LungViT: Ensembling Cascade of Texture Sensitive Hierarchical Vision Transformers for Cross-Volume Chest CT Image-to-Image Translation.

Chest computed tomography (CT) at inspiration is often complemented by an expiratory CT to identify peripheral airways disease. Additionally, co-registered inspiratory-expiratory volumes can be used to derive various markers of lung function. Expiratory CT scans, however, may not be acquired due to dose or scan time considerations or may be inadequate due to motion or insufficient exhale; leading to a missed opportunity to evaluate underlying small airways disease. Here, we propose LungViT - a generative adversarial learning approach using hierarchical vision transformers for translating inspiratory CT intensities to corresponding expiratory CT intensities. LungViT addresses several limitations of the traditional generative models including slicewise discontinuities, limited size of generated volumes, and their inability to model texture transfer at volumetric level. We propose a shifted-window hierarchical vision transformer architecture with squeeze-and-excitation decoder blocks for modeling dependencies between features. We also propose a multiview texture similarity distance metric for texture and style transfer in 3D. To incorporate global information into the training process and refine the output of our model, we use ensemble cascading. LungViT is able to generate large 3D volumes of size 320 × 320 × 320. We train and validate our model using a diverse cohort of 1500 subjects with varying disease severity. To assess model generalizability beyond the development set biases, we evaluate our model on an out-of-distribution external validation set of 200 subjects. Clinical validation on internal and external testing sets shows that synthetic volumes could be reliably adopted for deriving clinical endpoints of chronic obstructive pulmonary disease.

A Phase 2 Randomized Clinical Trial Evaluating 4-Dimensional Computed Tomography Ventilation-Based Functional Lung Avoidance Radiation Therapy for Non-Small Cell Lung Cancer.

PURPOSE: To determine whether 4-dimensional computed tomography (4DCT) ventilation-based functional lung avoidance radiation therapy preserves pulmonary function compared with standard radiation therapy for non-small cell lung cancer (NSCLC). METHODS AND MATERIALS: This single center, randomized, phase 2 trial enrolled patients with NSCLC receiving curative intent radiation therapy with either stereotactic body radiation therapy or conventionally fractionated radiation therapy between 2016 and 2022. Patients were randomized 1:1 to standard of care radiation therapy or functional lung avoidance radiation therapy. The primary endpoint was the change in Jacobian-based ventilation as measured on 4DCT from baseline to 3 months postradiation. Secondary endpoints included changes in volume of high- and low-ventilating lung, pulmonary toxicity, and changes in pulmonary function tests (PFTs). RESULTS: A total of 122 patients were randomized and 116 were available for analysis. Median follow up was 29.9 months. Functional avoidance plans significantly (P < .05) reduced dose to high-functioning lung without compromising target coverage or organs at risk constraints. When analyzing all patients, there was no difference in the amount of lung showing a reduction in ventilation from baseline to 3 months between the 2 arms (1.91% vs 1.87%; P = .90). Overall grade ≥2 and grade ≥3 pulmonary toxicities for all patients were 24.1% and 8.6%, respectively. There was no significant difference in pulmonary toxicity or changes in PFTs between the 2 study arms. In the conventionally fractionated cohort, there was a lower rate of grade ≥2 pneumonitis (8.2% vs 32.3%; P = .049) and less of a decline in change in forced expiratory volume in 1 second (-3 vs -5; P = .042) and forced vital capacity (1.5 vs -6; P = .005) at 3 months, favoring the functional avoidance arm. CONCLUSIONS: There was no difference in posttreatment ventilation as measured by 4DCT between the arms. In the cohort of patients treated with conventionally fractionated radiation therapy with functional lung avoidance, there was reduced pulmonary toxicity, and less decline in PFTs suggesting a clinical benefit in patients with locally advanced NSCLC.

Longitudinal Follow-Up of Participants With Tobacco Exposure and Preserved Spirometry.

