΔPpl during assisted ventilation. Baydur correction improves scaling and association, particularly when the Baydur ratio falls outside the accepted range, but does not improve and may worsen agreement during controlled ventilation.NEW & NOTEWORTHY This study shows that the reliability of esophageal pressure as a surrogate of pleural pressure depends on ventilation mode. Using a minimally invasive approach for direct pleural pressure measurement with balloon catheters, we found that Baydur ratio correction improves ΔPes accuracy during assisted ventilation, particularly when the ratio falls outside the accepted range, but not during controlled ventilation.

The acute respiratory distress syndrome (ARDS) is characterized by pathologic and heterogeneous alterations in the mechanical properties of lung tissue. Although several techniques exist that allow for assessment of global lung mechanics in health and disease, few techniques allow for quantitative assessment of regional mechanics, which is important for understanding the impact of therapeutic interventions on local structure-function relationships. X-ray computed tomography (CT) is a widely available imaging modality for assessment of regional lung structure, given its high spatial resolution, as well as its ability to provide detailed information on regional anatomic and pathologic features. Quantitative computed tomography (qCT) has evolved into an important tool for assessment of regional and global mechanical changes associated with deranged structure-function relationships in many lung diseases, especially ARDS. The purpose of this study was to determine how specific structural and functional characteristics of the acutely injured lung may be altered, as assessed with various qCT imaging metrics. Such alterations may serve as a template for characterizing the severity of ARDS in patients. We evaluated and compared pressure-volume relationships, distensibility, aeration, tissue texture, and parenchymal deformation in healthy and injured lungs of anesthetized pigs, using volumetric CT images obtained during static breath holds from 30 to 0 cmH(2)O airway pressure. We demonstrate how qCT imaging provides unique insight into structure-function changes associated with acute lung injury, and how such techniques may enhance our understanding of regional and global parenchymal mechanics in patients with ARDS or other forms of lung injury. NEW & NOTEWORTHY We noted that quantitative computed tomographic (qCT) imaging has potential applications for assessing the severity of regional injury in the lung by providing detailed information on pressure-volume characteristics, distensibility, aeration, tissue texture, and other structure-function relationships. Such image processing techniques may also be useful for evaluating mechanical derangements associated with acute lung injury, thus enhancing our understanding of pulmonary pathophysiologies associated with regional structural and functional heterogeneity, such as ARDS.

In obesity, excess weight of the chest and abdomen (mass loading) decreases lung volume and can worsen acute hypoxemic respiratory failure (AHRF). We investigated whether positive end-expiratory pressure (PEEP) fully reverses the effects of mass loading on lung volume and respiratory mechanics in an AHRF swine model. Eighteen Yorkshire pigs were studied: six healthy, eight pre- and postinjury, and four postinjury only. We randomly tested three mass loading conditions: without mass loading, with abdominal loading (6 kg weight), and with combined abdominal and chest mass loading (12 kg total weight). We performed a recruitment maneuver in each condition, followed by a decremental PEEP trial, and identified the best-PEEP as that with the greatest respiratory system compliance (CRS). Airway pressure, esophageal pressure, and thoracic impedance by electrical impedance tomography) were continuously monitored. After lung injury, best-PEEP increased with loading. CRS at best-PEEP decreased from 20.6 ± 3.4 mL/cmH2O without loading to 17.7 ± 3.0 mL/cmH2O with abdominal loading [mean difference 2.9, 95% confidence interval (CI): 1.6-4.2] and to 14.2 ± 2.8 mL/cmH2O with abdominal and chest loading (mean difference 6.3, 95% CI: 5.0-7.7). Any amount of loading decreased end-expiratory lung volume assessed by computed tomography (CT) at best-PEEP and PEEP 3 cmH2O. Combined abdominal-chest loading decreased the vertical lung dimension on CT compared with unloaded and abdominal loading at both levels of PEEP. With mass loading, PEEP did not restore values of CRS and lung aeration to their unloaded values. In AHRF with mass loading, geometrical constraints may limit PEEP efficacy even when optimally titrated.NEW & NOTEWORTHY In a ventilated swine model, we isolated the mechanical effects of mass loading from those of lung injury. Despite optimization, positive end-expiratory pressure (PEEP) could not restore baseline pulmonary compliance or lung volumes in either healthy or injured lungs. Partitioned respiratory mechanics and imaging reveal that geometric constraints and load-induced airway closure, demonstrated here for the first time in injured swine, may limit the effectiveness of recruitment maneuvers and optimized PEEP in mass-loaded lungs.

