Artificial intelligence in computed tomography for quantifying lung changes in the era of CFTR modulators.

BACKGROUND: Chest computed tomography (CT) remains the imaging standard for demonstrating cystic fibrosis (CF) airway structural disease in vivo. However, visual scoring systems as an outcome measure are time consuming, require training and lack high reproducibility. Our objective was to validate a fully automated artificial intelligence (AI)-driven scoring system of CF lung disease severity. METHODS: Data were retrospectively collected in three CF reference centres, between 2008 and 2020, in 184 patients aged 4-54 years. An algorithm using three 2D convolutional neural networks was trained with 78 patients' CT scans (23 530 CT slices) for the semantic labelling of bronchiectasis, peribronchial thickening, bronchial mucus, bronchiolar mucus and collapse/consolidation. 36 patients' CT scans (11 435 CT slices) were used for testing versus ground-truth labels. The method's clinical validity was assessed in an independent group of 70 patients with or without lumacaftor/ivacaftor treatment (n=10 and n=60, respectively) with repeat examinations. Similarity and reproducibility were assessed using the Dice coefficient, correlations using the Spearman test, and paired comparisons using the Wilcoxon rank test. RESULTS: The overall pixelwise similarity of AI-driven versus ground-truth labels was good (Dice 0.71). All AI-driven volumetric quantifications had moderate to very good correlations to a visual imaging scoring (p<0.001) and fair to good correlations to forced expiratory volume in 1 s % predicted at pulmonary function tests (p<0.001). Significant decreases in peribronchial thickening (p=0.005), bronchial mucus (p=0.005) and bronchiolar mucus (p=0.007) volumes were measured in patients with lumacaftor/ivacaftor. Conversely, bronchiectasis (p=0.002) and peribronchial thickening (p=0.008) volumes increased in patients without lumacaftor/ivacaftor. The reproducibility was almost perfect (Dice >0.99). CONCLUSION: AI allows fully automated volumetric quantification of CF-related modifications over an entire lung. The novel scoring system could provide a robust disease outcome in the era of effective CF transmembrane conductance regulator modulator therapy.

Utilizing flip angle/TR equivalence to reduce breath hold duration in hyperpolarized 129 Xe 1-point Dixon gas exchange imaging.

PURPOSE: To reduce scan duration in hyperpolarized 129 Xe 1-point Dixon gas exchange imaging by utilizing flip angle (FA)/TR equivalence. METHODS: Images were acquired in 12 subjects (n = 3 radiation therapy, n = 1 unexplained dyspnea, n = 8 healthy) using both standard (TR = 15 ms, FA = 20°, duration = 15 s, 998 projections) and "fast" (TR = 5.4 ms, FA = 12°, duration = 11.3 s, 2100 projections) acquisition parameters. For the fast acquisition, 3 image sets were reconstructed using subsets of 1900, 1500, and 1000 projections. From the resulting ventilation, tissue ("barrier"), and red blood cell (RBC) images, image metrics and biomarkers were compared to assess agreement between methods. RESULTS: Images acquired using both FA/TR settings had similar qualitative appearance. There were no significant differences in SNR, image mean, or image SD between images. Moreover, the percentage of the lungs in "defect", "normal", and "high" bins for each image (ventilation, RBC, barrier) was not significantly different among the acquisition types. After registration, comparison of 3D image metrics (Dice, volume similarity, average distance) agreed well between bins. Images using 1000 projections for reconstruction had no significant differences from images using all projections. CONCLUSION: Using flip angle/TR equivalence, hyperpolarized 129 Xe gas exchange images can be acquired via the 1-point Dixon technique in as little as 6 s, compared to ~15 s for previously reported parameter settings. The resulting images from this accelerated scan have no significant differences from the standard method in qualitative appearance or quantitative metrics.

Imaging in Asthma Management.

