Airway tapering: an objective image biomarker for bronchiectasis

Comparative sensitivity of early cystic fibrosis lung disease detection tools in school aged children

BACKGROUND

Effective detection of early lung disease in cystic fibrosis (CF) is critical to understanding early pathogenesis and evaluating early intervention strategies. We aimed to compare ability of several proposed sensitive functional tools to detect early CF lung disease as defined by CT structural disease in school aged children.

METHODS

50 CF subjects (mean±SD 11.2 ± 3.5y, range 5-18y) with early lung disease (FEV1≥70 % predicted: 95.7 ± 11.8 %) performed spirometry, Multiple breath washout (MBW, including trapped gas assessment), oscillometry, cardiopulmonary exercise testing (CPET) and simultaneous spirometer-directed low-dose CT imaging. CT data were analysed using well-evaluated fully quantitative software for bronchiectasis and air trapping (AT).

RESULTS

CT bronchiectasis and AT occurred in 24 % and 58 % of patients, respectively. Of the functional tools, MBW detected the highest rates of abnormality: Scond 82 %, MBWTG RV 78 %, LCI 74 %, MBWTG IC 68 % and Sacin 51 %. CPET VO2peak detected slightly higher rates of abnormality (9 %) than spirometry-based FEV1 (2 %). For oscillometry AX (14 %) performed better than Rrs (2 %) whereas Xrs and R5-19 failed to detect any abnormality. LCI and Scond correlated with bronchiectasis (r = 0.55-0.64, p < 0.001) and AT (r = 0.73-0.74, p < 0.001). MBW-assessed trapped gas was detectable in 92 % of subjects and concordant with CT-assessed AT in 74 %.

CONCLUSIONS

Significant structural and functional deficits occur in early CF lung disease, as detected by CT and MBW. For MBW, additional utility, beyond that offered by LCI, was suggested for Scond and MBW-assessed gas trapping. Our study reinforces the complementary nature of these tools and the limited utility of conventional oscillometry and CPET in this setting.

Radiographic Outcomes in Pediatric Bronchiectasis and Factors Associated with Reversibility

Rationale: Conventionally considered irreversible, bronchiectasis has been demonstrated to be reversible in children in small studies. However, the factors associated with radiographic reversibility of bronchiectasis have yet to be defined. Objectives: In a large cohort of children with bronchiectasis, we aimed to determine: 1) if and to what extent bronchiectasis is reversible and 2) factors associated with radiographic chest high-resolution computed tomography (cHRCT) resolution. Methods: We identified children with bronchiectasis who had a repeat multidetector cHRCT scan between 2010 and 2021. We excluded those with cystic fibrosis, surgical pulmonary resection, traction bronchiectasis only, or lobar opacification. Measurements and Main Results: cHRCT scans were scored using the modified Reiff score (MRS) with a pediatric correction. Resolution was defined as an absence of abnormal bronchoarterial ratio (>0.8) on the second cHRCT scan. We included 142 children (median age, 5 years; IQR, 2.6-7.4). Inter- and intrarater agreement in MRSs was excellent (weighted κ = 0.83-0.86 and 0.95, respectively). There was radiographic resolution in 57 of 142 patients (40.1%), improvement in 56 of 142 (39.4%), and no change or worsening in 29 of 142 (20.4%). Pseudomonas aeruginosa (PsA) was absolutely associated with a lack of resolution. On multivariable regression, in those without PsA cultured, younger age at the time of diagnosis (risk ratio [RR], 0.94; 95% confidence interval [CI], 0.88-0.99), lower MRS (RR, 0.89; 95% CI, 0.82-0.97), and lower annual rate of exacerbations requiring intravenous antibiotic therapy (RR, 0.60; 95% CI, 0.37-0.98) increased the likelihood of radiographic resolution. Conclusions: This first large cohort confirms that bronchiectasis in children is often reversible with appropriate management. Younger children and those with lesser radiographic severity at diagnosis were most likely to exhibit radiographic reversibility, whereas those with PsA infection were least likely.

Children with severe asthma have substantial structural airway changes on computed tomography

Background

In adults with severe asthma (SA) bronchial wall thickening, bronchiectasis and low attenuation regions (LAR) have been described on chest computed tomography (CT) scans. The extent to which these structural abnormalities are present in children with SA is largely unknown. Our aim was to study the presence and extent of airway abnormalities on chest CT of children with SA.