Importance: People who smoked cigarettes may experience respiratory symptoms without spirometric airflow obstruction. These individuals are typically excluded from chronic obstructive pulmonary disease (COPD) trials and lack evidence-based therapies. Objective: To define the natural history of persons with tobacco exposure and preserved spirometry (TEPS) and symptoms (symptomatic TEPS). Design, Setting, and Participants: SPIROMICS II was an extension of SPIROMICS I, a multicenter study of persons aged 40 to 80 years who smoked cigarettes (>20 pack-years) with or without COPD and controls without tobacco exposure or airflow obstruction. Participants were enrolled in SPIROMICS I and II from November 10, 2010, through July 31, 2015, and followed up through July 31, 2021. Exposures: Participants in SPIROMICS I underwent spirometry, 6-minute walk distance testing, assessment of respiratory symptoms, and computed tomography of the chest at yearly visits for 3 to 4 years. Participants in SPIROMICS II had 1 additional in-person visit 5 to 7 years after enrollment in SPIROMICS I. Respiratory symptoms were assessed with the COPD Assessment Test (range, 0 to 40; higher scores indicate more severe symptoms). Participants with symptomatic TEPS had normal spirometry (postbronchodilator ratio of forced expiratory volume in the first second [FEV1] to forced vital capacity >0.70) and COPD Assessment Test scores of 10 or greater. Participants with asymptomatic TEPS had normal spirometry and COPD Assessment Test scores of less than 10. Patient-reported respiratory symptoms and exacerbations were assessed every 4 months via phone calls. Main Outcomes and Measures: The primary outcome was assessment for accelerated decline in lung function (FEV1) in participants with symptomatic TEPS vs asymptomatic TEPS. Secondary outcomes included development of COPD defined by spirometry, respiratory symptoms, rates of respiratory exacerbations, and progression of computed tomographic-defined airway wall thickening or emphysema. Results: Of 1397 study participants, 226 had symptomatic TEPS (mean age, 60.1 [SD, 9.8] years; 134 were women [59%]) and 269 had asymptomatic TEPS (mean age, 63.1 [SD, 9.1] years; 134 were women [50%]). At a median follow-up of 5.76 years, the decline in FEV1 was -31.3 mL/y for participants with symptomatic TEPS vs -38.8 mL/y for those with asymptomatic TEPS (between-group difference, -7.5 mL/y [95% CI, -16.6 to 1.6 mL/y]). The cumulative incidence of COPD was 33.0% among participants with symptomatic TEPS vs 31.6% among those with asymptomatic TEPS (hazard ratio, 1.05 [95% CI, 0.76 to 1.46]). Participants with symptomatic TEPS had significantly more respiratory exacerbations than those with asymptomatic TEPS (0.23 vs 0.08 exacerbations per person-year, respectively; rate ratio, 2.38 [95% CI, 1.71 to 3.31], P < .001). Conclusions and Relevance: Participants with symptomatic TEPS did not have accelerated rates of decline in FEV1 or increased incidence of COPD vs those with asymptomatic TEPS, but participants with symptomatic TEPS did experience significantly more respiratory exacerbations over a median follow-up of 5.8 years.

Attention U-net for automated pulmonary fissure integrity analysis in lung computed tomography images.

Computed Tomography (CT) imaging is routinely used for imaging of the lungs. Deep learning can effectively automate complex and laborious tasks in medical imaging. In this work, a deep learning technique is utilized to assess lobar fissure completeness (also known as fissure integrity) from pulmonary CT images. The human lungs are divided into five separate lobes, divided by the lobar fissures. Fissure integrity assessment is important to endobronchial valve treatment screening. Fissure integrity is known to be a biomarker of collateral ventilation between lobes impacting the efficacy of valves designed to block airflow to diseased lung regions. Fissure integrity is also likely to impact lobar sliding which has recently been shown to affect lung biomechanics. Further widescale study of fissure integrity's impact on disease susceptibility and progression requires rapid, reproducible, and noninvasive fissure integrity assessment. In this paper we describe IntegrityNet, an attention U-Net based automatic fissure integrity analysis tool. IntegrityNet is able to predict fissure integrity with an accuracy of 95.8%, 96.1%, and 89.8% for left oblique, right oblique, and right horizontal fissures, compared to manual analysis on a dataset of 82 subjects. We also show that our method is robust to COPD severity and reproducible across subject scans acquired at different time points.

Role of lung lobar sliding on parenchymal distortion during breathing.

Sliding between lung lobes along lobar fissures is a poorly understood aspect of lung mechanics. The objective of this study was to test the hypothesis that lobar sliding helps reduce distortion in the lung parenchyma during breathing. Finite element models of left lungs with geometries and boundary conditions derived from medical images of human subjects were developed. Effect of lobar sliding was studied by comparing nonlinear finite elastic contact mechanics simulations that allowed and disallowed lobar sliding. Lung parenchymal distortion during simulated breath-holds and tidal breathing was quantified with the model's spatial mean anisotropic deformation index (ADI), a measure of directional preference in volume change that varies spatially in the lung. Models that allowed lobar sliding had significantly lower mean ADI (i.e., lesser parenchymal distortion) than models that disallowed lobar sliding under simulations of both tidal breathing (5.3% median difference, P = 0.008, n = 8) and lung deformation between breath-holds at total lung capacity and functional residual capacity (3.2% median difference, P = 0.03, n = 6). This effect was most pronounced in the lower lobe where lobar sliding reduced parenchymal distortion with statistical significance, but not in the upper lobe. In addition, more lobar sliding was correlated with greater reduction in distortion between sliding and nonsliding models in our study cohorts (Pearson's correlation coefficient of 0.95 for tidal breathing, 0.87 for breath-holds, and 0.91 for the combined dataset). These findings are consistent with the hypothesis that lung lobar sliding reduces parenchymal distortion during breathing.NEW & NOTEWORTHY The role of lobar sliding in lung mechanics is poorly understood. Delineating this role could help explain how breathing is affected by anatomical differences between subjects such as incomplete and missing lobar fissures. We used computational contact mechanics models of lungs from human subjects to delineate the effect of lobar sliding by comparing simulations that allowed and disallowed sliding. We found evidence consistent with the hypothesis that lung lobar sliding reduces parenchymal distortion during breathing.