Quantifying functional small airways disease (fSAD) requires additional expiratory computed tomography (CT) scan, limiting clinical applicability. Artificial intelligence (AI) could enable fSAD quantification from chest CT scan at total lung capacity (TLC) alone (fSADTLC). To evaluate an AI model for estimating fSADTLC, compare it with dual-volume parametric response mapping fSAD (fSADPRM), and assess its clinical associations and repeatability in chronic obstructive pulmonary disease (COPD). We analyzed 2513 participants from the SubPopulations and InteRmediate Outcome Measures in COPD Study (SPIROMICS). Using a randomly sampled subset (n = 1055), we developed a generative model to produce virtual expiratory CTs for estimating fSADTLC in the remaining 1458 SPIROMICS participants. We compared fSADTLC with dual volume, parametric response mapping fSADPRM. We investigated univariate and multivariable associations of fSADTLC with FEV1, FEV1/FVC, six-minute walk distance (6MWD), St. George's Respiratory Questionnaire (SGRQ), and FEV1 decline. The results were validated in a subset (n = 458) from COPDGene study. Multivariable models were adjusted for age, race, sex, BMI, baseline FEV1, smoking pack years, smoking status, and percent emphysema. Inspiratory fSADTLC showed a strong correlation with fSADPRM in both SPIROMICS (Pearson's R = 0.895) and COPDGene (R = 0.897) cohorts. Higher fSADTLC levels were significantly associated with lower lung function, including lower postbronchodilator FEV1 (L) and FEV1/FVC ratio, and poorer quality of life reflected by higher total SGRQ scores, independent of percent CT emphysema. In SPIROMICS, individuals with higher fSADTLC experienced an annual decline in FEV1 of 1.156 mL (relative decrease; 95% CI: 0.613, 1.699; P < 0.001) per year for every 1% increase in fSADTLC. The rate of decline in COPDGene was slightly lower at 0.866 mL / year (relative decrease; 95% CI: 0.345, 1.386; P < 0.001) for percent increase in fSADTLC. Inspiratory fSADTLC demonstrated greater consistency between repeated measurements with a higher intraclass correlation coefficient (ICC) of 0.99 (95% CI: 0.98, 0.99) compared to fSADPRM [ICC: 0.83 (95% CI: 0.76, 0.88)]. Small airways disease can be reliably assessed from a single inspiratory CT scan using generative AI, eliminating the need for an additional expiratory CT scan. fSAD estimation from inspiratory CT correlates strongly with fSADPRM, demonstrates a significant association with FEV1 decline, and offers greater repeatability.

Rationale: COPD is a heterogeneous inflammatory disease that affects the central and peripheral airways, vasculature, and overall lung parenchyma. These structural pathologies in the lung can be captured using CT textures obtained through the Adaptive Multiple Feature Method (AMFM). Among these, the CT density gradient (CTDG) texture is predominantly observed around the bronchovascular bundles, where it is speculated to capture underlying inflammatory processes. Our study investigates if varying degrees of CTDG texture can impact the local biomechanical properties of the bronchovascular bundles, particularly their distensibility. Methods: Using the AMFM pipeline, we extracted three non-overlapping textures from n=2,718 inspiratory scans in the SPIROMICS cohort: (1) CTDG; (2) bronchovascular bundle (BVB), capturing the airways and vasculature within the lung; and (3) normal texture. To quantify ventilation, we applied image registration on paired inspiratory and expiratory CT scans, calculating the Jacobian determinant of the deformation field from inhale to exhale to visualize local volume changes. To address outliers due to potential registration failures at the lung boundary, we applied a binary erosion technique to the Jacobian maps. After applying erosion, we computed the mean Jacobian determinant for the entire lung. Additionally, we overlaid the BVB and normal lung tissue texture maps onto the Jacobian map and computed mean Jacobian determinant within the defined regions of interest (ROIs). To assess differences in the BVB-associated mean Jacobian determinant across CTDG levels, while accounting for overall lung stiffness/compliance, we constructed three linear regression models with outcomes: overall mean Jacobian, BVB-associated mean Jacobian, and mean Jacobian of the normal regions. This approach ensured that the observed BVB distensibility was not merely a result of overall lung mechanics with varying CTDG. Adjustments were made for age, sex, race, BMI, current smoking status, smoking pack-years, and CT scanner type, as well as for % BVB texture and % normal texture in the corresponding mean Jacobian determinant models. Results: Our analysis revealed that participants with high CTDG had higher mean Jacobian determinant in the overall lung (β=0.110; P<0.001) and BVB regions (β=0.117; P<0.001). However, there were no significant differences in the mean Jacobian determinant within the normal texture regions across the three CTDG tertiles (Fig. 1). A high mean Jacobian (closer to 1) in the BVB regions of participants with high %CTDG suggests increased stiffness and reduced volume change in these regions. Conclusion: CTDG texture may be indicative of significant changes in mechanics of parenchymal regions surrounding the BVBs.