Methods

161 inspiratory and expiratory CT scans, either spirometer-controlled or technician-controlled, obtained in 131 children with SA (mean±SD age 11.0±3.8 years) were collected retrospectively. Inspiratory scans were analysed manually using a semi-quantitative score and automatically using LungQ (v2.1.0.1; Thirona B.V., Nijmegen, the Netherlands). LungQ segments the bronchial tree, identifies the generation for each bronchus-artery (BA) pair and measures the following BA dimensions: outer bronchial wall diameter (Bout), adjacent artery diameter (A) and bronchial wall thickness (Bwt). Bronchiectasis was defined as Bout/A ≥1.1, bronchial wall thickening as Bwt/A ≥0.14. LAR, reflecting small airways disease (SAD), was measured automatically on inspiratory and expiratory scans and manually on expiratory scans. Functional SAD was defined as FEF25-75 and/or FEF75 z-scores <-1.645. Results are shown as median and interquartile range.

Results

Bronchiectasis was present on 95.8% and bronchial wall thickening on all CTs using the automated method. Bronchiectasis was present on 28% and bronchial wall thickening on 88.8% of the CTs using the manual semi-quantitative analysis. The percentage of BA pairs defined as bronchiectasis was 24.62% (12.7-39.3%) and bronchial wall thickening was 41.7% (24.0-79.8%) per CT using the automated method. LAR was observed on all CTs using the automatic analysis and on 82.9% using the manual semi-quantitative analysis. Patients with LAR or functional SAD had more thickened bronchi than patients without.

Conclusion

Despite a large discrepancy between the automated and the manual semi-quantitative analysis, bronchiectasis and bronchial wall thickening are present on most CT scans of children with SA. SAD is related to bronchial wall thickening.

Adversarial Transformer for Repairing Human Airway Segmentation

Automated airway segmentation models often suffer from discontinuities in peripheral bronchioles, which limits their clinical applicability. Furthermore, data heterogeneity across different centres and pathological abnormalities pose significant challenges to achieving accurate and robust segmentation in distal small airways. Accurate segmentation of airway structures is essential for the diagnosis and prognosis of lung diseases. To address these issues, we propose a patch-scale adversarial-based refinement network that takes in preliminary segmentation and original CT images and outputs a refined mask of the airway structure. Our method is validated on three datasets, including healthy cases, pulmonary fibrosis, and COVID-19 cases, and quantitatively evaluated using seven metrics. Our method achieves more than a 15% increase in the detected length ratio and detected branch ratio compared to previously proposed models, demonstrating its promising performance. The visual results show that our refinement approach, guided by a patch-scale discriminator and centreline objective functions, effectively detects discontinuities and missing bronchioles. We also demonstrate the generalizability of our refinement pipeline on three previous models, significantly improving their segmentation completeness. Our method provides a robust and accurate airway segmentation tool that can help improve diagnosis and treatment planning for lung diseases.

Artificial Intelligence-based CT Assessment of Bronchiectasis: The COPDGene Study

Background CT is the standard method used to assess bronchiectasis. A higher airway-to-artery diameter ratio (AAR) is typically used to identify enlarged bronchi and bronchiectasis; however, current imaging methods are limited in assessing the extent of this metric in CT scans. Purpose To determine the extent of AARs using an artificial intelligence-based chest CT and assess the association of AARs with exacerbations over time. Materials and Methods In a secondary analysis of ever-smokers from the prospective, observational, multicenter COPDGene study, AARs were quantified using an artificial intelligence tool. The percentage of airways with AAR greater than 1 (a measure of airway dilatation) in each participant on chest CT scans was determined. Pulmonary exacerbations were prospectively determined through biannual follow-up (from July 2009 to September 2021). Multivariable zero-inflated regression models were used to assess the association between the percentage of airways with AAR greater than 1 and the total number of pulmonary exacerbations over follow-up. Covariates included demographics, lung function, and conventional CT parameters. Results Among 4192 participants (median age, 59 years; IQR, 52-67 years; 1878 men [45%]), 1834 had chronic obstructive pulmonary disease (COPD). During a 10-year follow-up and in adjusted models, the percentage of airways with AARs greater than 1 (quartile 4 vs 1) was associated with a higher total number of exacerbations (risk ratio [RR], 1.08; 95% CI: 1.02, 1.15; P = .01). In participants meeting clinical and imaging criteria of bronchiectasis (ie, clinical manifestations with ≥3% of AARs >1) versus those who did not, the RR was 1.37 (95% CI: 1.31, 1.43; P < .001). Among participants with COPD, the corresponding RRs were 1.10 (95% CI: 1.02, 1.18; P = .02) and 1.32 (95% CI: 1.26, 1.39; P < .001), respectively. Conclusion In ever-smokers with chronic obstructive pulmonary disease, artificial intelligence-based CT measures of bronchiectasis were associated with more exacerbations over time. Clinical trial registration no. NCT00608764 © RSNA, 2022 Supplemental material is available for this article. See also the editorial by Schiebler and Seo in this issue.