Asthma is a heterogeneous disease characterized by chronic airway inflammation that affects more than 300 million people worldwide. Clinically, asthma has a widely variable presentation and is defined based on a history of respiratory symptoms alongside airflow limitation. Imaging is not needed to confirm a diagnosis of asthma, and thus the use of imaging in asthma has historically been limited to excluding alternative diagnoses. However, significant advances continue to be made in novel imaging methodologies, which have been increasingly used to better understand respiratory impairment in asthma. As a disease primarily impacting the airways, asthma is best understood by imaging methods with the ability to elucidate airway impairment. Techniques such as computed tomography, magnetic resonance imaging with gaseous contrast agents, and positron emission tomography enable assessment of the small airways. Others, such as optical coherence tomography and endobronchial ultrasound enable high-resolution imaging of the large airways accessible to bronchoscopy. These imaging techniques are providing new insights in the pathophysiology and treatments of asthma and are poised to impact the clinical management of asthma.

Protocols for multi-site trials using hyperpolarized 129 Xe MRI for imaging of ventilation, alveolar-airspace size, and gas exchange: A position paper from the 129 Xe MRI clinical trials consortium.

Hyperpolarized (HP) 129 Xe MRI uniquely images pulmonary ventilation, gas exchange, and terminal airway morphology rapidly and safely, providing novel information not possible using conventional imaging modalities or pulmonary function tests. As such, there is mounting interest in expanding the use of biomarkers derived from HP 129 Xe MRI as outcome measures in multi-site clinical trials across a range of pulmonary disorders. Until recently, HP 129 Xe MRI techniques have been developed largely independently at a limited number of academic centers, without harmonizing acquisition strategies. To promote uniformity and adoption of HP 129 Xe MRI more widely in translational research, multi-site trials, and ultimately clinical practice, this position paper from the 129 Xe MRI Clinical Trials Consortium (https://cpir.cchmc.org/XeMRICTC) recommends standard protocols to harmonize methods for image acquisition in HP 129 Xe MRI. Recommendations are described for the most common HP gas MRI techniques-calibration, ventilation, alveolar-airspace size, and gas exchange-across MRI scanner manufacturers most used for this application. Moreover, recommendations are described for 129 Xe dose volumes and breath-hold standardization to further foster consistency of imaging studies. The intention is that sites with HP 129 Xe MRI capabilities can readily implement these methods to obtain consistent high-quality images that provide regional insight into lung structure and function. While this document represents consensus at a snapshot in time, a roadmap for technical developments is provided that will further increase image quality and efficiency. These standardized dosing and imaging protocols will facilitate the wider adoption of HP 129 Xe MRI for multi-site pulmonary research.

Single-Session Bronchial Thermoplasty Guided by 129Xe Magnetic Resonance Imaging. A Pilot Randomized Controlled Clinical Trial.

Rationale: Adverse events have limited the use of bronchial thermoplasty (BT) in severe asthma.Objectives: We sought to evaluate the effectiveness and safety of using 129Xe magnetic resonance imaging (129Xe MRI) to prioritize the most involved airways for guided BT.Methods: Thirty subjects with severe asthma were imaged with volumetric computed tomography and 129Xe MRI to quantitate segmental ventilation defects. Subjects were randomized to treatment of the six most involved airways in the first session (guided group) or a standard three-session BT (unguided). The primary outcome was the change in Asthma Quality of Life Questionnaire score from baseline to 12 weeks after the first BT for the guided group compared with after three treatments for the unguided group.Measurements and Main Results: There was no significant difference in quality of life after one guided compared with three unguided BTs (change in Asthma Quality of Life Questionnaire guided = 0.91 [95% confidence interval, 0.28-1.53]; unguided = 1.49 [95% confidence interval, 0.84-2.14]; P = 0.201). After one BT, the guided group had a greater reduction in the percentage of poorly and nonventilated lung from baseline when compared with unguided (-17.2%; P = 0.009). Thirty-three percent experienced asthma exacerbations after one guided BT compared with 73% after three unguided BTs (P = 0.028).Conclusions: Results of this pilot study suggest that similar short-term improvements can be achieved with one BT treatment guided by 129Xe MRI when compared with standard three-treatment-session BT with fewer periprocedure adverse events.