Accurate segmentation of the vocal tract from magnetic resonance imaging (MRI) data is essential for various voice and speech applications. Manual segmentation is time intensive and susceptible to errors. This study aimed to evaluate the efficacy of deep learning algorithms for automatic vocal tract segmentation from 3D MRI.

Rationale: Quantifying functional small airway disease (fSAD) requires additional expiratory computed tomography (CT) scans, limiting clinical applicability. Artificial intelligence (AI) could enable fSAD quantification from chest CT scans at total lung capacity (TLC) alone (fSADTLC). Objectives: To evaluate an AI model for estimating fSADTLC, compare it with dual-volume parametric response mapping fSAD (fSADPRM), and assess its clinical associations and repeatability in chronic obstructive pulmonary disease (COPD). Methods: We analyzed 2,513 participants from SPIROMICS (the Subpopulations and Intermediate Outcome Measures in COPD Study). Using a randomly sampled subset (n = 1,055), we developed a generative model to produce virtual expiratory CT scans for estimating fSADTLC in the remaining 1,458 SPIROMICS participants. We compared fSADTLC with dual-volume fSADPRM. We investigated univariate and multivariable associations of fSADTLC with FEV1, FEV1/FVC ratio, 6-minute-walk distance, St. George's Respiratory Questionnaire score, and FEV1 decline. The results were validated in a subset of patients from the COPDGene (Genetic Epidemiology of COPD) study (n = 458). Multivariable models were adjusted for age, race, sex, body mass index, baseline FEV1, smoking pack-years, smoking status, and percent emphysema. Measurements and Main Results: Inspiratory fSADTLC showed a strong correlation with fSADPRM in SPIROMICS (Pearson's R = 0.895) and COPDGene (R = 0.897) cohorts. Higher fSADTLC levels were significantly associated with lower lung function, including lower postbronchodilator FEV1 (in liters) and FEV1/FVC ratio, and poorer quality of life reflected by higher total St. George's Respiratory Questionnaire scores independent of percent CT emphysema. In SPIROMICS, individuals with higher fSADTLC experienced an annual decline in FEV1 of 1.156 ml (relative decrease; 95% confidence interval [CI], 0.613-1.699; P < 0.001) per year for every 1% increase in fSADTLC. The rate of decline in the COPDGene cohort was slightly lower at 0.866 ml/yr (relative decrease; 95% CI, 0.345-1.386; P < 0.001) per 1% increase in fSADTLC. Inspiratory fSADTLC demonstrated greater consistency between repeated measurements, with a higher intraclass correlation coefficient of 0.99 (95% CI, 0.98-0.99) compared with fSADPRM (0.83; 95% CI, 0.76-0.88). Conclusions: Small airway disease can be reliably assessed from a single inspiratory CT scan using generative AI, eliminating the need for an additional expiratory CT scan. fSAD estimation from inspiratory CT correlates strongly with fSADPRM, demonstrates a significant association with FEV1 decline, and offers greater repeatability.