Validation of CT-based ventilation and perfusion biomarkers with histopathology confirms radiation-induced pulmonary changes in a porcine model.

Imaging biomarkers can assess disease progression or prognoses and are valuable tools to help guide interventions. Particularly in lung imaging, biomarkers present an opportunity to extract regional information that is more robust to the patient's condition prior to intervention than current gold standard pulmonary function tests (PFTs). This regional aspect has particular use in functional avoidance radiation therapy (RT) in which treatment planning is optimized to avoid regions of high function with the goal of sparing functional lung and improving patient quality of life post-RT. To execute functional avoidance, detailed dose-response models need to be developed to identify regions which should be protected. Previous studies have begun to do this, but for these models to be clinically translated, they need to be validated. This work validates two metrics that encompass the main components of lung function (ventilation and perfusion) through post-mortem histopathology performed in a novel porcine model. With these methods validated, we can use them to study the nuanced radiation-induced changes in lung function and develop more advanced models.

Radiomics for Improved Detection of Chronic Obstructive Pulmonary Disease in Low-Dose and Standard-Dose Chest CT Scans.

Background Approximately half of adults with chronic obstructive pulmonary disease (COPD) remain undiagnosed. Chest CT scans are frequently acquired in clinical practice and present an opportunity to detect COPD. Purpose To assess the performance of radiomics features in COPD diagnosis using standard-dose and low-dose CT models. Materials and Methods This secondary analysis included participants enrolled in the Genetic Epidemiology of COPD, or COPDGene, study at baseline (visit 1) and 10 years after baseline (visit 3). COPD was defined by a forced expiratory volume in the 1st second of expiration to forced vital capacity ratio less than 0.70 at spirometry. The performance of demographics, CT emphysema percentage, radiomics features, and a combined feature set derived from inspiratory CT alone was evaluated. CatBoost (Yandex), a gradient boosting algorithm, was used to perform two classification experiments to detect COPD; the two models were trained and tested on standard-dose CT data from visit 1 (model I) and low-dose CT data from visit 3 (model II). Classification performance of the models was evaluated using area under the receiver operating characteristic curve (AUC) and precision-recall curve analysis. Results A total of 8878 participants (mean age, 57 years ± 9 [SD]; 4180 female, 4698 male) were evaluated. Radiomics features in model I achieved an AUC of 0.90 (95% CI: 0.88, 0.91) in the standard-dose CT test cohort versus demographics (AUC, 0.73; 95% CI: 0.71, 0.76; P < .001), emphysema percentage (AUC, 0.82; 95% CI 0.80, 0.84; P < .001), and combined features (AUC, 0.90; 95% CI: 0.89, 0.92; P = .16). Model II, trained on low-dose CT scans, achieved an AUC of 0.87 (95% CI: 0.83, 0.91) on the 20% held-out test set for radiomics features compared with demographics (AUC, 0.70; 95% CI: 0.64, 0.75; P = .001), emphysema percentage (AUC, 0.74; 95% CI: 0.69, 0.79; P = .002), and combined features (AUC, 0.88; 95% CI: 0.85, 0.92; P = .32). Density and texture features were the majority of the top 10 features in the standard-dose model, whereas shape features of lungs and airways were significant contributors in the low-dose CT model. Conclusion A combination of features representing parenchymal texture and lung and airway shape on inspiratory CT scans can be used to accurately detect COPD. ClinicalTrials.gov registration no. NCT00608764 © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Vliegenthart in this issue.

Quantifying robustness of CT-ventilation biomarkers to image noise.