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function.

Hyperpolarized 129Xe gas MRI is an emerging technique to evaluate and measure regional lung function including pulmonary gas distribution and gas exchange. Chest computed tomography (CT) still remains the clinical gold standard for imaging of the lungs, though, in part due to the rapid CT protocols that acquire high-resolution images in seconds and the widespread availability of CT scanners. Quantitative approaches have enabled the extraction of structural lung parenchymal, airway and vascular measurements from chest CT that have been evaluated in many clinical research studies. Together, CT and 129Xe MRI provide complementary information that can be used to evaluate regional lung structure and function, resulting in new insights into lung health and disease. 129Xe MR-CT image registration can be performed to measure regional lung structure-function to better understand lung disease pathophysiology, and to perform image-guided pulmonary interventions. Here, a method for 129Xe MRI-CT registration is outlined to support implementation in research or clinical settings. Registration methods and applications that have been employed to date in the literature are also summarized, and suggestions are provided for future directions that may further overcome technical challenges related to 129Xe MR-CT image registration and facilitate broader implementation of regional lung structure-function evaluation.

Use of Quantitative CT Imaging to Identify Bronchial Thermoplasty Responders.

BACKGROUND: Bronchial thermoplasty (BT) is a treatment for patients with poorly controlled, severe asthma. However, predictors of treatment response to BT are defined poorly. RESEARCH QUESTION: Do baseline radiographic and clinical characteristics exist that predict response to BT? STUDY DESIGN AND METHODS: We conducted a longitudinal prospective cohort study of participants with severe asthma receiving BT across eight academic medical centers. Participants received three separate BT treatments and were monitored at 3-month intervals for 1 year after BT. Similar to prior studies, a positive response to BT was defined as either improvement in Asthma Control Test results of ≥ 3 or Asthma Quality of Life Questionnaire of ≥ 0.5. Regression analyses were used to evaluate the association between pretreatment clinical and quantitative CT scan measures with subsequent BT response. RESULTS: From 2006 through 2017, 88 participants received BT, with 70 participants (79.5%) identified as responders by Asthma Control Test or Asthma Quality of Life Questionnaire criteria. Responders were less likely to undergo an asthma-related ICU admission in the prior year (3% vs 25%; P = .01). On baseline quantitative CT imaging, BT responders showed less air trapping percentage (OR, 0.90; 95% CI, 0.82-0.99; P = .03), a greater Jacobian determinant (OR, 1.49; 95% CI, 1.05-2.11), greater SD of the Jacobian determinant (OR, 1.84; 95% CI, 1.04-3.26), and greater anisotropic deformation index (OR, 3.06; 95% CI, 1.06-8.86). INTERPRETATION: To our knowledge, this is the largest study to evaluate baseline quantitative CT imaging and clinical characteristics associated with BT response. Our results show that preservation of normal lung expansion, indicated by less air trapping, a greater magnitude of isotropic expansion, and greater within-lung spatial variation on quantitative CT imaging, were predictors of future BT response. TRIAL REGISTRY: ClinicalTrials.gov; No.: NCT01185275; URL: www. CLINICALTRIALS: gov.

Preclinical MRI to Quantify Pulmonary Disease Severity and Trajectories in Poorly Characterized Mouse Models: A Pedagogical Example Using Data from Novel Transgenic Models of Lung Fibrosis.