Predicting radiologists' decisions when reading mammograms is a novel way to reduce the number of false positives and false negatives made at breast cancer screening. In this study, we aimed to enhance the accuracy of predicting radiologists' decisions in mammography by leveraging transfer learning. Our dataset comprised 120 digital mammogram cases, each annotated with radiologists' decisions categorized as true positive (TP), false positive (FP), or false negative (FN). We adopted the ResNet50 convolutional neural network (CNN) for our modeling approach, developing two different models. In the first model, ResNet50 was pretrained on the ImageNet dataset, with the initial layers frozen and the remaining layers fine-tuned to adapt to our mammography data. The second model was initialized with ImageNet weights obtained in the first model and further pretrained using the VinDr-Mammo dataset, an open-access large-scale Vietnamese dataset of full-field digital mammograms (FFDM) consisting of 5,000 four-view exams with breast-level assessments and extensive lesion-level annotations. Our transfer learning method improved the decision prediction accuracy by leveraging features from the VinDr-Mammo models.

Ultrashort echo time (UTE) magnetic resonance imaging (MRI) produces high-resolution structural images of the lungs without the ionizing radiation risks associated with computed tomography (CT) imaging. Lung segmentation in UTE is a necessary precursor to biomarker analysis, however, there are challenges associated with limited labeled training data, intensity inhomogeneity, noise, and image gradients. In this work, CT datasets are leveraged to improve the robustness of UTE lung segmentation, given limited labeled training data in the UTE domain. A novel joint training framework is proposed to simultaneously learn structural patterns important for multimodal lung segmentation. Additionally, a learnable downsample layer is proposed to enable training on full 3D CT and MRI images, while maintaining network complexity. Lastly, a false positive penalization loss is proposed to decrease erroneous segmentations associated with noise and gradients in UTE MRI. An ablation study evaluates each component's contribution, with the proposed approach achieving a Dice coefficient of 0.97 and a surface distance of 1.05 mm.

RATIONALE: Airway-to-lung ratio (AirLR), calculated as the mean of airway lumen diameters at standard anatomic locations divided by the cube-root of total lung volume, is associated with COPD risk regardless of smoking status, and we have previously shown an association between total-pulmonary-vascular-volume-to-lung-size relationship with AirLR. [PMCID: PMC11284327] Using dual energy computed tomography (DECT), we recently developed a deep learning-based algorithm for pulmonary arterial segmentation to compute pulmonary-arterial-to-lung ratio (ArtLR) which correlated significantly with AirLR and markers COPD. Here we automate image processing in a larger cohort to estimate ArtLR, introduce an alternative ArtLR standardization and correlate it to COPD-related measures of lung structure and function. METHODS: Using a SPIROMICS sub-cohort (110 participants), imaged via contrast enhanced DECT at functional residual capacity (FRC), an automatic deep learning pipeline segmented the arteries from the pulmonary vascular tree. Another pipeline automatically extracted the centerlines and calculated average arterial segment diameters. A paired non-contrast total lung capacity (TLC) scan was registered to the DECT FRC scan to transfer airway segment labels from the TLC to FRC domain. AirLR was calculated as the mean of airway lumen diameters at standard anatomic locations (trachea-to-subsegments) divided by cube root of lung volume [TLC or FRC]. A simple Long Short-Term Memory (LSTM) network was used to find corresponding anatomic arterial segments. Associations between ArtLR and %Emphysema, AirLR, pre- and post-bronchodilator FEV1/FVC, and a texture-based (AMFM) measure of %broncho-vascular bundles was assessed using linear regression to adjust for age, sex and BMI. RESULTS: In adjusted analyses, a 1-SD decrement in ArtLR-TLC was associated with 4.198 units increase in %Emphysema-910 (95%CI: 1.360-7.037; p = 0.0041), and 0.8198 units decrease in %Bronchovascular (95%CI: 0.5037-1.136; p < 0.0001). A 1-SD increment in ArtLR-TLC was associated with 0.2515 SD increase in AirLR-Outer (95%CI: 0.04947SD-0.4536SD; p = 0.0152), and 0.02083 units increase in PreBronch-FEV1FVC (95%CI: 0.001814-0.03984; p = 0.0321). Sex and BMI show significant associations with ArtLR-TLC, where female is associated with 1.068 SD decrease in ArtLR, and a unit increase in BMI is associated with 0.05788 SD increase in ArtLR (both p-values < 0.0001), and age was not association with ArtLR. CONCLUSIONS: An automated pipeline for pulmonary arterial tree segmentation and standardization from contrast enhanced DECT FRC scans demonstrates a significant relationship between ArtLR and AirLR as well as between ArtLR and %emphysema, and FEV1/FVC. A standardized method of arterial tree size assessment provides for expanded exploration of vascular vs airway disease etiologies.