Purpose: To quantify the impact of image noise on CT-based lung ventilation biomarkers calculated using Jacobian determinant techniques. Methods: Five mechanically ventilated swine were imaged on a multi-row CT scanner with acquisition parameters of 120 kVp and 0.6 mm slice thickness in static and 4-dimensional CT (4DCT) modes with respective pitches of 1 and 0.09. A range of tube current time product (mAs) values were used to vary image dose. On two dates, subjects received two 4DCTs: one with 10 mAs/rotation (low-dose, high-noise) and one with CT simulation standard of care 100 mAs/rotation (high-dose, low-noise). Additionally, 10 intermediate noise level breath-hold (BHCT) scans were acquired with inspiratory and expiratory lung volumes. Images were reconstructed with and without iterative reconstruction (IR) using 1 mm slice thickness. The Jacobian determinant of an estimated transformation from a B-spline deformable image registration was used to create CT-ventilation biomarkers estimating lung tissue expansion. 24 CT-ventilation maps were generated per subject per scan date: four 4DCT ventilation maps (two noise levels each with and without IR) and 20 BHCT ventilation maps (10 noise levels each with and without IR). Biomarkers derived from reduced dose scans were registered to the reference full dose scan for comparison. Evaluation metrics were gamma pass rate (Γ) with 2 mm distance-to-agreement and 6% intensity criterion, voxel-wise Spearman correlation (ρ) and Jacobian ratio coefficient of variation (CoV JR ). Results: Comparing biomarkers derived from low (CTDI vol = 6.07 mGy) and high (CTDI vol = 60.7 mGy) dose 4DCT scans, mean Γ, ρ and CoV JR values were 93% ± 3%, 0.88 ± 0.03 and 0.04 ± 0.009, respectively. With IR applied, those values were 93% ± 4%, 0.90 ± 0.04 and 0.03 ± 0.003. Similarly, comparisons between BHCT-based biomarkers with variable dose (CTDI vol = 1.35-7.95 mGy) had mean Γ, ρ and CoV JR of 93% ± 4%, 0.97 ± 0.02 and 0.03 ± 0.006 without IR and 93% ± 4%, 0.97 ± 0.03 and 0.03 ± 0.007 with IR. Applying IR did not significantly change any metrics (p > 0.05). Discussion: This work demonstrated that CT-ventilation, calculated using the Jacobian determinant of an estimated transformation from a B-spline deformable image registration, is invariant to Hounsfield Unit (HU) variation caused by image noise. This advantageous finding may be leveraged clinically with potential applications including dose reduction and/or acquiring repeated low-dose acquisitions for improved ventilation characterization.

Robust quantification of CT-ventilation biomarker techniques and repeatability in a porcine model.

BACKGROUND: Biomarkers estimating local lung ventilation have been derived from computed tomography (CT) imaging using various image acquisition and post-processing techniques. CT-ventilation biomarkers have potential clinical use in functional avoidance radiation therapy (RT), in which RT treatment plans are optimized to reduce dose delivered to highly ventilated lung. Widespread clinical implementation of CT-ventilation biomarkers necessitates understanding of biomarker repeatability. Performing imaging within a highly controlled experimental design enables quantification of error associated with remaining variables. PURPOSE: To characterize CT-ventilation biomarker repeatability and dependence on image acquisition and post-processing methodology in anesthetized and mechanically ventilated pigs. METHODS: Five mechanically ventilated Wisconsin Miniature Swine (WMS) received multiple consecutive four-dimensional CT (4DCT) and maximum inhale and exhale breath-hold CT (BH-CT) scans on five dates to generate CT-ventilation biomarkers. Breathing maneuvers were controlled with an average tidal volume difference <200 cc. As surrogates for ventilation, multiple local expansion ratios (LERs) were calculated from the acquired CT scans using Jacobian-based post-processing techniques. L E R 2 $LER_2$ measured local expansion between an image pair using either inhale and exhale BH-CT images or two 4DCT breathing phase images. L E R N $LER_N$ measured the maximum local expansion across the 4DCT breathing phase images. Breathing maneuver consistency, intra- and interday biomarker repeatability, image acquisition and post-processing technique dependence were quantitatively analyzed. RESULTS: Biomarkers showed strong agreement with voxel-wise Spearman correlation ρ > 0.9 $\rho > 0.9$ for intraday repeatability and ρ > 0.8 $\rho > 0.8$ for all other comparisons, including between image acquisition techniques. Intra- and interday repeatability were significantly different (p < 0.01). LER2 and LERN post-processing did not significantly affect intraday repeatability. CONCLUSIONS: 4DCT and BH-CT ventilation biomarkers derived from consecutive scans show strong agreement in controlled experiments with nonhuman subjects.

Direct estimation of regional lung volume change from paired and single CT images using residual regression neural network.