Structural remodeling in lung disease is progressive and heterogeneous, making temporally and spatially explicit information necessary to understand disease initiation and progression. While mouse models are essential to elucidate mechanistic pathways underlying disease, the experimental tools commonly available to quantify lung disease burden are typically invasive (e.g., histology). This necessitates large cross-sectional studies with terminal endpoints, which increases experimental complexity and expense. Alternatively, magnetic resonance imaging (MRI) provides information noninvasively, thus permitting robust, repeated-measures statistics. Although lung MRI is challenging due to low tissue density and rapid apparent transverse relaxation (T2* <1 ms), various imaging methods have been proposed to quantify disease burden. However, there are no widely accepted strategies for preclinical lung MRI. As such, it can be difficult for researchers who lack lung imaging expertise to design experimental protocols-particularly for novel mouse models. Here, we build upon prior work from several research groups to describe a widely applicable acquisition and analysis pipeline that can be implemented without prior preclinical pulmonary MRI experience. Our approach utilizes 3D radial ultrashort echo time (UTE) MRI with retrospective gating and lung segmentation is facilitated with a deep-learning algorithm. This pipeline was deployed to assess disease dynamics over 255 days in novel, transgenic mouse models of lung fibrosis based on disease-associated, loss-of-function mutations in Surfactant Protein-C. Previously identified imaging biomarkers (tidal volume, signal coefficient of variation, etc.) were calculated semi-automatically from these data, with an objectively-defined high signal volume identified as the most robust metric. Beyond quantifying disease dynamics, we discuss common pitfalls encountered in preclinical lung MRI and present systematic approaches to identify and mitigate these challenges. While the experimental results and specific pedagogical examples are confined to lung fibrosis, the tools and approaches presented should be broadly useful to quantify structural lung disease in a wide range of mouse models.

Cyst Ventilation Heterogeneity and Alveolar Airspace Dilation as Early Disease Markers in Lymphangioleiomyomatosis.

Rationale: Lymphangioleiomyomatosis (LAM) is a rare disease associated with cystic destruction of the pulmonary parenchyma and chronic respiratory failure, and there are trials underway to determine if early intervention can prevent disease progression. An imaging technique that is sensitive to early regional disease would therefore be valuable for patient care and clinical trials.Objectives: We postulated that hyperpolarized 129Xe MRI would be sensitive to ventilation abnormalities and alveolar airspace dilation in patients with mild LAM disease and normal pulmonary function and that 129Xe MRI would reveal important features of cyst ventilation.Methods:129Xe ventilation and diffusion-weighted MR images were acquired in 22 patients with LAM during two breath-holds of hyperpolarized 129Xe. 129Xe ventilation defect percentage (VDP; percentage of voxels <60% of the mean whole-lung 129Xe MRI signal) and apparent diffusion coefficient (ADC), a measure of alveolar airspace size, were quantified and compared with pulmonary function test parameters with Spearman statistics. Sixteen patients with LAM had a recent, clinical chest computed tomography (CT) scan available, and cyst ventilation was assessed by thresholding cysts on the CT images and registration to the 129Xe ventilation images.Results: Ventilation deficits were observed in all patients with LAM, including those with normal pulmonary function and few cysts, and the mean VDP was 19.2% (95% confidence interval [CI], 14.8-23.5%). 129Xe VDP was strongly correlated with forced expiratory volume in 1 second (FEV1)/forced vital capacity (FVC) ratio (r = -0.51, P = 0.02) and diffusing capacity of the lung for carbon monoxide (DlCO) (r = -0.60, P = 0.009) but not with FEV1 (r = -0.33, P = 0.13), likely because of the sensitivity of 129Xe MRI to mild LAM disease in patients with normal FEV1. The mean ADC was 0.048 cm2/s (95% CI, 0.042-0.053 cm2/s). In many cases, ADC was elevated relative to previously reported values in adults, and ADC was correlated with FEV1, FEV1/FVC ratio, and DlCO (P ≤ 0.02 for all). Co-registered 129Xe MRI and CT imaging revealed considerable ventilation heterogeneity within individual patients with LAM and across patients with similarly sized cysts.Conclusions:129Xe MRI provides a means to assess the complex regional ventilation and alveolar airspace size changes of LAM with high sensitivity and may be a clinically useful future tool for screening, managing patients, and measuring treatment efficacy.