The field of supervised automated medical imaging segmentation suffers from relatively small datasets with ground truth labels. This is especially true for challenging segmentation problems that target structures with low contrast and ambiguous boundaries, such as ground glass opacities and consolidation in chest computed tomography images. In this work, we make available the first public dataset of ground glass opacity and consolidation in the lungs of Long COVID patients. The Long COVID Iowa-UNICAMP dataset (LongCIU) was built by three independent expert annotators, blindly segmenting the same 90 selected axial slices manually, without using any automated initialization. The public dataset includes the final consensus segmentation in addition to the individual segmentation from each annotator (360 slices total). This dataset is a valuable resource for training and validating new automated segmentation methods and for studying interrater uncertainty in the segmentation of lung opacities in computed tomography.

The respiratory system depends on complex biomechanical processes to enable gas exchange. The mechanical properties of the lung parenchyma, airways, vasculature, and surrounding structures play an essential role in overall ventilation efficacy. These complex biomechanical processes, however, are significantly altered in chronic obstructive pulmonary disease (COPD) due to emphysematous destruction of the lung parenchyma, chronic airway inflammation, and small airway obstruction. Recent advancements in computed tomography (CT) and magnetic resonance imaging (MRI) acquisition techniques, combined with advanced image post-processing algorithms and deep neural networks, have enabled comprehensive quantitative assessment of lung structure, tissue deformation, and lung function at the voxel level. These methods have led to better phenotyping, therapeutic strategies, and refined our understanding of pathological processes that compromise pulmonary function in COPD. In this review, we discuss recent developments in imaging and image processing methods for studying pulmonary biomechanics with a specific focus on clinical applications for COPD, including the assessment of regional ventilation, planning of endobronchial valve treatment, prediction of disease onset and progression, sizing of lungs for transplantation, and guiding mechanical ventilation. These advanced image-based biomechanical measurements, when combined with clinical expertise, play a critical role in disease management and personalized therapeutic interventions for patients with COPD.

Rationale E-cigarettes (e-cigs) are the most used tobacco product among adolescents and young adults despite uncertainty regarding long-term respiratory risks. Emerging evidence suggests that e-cig use may be associated with the development of chronic lung diseases such as chronic bronchitis, emphysema, and COPD. We aimed to test associations of e-cigarette use with quantitative CT measures of lung parenchymal and vascular structure in healthy young adults. Methods The VapeScan Study recruited participants aged 18 to 50 from New York City. Exclusion criteria included pregnancy, clinical cardiovascular disease, and physician diagnoses of bronchiectasis, emphysema, or COPD. Participants were recruited into one of four groups: Control participants without a history of e-cig or cigarette (cig) use, dual e-cig/cig users, current e-cig users with former cig use, and exclusive e-cig users. Participants underwent full-lung low-dose CT scans at total lung capacity (TLC) and, in a subset, functional residual capacity (FRC). Percentage of low attenuation areas (%LAA) was defined by the percentage of voxels < -910 HU. Percentage of functional small airways disease (%fSAD) was determined as the percentage of lung voxels >-950 HU at TLC < -856 HU at FRC. Total pulmonary vascular volume (TPVV) was defined as the volume of detectable pulmonary arteries and veins. Differences across groups were assessed using ANOVA, adjusted for age, gender, height, and weight. Secondary analyses also adjusted for cannabis use. Results Of 254 participants with lung CT data (mean age 28±7.6, mean BMI 26±5, 48% male, 36% non-Hispanic White, 75% with FRC scan), there were 85 (33%) controls, 66 (26%) dual users, 45 (18%) e-cig users with former cig use, and 58 (23%) exclusive e-cig users; 39% were current and 30% were former cannabis users. In fully-adjusted models, compared to controls, current e-cig users—regardless of active, former, or no cig use history—showed greater %LAA (p=0.04), %fSAD (p=0.003), and TPVV (p=0.03). After exclusion of participants with current or former cig use, compared to controls, exclusive e-cig users had greater adjusted %LAA (21.5% vs. 17.2%, p=0.02), higher %fSAD (24.9% vs. 17.8%, p=0.04), and greater TPVV (118.8 mL vs. 110.7 mL, p=0.02). Estimates were similar after further adjustment for cannabis use. Conclusions Current e-cig use (versus non-use) was associated with lower lung density, evidence of small airway disease, and increased vascular perfusion on non-contrast CT in healthy young adults. This may be representative of mild emphysema, small airway inflammation, and changes in pulmonary vascular resistance respectively.