BACKGROUND: Chest computed tomography (CT) enables characterization of pulmonary diseases by producing high-resolution and high-contrast images of the intricate lung structures. Deformable image registration is used to align chest CT scans at different lung volumes, yielding estimates of local tissue expansion and contraction. PURPOSE: We investigated the utility of deep generative models for directly predicting local tissue volume change from lung CT images, bypassing computationally expensive iterative image registration and providing a method that can be utilized in scenarios where either one or two CT scans are available. METHODS: A residual regression convolutional neural network, called Reg3DNet+, is proposed for directly regressing high-resolution images of local tissue volume change (i.e., Jacobian) from CT images. Image registration was performed between lung volumes at total lung capacity (TLC) and functional residual capacity (FRC) using a tissue mass- and structure-preserving registration algorithm. The Jacobian image was calculated from the registration-derived displacement field and used as the ground truth for local tissue volume change. Four separate Reg3DNet+ models were trained to predict Jacobian images using a multifactorial study design to compare the effects of network input (i.e., single image vs. paired images) and output space (i.e., FRC vs. TLC). The models were trained and evaluated on image datasets from the COPDGene study. Models were evaluated against the registration-derived Jacobian images using local, regional, and global evaluation metrics. RESULTS: Statistical analysis revealed that both factors - network input and output space - were significant determinants for change in evaluation metrics. Paired-input models performed better than single-input models, and model performance was better in the output space of FRC rather than TLC. Mean structural similarity index for paired-input models was 0.959 and 0.956 for FRC and TLC output spaces, respectively, and for single-input models was 0.951 and 0.937. Global evaluation metrics demonstrated correlation between registration-derived Jacobian mean and predicted Jacobian mean: coefficient of determination (r2 ) for paired-input models was 0.974 and 0.938 for FRC and TLC output spaces, respectively, and for single-input models was 0.598 and 0.346. After correcting for effort, registration-derived lobar volume change was strongly correlated with the predicted lobar volume change: for paired-input models r2 was 0.899 for both FRC and TLC output spaces, and for single-input models r2 was 0.803 and 0.862, respectively. CONCLUSIONS: Convolutional neural networks can be used to directly predict local tissue mechanics, eliminating the need for computationally expensive image registration. Networks that use paired CT images acquired at TLC and FRC allow for more accurate prediction of local tissue expansion compared to networks that use a single image. Networks that only require a single input image still show promising results, particularly after correcting for effort, and allow for local tissue expansion estimation in cases where multiple CT scans are not available. For single-input networks, the FRC image is more predictive of local tissue volume change compared to the TLC image.

Metrics of dose to highly ventilated lung are predictive of radiation-induced pneumonitis in lung cancer patients.

PURPOSE: To identify metrics of radiation dose delivered to highly ventilated lung that are predictive of radiation-induced pneumonitis. METHODS AND MATERIALS: A cohort of 90 patients with locally advanced non-small cell lung cancer treated with standard fractionated radiation therapy (RT) (60-66 Gy in 30-33 fractions) were evaluated. Regional lung ventilation was determined from pre-RT 4-dimensional computed tomography (4DCT) using the Jacobian determinant of a B-spline deformable image registration to estimate lung tissue expansion during respiration. Multiple voxel-wise population- and individual-based thresholds for defining high functioning lung were considered. Mean dose and volumes receiving dose ≥ 5-60 Gy were analyzed for both total lung-ITV (MLD,V5-V60) and highly ventilated functional lung-ITV (fMLD,fV5-fV60). The primary endpoint was symptomatic grade 2+ (G2+) pneumonitis. Receiver operator curve (ROC) analyses were used to identify predictors of pneumonitis. RESULTS: G2+ pneumonitis occurred in 22.2% of patients, with no differences between stage, smoking status, COPD, or chemo/immunotherapy use between G<2 and G2+ patients (P≥ 0.18). Highly ventilated lung was defined as voxels exceeding the population-wide median of 18% voxel-level expansion. All total and functional metrics were significantly different between patients with and without pneumonitis (P≤ 0.039). Optimal ROC points predicting pneumonitis from functional lung dose were fMLD ≤ 12.3 Gy, fV5 ≤ 54% and fV20 ≤ 19 %. Patients with fMLD ≤ 12.3 Gy had a 14% risk of developing G2+ pneumonitis whereas risk significantly increased to 35% for those with fMLD > 12.3 Gy (P = 0.035). CONCLUSIONS: Dose to highly ventilated lung is associated with symptomatic pneumonitis and treatment planning strategies should focus on limiting dose to functional regions. These findings provide important metrics to be used in functional lung avoidance RT planning and designing clinical trials.

Predicting pulmonary ventilation damage after radiation therapy for nonsmall cell lung cancer using a ResNet generative adversarial network.

BACKGROUND: Functional lung avoidance radiation therapy (RT) is a technique being investigated to preferentially avoid specific regions of the lung that are predicted to be more susceptible to radiation-induced damage. Reducing the dose delivered to high functioning regions may reduce the occurrence radiation-induced lung injuries (RILIs) and toxicities. However, in order to develop effective lung function-sparing plans, accurate predictions of post-RT ventilation change are needed to determine which regions of the lung should be spared. PURPOSE: To predict pulmonary ventilation change following RT for nonsmall cell lung cancer using machine learning. METHODS: A conditional generative adversarial network (cGAN) was developed with data from 82 human subjects enrolled in a randomized clinical trial approved by the institution's IRB to predict post-RT pulmonary ventilation change. The inputs to the network were the pre-RT pulmonary ventilation map and radiation dose distribution. The loss function was a combination of the binary cross-entropy loss and an asymmetrical structural similarity index measure (aSSIM) function designed to increase penalization of under-prediction of ventilation damage. Network performance was evaluated against a previously developed polynomial regression model using a paired sample t-test for comparison. Evaluation was performed using eight-fold cross-validation. RESULTS: From the eight-fold cross-validation, we found that relative to the polynomial model, the cGAN model significantly improved predicting regions of ventilation damage following radiotherapy based on true positive rate (TPR), 0.14±0.15 to 0.72±0.21, and Dice similarity coefficient (DSC), 0.19±0.16 to 0.46±0.14, but significantly declined in true negative rate, 0.97±0.05 to 0.62±0.21, and accuracy, 0.79±0.08 to 0.65±0.14. Additionally, the average true positive volume increased from 104±119 cc in the POLY model to 565±332 cc in the cGAN model, and the average false negative volume decreased from 654±361 cc in the POLY model to 193±163 cc in the cGAN model. CONCLUSIONS: The proposed cGAN model demonstrated significant improvement in TPR and DSC. The higher sensitivity of the cGAN model can improve the clinical utility of functional lung avoidance RT by identifying larger volumes of functional lung that can be spared and thus decrease the probability of the patient developing RILIs.

Predicting severe chronic obstructive pulmonary disease exacerbations using quantitative CT: a retrospective model development and external validation study.

BACKGROUND: Quantitative CT is becoming increasingly common for the characterisation of lung disease; however, its added potential as a clinical tool for predicting severe exacerbations remains understudied. We aimed to develop and validate quantitative CT-based models for predicting severe chronic obstructive pulmonary disease (COPD) exacerbations. METHODS: We analysed the Subpopulations and Intermediate Outcome Measures In COPD Study (SPIROMICS) cohort, a multicentre study done at 12 clinical sites across the USA, of individuals aged 40-80 years from four strata: individuals who never smoked, individuals who smoked but had normal spirometry, individuals who smoked and had mild to moderate COPD, and individuals who smoked and had severe COPD. We used 3-year follow-up data to develop logistic regression classifiers for predicting severe exacerbations. Predictors included age, sex, race, BMI, pulmonary function, exacerbation history, smoking status, respiratory quality of life, and CT-based measures of density gradient texture and airway structure. We externally validated our models in a subset from the Genetic Epidemiology of COPD (COPDGene) cohort. Discriminative model performance was assessed using the area under the receiver operating characteristic curve (AUC), which was also compared with other predictors, including exacerbation history and the BMI, airflow obstruction, dyspnoea, and exercise capacity (BODE) index. We evaluated model calibration using calibration plots and Brier scores. FINDINGS: Participants in SPIROMICS were enrolled between Nov 12, 2010, and July 31, 2015. Participants in COPDGene were enrolled between Jan 10, 2008, and April 15, 2011. We included 1956 participants from the SPIROMICS cohort who had complete 3-year follow-up data: the mean age of the cohort was 63·1 years (SD 9·2) and 1017 (52%) were men and 939 (48%) were women. Among the 1956 participants, 434 (22%) had a history of at least one severe exacerbation. For the CT-based models, the AUC was 0·854 (95% CI 0·852-0·855) for at least one severe exacerbation within 3 years and 0·931 (0·930-0·933) for consistent exacerbations (defined as ≥1 acute episode in each of the 3 years). Models were well calibrated with low Brier scores (0·121 for at least one severe exacerbation; 0·039 for consistent exacerbations). For the prediction of at least one severe event during 3-year follow-up, AUCs were significantly higher with CT biomarkers (0·854 [0·852-0·855]) than exacerbation history (0·823 [0·822-0·825]) and BODE index 0·812 [0·811-0·814]). 6965 participants were included in the external validation cohort, with a mean age of 60·5 years (SD 8·9). In this cohort, AUC for at least one severe exacerbation was 0·768 (0·767-0·769; Brier score 0·088). INTERPRETATION: CT-based prediction models can be used for identification of patients with COPD who are at high risk of severe exacerbations. The newly identified CT biomarkers could potentially enable investigation into underlying disease mechanisms responsible for exacerbations. FUNDING: National Institutes of Health and the National Heart, Lung, and Blood Institute.

Robust Measures of Image-Registration-Derived Lung Biomechanics in SPIROMICS.

Chronic obstructive pulmonary disease (COPD) is an umbrella term used to define a collection of inflammatory lung diseases that cause airflow obstruction and severe damage to the lung parenchyma. This study investigated the robustness of image-registration-based local biomechanical properties of the lung in individuals with COPD as a function of Global Initiative for Chronic Obstructive Lung Disease (GOLD) stage. Image registration was used to estimate the pointwise correspondences between the inspiration (total lung capacity) and expiration (residual volume) computed tomography (CT) images of the lung for each subject. In total, three biomechanical measures were computed from the correspondence map: the Jacobian determinant; the anisotropic deformation index (ADI); and the slab-rod index (SRI). CT scans from 245 subjects with varying GOLD stages were analyzed from the SubPopulations and InteRmediate Outcome Measures In COPD Study (SPIROMICS). Results show monotonic increasing or decreasing trends in the three biomechanical measures as a function of GOLD stage for the entire lung and on a lobe-by-lobe basis. Furthermore, these trends held across all five image registration algorithms. The consistency of the five image registration algorithms on a per individual basis is shown using Bland-Altman plots.