Rationale: Chronic obstructive pulmonary disease (COPD) due to tobacco smoking commonly presents when extensive lung damage has occurred. Objectives: We hypothesized that structural change would be detected early in the natural history of COPD and would relate to loss of lung function with time. Methods: We recruited 431 current smokers (median age, 39 yr; 16 pack-years smoked) and recorded symptoms using the COPD Assessment Test (CAT), spirometry, and quantitative thoracic computed tomography (QCT) scans at study entry. These scan results were compared with those from 67 never-smoking control subjects. Three hundred sixty-eight participants were followed every six months with measurement of postbronchodilator spirometry for a median of 32 months. The rate of FEV1 decline, adjusted for current smoking status, age, and sex, was related to the initial QCT appearances and symptoms, measured using the CAT. Measurements and Main Results: There were no material differences in demography or subjective CT appearances between the young smokers and control subjects, but 55.7% of the former had CAT scores greater than 10, and 24.2% reported chronic bronchitis. QCT assessments of disease probability-defined functional small airway disease, ground-glass opacification, bronchovascular prominence, and ratio of small blood vessel volume to total pulmonary vessel volume were increased compared with control subjects and were all associated with a faster FEV1 decline, as was a higher CAT score. Conclusions: Radiological abnormalities on CT are already established in young smokers with normal lung function and are associated with FEV1 loss independently of the impact of symptoms. Structural abnormalities are present early in the natural history of COPD and are markers of disease progression. Clinical trial registered with www.clinicaltrials.gov (NCT03480347).

Rationale: Rates of emphysema progression vary in chronic obstructive pulmonary disease (COPD), and the relationships with vascular and airway pathophysiology remain unclear. Objectives: We sought to determine if indices of peripheral (segmental and beyond) pulmonary arterial dilation measured on computed tomography (CT) are associated with a 1-year index of emphysema (EI; percentage of voxels <-950 Hounsfield units) progression. Methods: Five hundred ninety-nine former and never-smokers (Global Initiative for Chronic Obstructive Lung Disease stages 0-3) were evaluated from the SPIROMICS (Subpopulations and Intermediate Outcome Measures in COPD Study) cohort: rapid emphysema progressors (RPs; n = 188, 1-year ΔEI > 1%), nonprogressors (n = 301, 1-year ΔEI ± 0.5%), and never-smokers (n = 110). Segmental pulmonary arterial cross-sectional areas were standardized to associated airway luminal areas (segmental pulmonary artery-to-airway ratio [PAARseg]). Full-inspiratory CT scan-derived total (arteries and veins) pulmonary vascular volume (TPVV) was compared with small vessel volume (radius smaller than 0.75 mm). Ratios of airway to lung volume (an index of dysanapsis and COPD risk) were compared with ratios of TPVV to lung volume. Results: Compared with nonprogressors, RPs exhibited significantly larger PAARseg (0.73 ± 0.29 vs. 0.67 ± 0.23; P = 0.001), lower ratios of TPVV to lung volume (3.21 ± 0.42% vs. 3.48 ± 0.38%; P = 5.0 × 10-12), lower ratios of airway to lung volume (0.031 ± 0.003 vs. 0.034 ± 0.004; P = 6.1 × 10-13), and larger ratios of small vessel volume to TPVV (37.91 ± 4.26% vs. 35.53 ± 4.89%; P = 1.9 × 10-7). In adjusted analyses, an increment of 1 standard deviation in PAARseg was associated with a 98.4% higher rate of severe exacerbations (95% confidence interval, 29-206%; P = 0.002) and 79.3% higher odds of being in the RP group (95% confidence interval, 24-157%; P = 0.001). At 2-year follow-up, the CT-defined RP group demonstrated a significant decline in postbronchodilator percentage predicted forced expiratory volume in 1 second. Conclusions: Rapid one-year progression of emphysema was associated with indices indicative of higher peripheral pulmonary vascular resistance and a possible role played by pulmonary vascular-airway dysanapsis.