CT-derived vessel segmentation for analysis of post-radiation therapy changes in vasculature and perfusion.

Vessel segmentation in the lung is an ongoing challenge. While many methods have been able to successfully identify vessels in normal, healthy, lungs, these methods struggle in the presence of abnormalities. Following radiotherapy, these methods tend to identify regions of radiographic change due to post-radiation therapytoxicities as vasculature falsely. By combining texture analysis and existing vasculature and masking techniques, we have developed a novel vasculature segmentation workflow that improves specificity in irradiated lung while preserving the sensitivity of detection in the rest of the lung. Furthermore, radiation dose has been shown to cause vascular injury as well as reduce pulmonary function post-RT. This work shows the improvements our novel vascular segmentation method provides relative to existing methods. Additionally, we use this workflow to show a dose dependent radiation-induced change in vasculature which is correlated with previously measured perfusion changes (R 2 = 0.72) in both directly irradiated and indirectly damaged regions of perfusion. These results present an opportunity to extend non-contrast CT-derived models of functional change following radiation therapy.

Measuring Indirect Radiation-Induced Perfusion Change in Fed Vasculature Using Dynamic Contrast CT.

Recent functional lung imaging studies have presented evidence of an "indirect effect" on perfusion damage, where regions that are unirradiated or lowly irradiated but that are supplied by highly irradiated regions observe perfusion damage post-radiation therapy (RT). The purpose of this work was to investigate this effect using a contrast-enhanced dynamic CT protocol to measure perfusion change in five novel swine subjects. A cohort of five Wisconsin Miniature Swine (WMS) were given a research course of 60 Gy in five fractions delivered locally to a vessel in the lung using an Accuray Radixact tomotherapy system with Synchrony motion tracking to increase delivery accuracy. Imaging was performed prior to delivering RT and 3 months post-RT to yield a 28−36 frame image series showing contrast flowing in and out of the vasculature. Using MIM software, contours were placed in six vessels on each animal to yield a contrast flow curve for each vessel. The contours were placed as follows: one at the point of max dose, one low-irradiated (5−20 Gy) branching from the max dose vessel, one low-irradiated (5−20 Gy) not branching from the max dose vessel, one unirradiated (<5 Gy) branching from the max dose vessel, one unirradiated (<5 Gy) not branching from the max dose vessel, and one in the contralateral lung. Seven measurements (baseline-to-baseline time and difference, slope up and down, max rise and value, and area under the curve) were acquired for each vessel's contrast flow curve in each subject. Paired Student t-tests showed statistically significant (p < 0.05) reductions in the area under the curve in the max dose, and both fed contours indicating an overall reduction in contrast in these regions. Additionally, there were statistically significant reductions observed when comparing pre- and post-RT in slope up and down in the max dose, low-dose fed, and no-dose fed contours but not the low-dose not-fed, no-dose not-fed, or contralateral contours. These findings suggest an indirect damage effect where irradiation of the vasculature causes a reduction in perfusion in irradiated regions as well as regions fed by the irradiated vasculature.

Sex Differences in Airways at Chest CT: Results from the COPDGene Cohort.

Background The prevalence of chronic obstructive pulmonary disease (COPD) in women is fast approaching that in men, and women experience greater symptom burden. Although sex differences in emphysema have been reported, differences in airways have not been systematically characterized. Purpose To evaluate whether structural differences in airways may underlie some of the sex differences in COPD prevalence and clinical outcomes. Materials and Methods In a secondary analyses of a multicenter study of never-, current-, and former-smokers enrolled from January 2008 to June 2011 and followed up longitudinally until November 2020, airway disease on CT images was quantified using seven metrics: airway wall thickness, wall area percent, and square root of the wall thickness of a hypothetical airway with internal perimeter of 10 mm (referred to as Pi10) for airway wall; and lumen diameter, airway volume, total airway count, and airway fractal dimension for airway lumen. Least-squares mean values for each airway metric were calculated and adjusted for age, height, ethnicity, body mass index, pack-years of smoking, current smoking status, total lung capacity, display field of view, and scanner type. In ever-smokers, associations were tested between each airway metric and postbronchodilator forced expiratory volume in 1 second (FEV1)-to-forced vital capacity (FVC) ratio, modified Medical Research Council dyspnea scale, St George's Respiratory Questionnaire score, and 6-minute walk distance. Multivariable Cox proportional hazards models were created to evaluate the sex-specific association between each airway metric and mortality. Results In never-smokers (n = 420), men had thicker airway walls than women as quantified on CT images for segmental airway wall area percentage (least-squares mean, 47.68 ± 0.61 [standard error] vs 45.78 ± 0.55; difference, -1.90; P = .02), whereas airway lumen dimensions were lower in women than men after accounting for height and total lung capacity (segmental lumen diameter, 8.05 mm ± 0.14 vs 9.05 mm ± 0.16; difference, -1.00 mm; P < .001). In ever-smokers (n = 9363), men had greater segmental airway wall area percentage (least-squares mean, 52.19 ± 0.16 vs 48.89 ± 0.18; difference, -3.30; P < .001), whereas women had narrower segmental lumen diameter (7.80 mm ± 0.05 vs 8.69 mm ± 0.04; difference, -0.89; P < .001). A unit change in each of the airway metrics (higher wall or lower lumen measure) resulted in lower FEV1-to-FVC ratio, more dyspnea, poorer respiratory quality of life, lower 6-minute walk distance, and worse survival in women compared with men (all P < .01). Conclusion Airway lumen sizes quantified at chest CT were smaller in women than in men after accounting for height and lung size, and these lower baseline values in women conferred lower reserves against respiratory morbidity and mortality for equivalent changes compared with men. © RSNA, 2022 Online supplemental material is available for this article.

Quantitative CT Characteristics of Cluster Phenotypes in the Severe Asthma Research Program Cohorts.

Background Clustering key clinical characteristics of participants in the Severe Asthma Research Program (SARP), a large, multicenter prospective observational study of patients with asthma and healthy controls, has led to the identification of novel asthma phenotypes. Purpose To determine whether quantitative CT (qCT) could help distinguish between clinical asthma phenotypes. Materials and Methods A retrospective cross-sectional analysis was conducted with the use of qCT images (maximal bronchodilation at total lung capacity [TLC], or inspiration, and functional residual capacity [FRC], or expiration) from the cluster phenotypes of SARP participants (cluster 1: minimal disease; cluster 2: mild, reversible; cluster 3: obese asthma; cluster 4: severe, reversible; cluster 5: severe, irreversible) enrolled between September 2001 and December 2015. Airway morphometry was performed along standard paths (RB1, RB4, RB10, LB1, and LB10). Corresponding voxels from TLC and FRC images were mapped with use of deformable image registration to characterize disease probability maps (DPMs) of functional small airway disease (fSAD), voxel-level volume changes (Jacobian), and isotropy (anisotropic deformation index [ADI]). The association between cluster assignment and qCT measures was evaluated using linear mixed models. Results A total of 455 participants were evaluated with cluster assignments and CT (mean age ± SD, 42.1 years ± 14.7; 270 women). Airway morphometry had limited ability to help discern between clusters. DPM fSAD was highest in cluster 5 (cluster 1 in SARP III: 19.0% ± 20.6; cluster 2: 18.9% ± 13.3; cluster 3: 24.9% ± 13.1; cluster 4: 24.1% ± 8.4; cluster 5: 38.8% ± 14.4; P < .001). Lower whole-lung Jacobian and ADI values were associated with greater cluster severity. Compared to cluster 1, cluster 5 lung expansion was 31% smaller (Jacobian in SARP III cohort: 2.31 ± 0.6 vs 1.61 ± 0.3, respectively, P < .001) and 34% more isotropic (ADI in SARP III cohort: 0.40 ± 0.1 vs 0.61 ± 0.2, P < .001). Within-lung Jacobian and ADI SDs decreased as severity worsened (Jacobian SD in SARP III cohort: 0.90 ± 0.4 for cluster 1; 0.79 ± 0.3 for cluster 2; 0.62 ± 0.2 for cluster 3; 0.63 ± 0.2 for cluster 4; and 0.41 ± 0.2 for cluster 5; P < .001). Conclusion Quantitative CT assessments of the degree and intraindividual regional variability of lung expansion distinguished between well-established clinical phenotypes among participants with asthma from the Severe Asthma Research Program study. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Verschakelen in this issue.

PLOSL: Population learning followed by one shot learning pulmonary image registration using tissue volume preserving and vesselness constraints.

This paper presents the Population Learning followed by One Shot Learning (PLOSL) pulmonary image registration method. PLOSL is a fast unsupervised learning-based framework for 3D-CT pulmonary image registration algorithm based on combining population learning (PL) and one-shot learning (OSL). The PLOSL image registration has the advantages of the PL and OSL approaches while reducing their respective drawbacks. The advantages of PLOSL include improved performance over PL, substantially reducing OSL training time and reducing the likelihood of OSL getting stuck in local minima. PLOSL pulmonary image registration uses tissue volume preserving and vesselness constraints for registration of inspiration-to-expiration and expiration-to-inspiration pulmonary CT images. A coarse-to-fine convolution encoder-decoder CNN architecture is used to register large and small shape features. During training, the sum of squared tissue volume difference (SSTVD) compensates for intensity differences between inspiration and expiration computed tomography (CT) images and the sum of squared vesselness measure difference (SSVMD) helps match the lung vessel tree. Results show that the PLOSL (SSTVD+SSVMD) algorithm achieved subvoxel landmark error while preserving pulmonary topology on the SPIROMICS data set, the public DIR-LAB COPDGene and 4DCT data sets.