Towards development of evidence to inform recommendations for the evaluation and management of bronchiectasis

Bronchiectasis (BE) is a chronic condition characterized by airway dilation as a consequence of a variety of pathogenic processes. It is often associated with persistent airway infection and an inflammatory response resulting in cough productive of purulent sputum, which has an adverse impact on quality of life. The prevalence of BE is increasing worldwide. Treatment guidelines exist for managing BE, but they are generally informed by a paucity of high-quality evidence. This review presents the findings of a scientific advisory board of experts held in the United States in November 2020. The main focus of the meeting was to identify unmet needs in BE and propose ways to identify research priorities for the management of BE, with a view to developing evidence-based treatment recommendations. Key issues identified include diagnosis, patient evaluation, promoting airway clearance and appropriate use of antimicrobials. Unmet needs include effective pharmacological agents to promote airway clearance and reduce inflammation, control of chronic infection, clinical endpoints to be used in the design of BE clinical trials, and more accurate classification of patients using phenotypes and endotypes to better guide treatment decisions and improve outcomes.

Automated Detection of Broncho-Arterial Pairs Using CT Scans Employing Different Approaches to Classify Lung Diseases

Current research indicates that for the identification of lung disorders, comprising pneumonia and COVID-19, structural distortions of bronchi and arteries (BA) should be taken into account. CT scans are an effective modality to detect lung anomalies. However, anomalies in bronchi and arteries can be difficult to detect. Therefore, in this study, alterations of bronchi and arteries are considered in the classification of lung diseases. Four approaches to highlight these are introduced: (a) a Hessian-based approach, (b) a region-growing algorithm, (c) a clustering-based approach, and (d) a color-coding-based approach. Prior to this, the lungs are segmented, employing several image preprocessing algorithms. The utilized COVID-19 Lung CT scan dataset contains three classes named Non-COVID, COVID, and community-acquired pneumonia, having 6983, 7593, and 2618 samples, respectively. To classify the CT scans into three classes, two deep learning architectures, (a) a convolutional neural network (CNN) and (b) a CNN with long short-term memory (LSTM) and an attention mechanism, are considered. Both these models are trained with the four datasets achieved from the four approaches. Results show that the CNN model achieved test accuracies of 88.52%, 87.14%, 92.36%, and 95.84% for the Hessian, the region-growing, the color-coding, and the clustering-based approaches, respectively. The CNN with LSTM and an attention mechanism model results in an increase in overall accuracy for all approaches with an 89.61%, 88.28%, 94.61%, and 97.12% test accuracy for the Hessian, region-growing, color-coding, and clustering-based approaches, respectively. To assess overfitting, the accuracy and loss curves and k-fold cross-validation technique are employed. The Hessian-based and region-growing algorithm-based approaches produced nearly equivalent outcomes. Our proposed method outperforms state-of-the-art studies, indicating that it may be worthwhile to pay more attention to BA features in lung disease classification based on CT images.

The effect of CFTR modulators on structural lung disease in cystic fibrosis

Background: Newly developed quantitative chest computed tomography (CT) outcomes designed specifically to assess structural abnormalities related to cystic fibrosis (CF) lung disease are now available. CFTR modulators potentially can reduce some structural lung abnormalities. We aimed to investigate the effect of CFTR modulators on structural lung disease progression using different quantitative CT analysis methods specific for people with CF (PwCF). Methods: PwCF with a gating mutation (Ivacaftor) or two Phe508del alleles (lumacaftor-ivacaftor) provided clinical data and underwent chest CT scans. Chest CTs were performed before and after initiation of CFTR modulator treatment. Structural lung abnormalities on CT were assessed using the Perth Rotterdam Annotated Grid Morphometric Analysis for CF (PRAGMA-CF), airway-artery dimensions (AA), and CF-CT methods. Lung disease progression (0-3 years) in exposed and matched unexposed subjects was compared using analysis of covariance. To investigate the effect of treatment in early lung disease, subgroup analyses were performed on data of children and adolescents aged <18 years. Results: We included 16 modulator exposed PwCF and 25 unexposed PwCF. Median (range) age at the baseline visit was 12.55 (4.25-36.49) years and 8.34 (3.47-38.29) years, respectively. The change in PRAGMA-CF %Airway disease (-2.88 (-4.46, -1.30), p = 0.001) and %Bronchiectasis extent (-2.07 (-3.13, -1.02), p < 0.001) improved in exposed PwCF compared to unexposed. Subgroup analysis of paediatric data showed that only PRAGMA-CF %Bronchiectasis (-0.88 (-1.70, -0.07), p = 0.035) improved in exposed PwCF compared to unexposed. Conclusion: In this preliminary real-life retrospective study CFTR modulators improve several quantitative CT outcomes. A follow-up study with a large cohort and standardization of CT scanning is needed to confirm our findings.

Detection and Classification of Bronchiectasis Through Convolutional Neural Networks

PURPOSE

Bronchiectasis is a chronic disease characterized by an irreversible dilatation of bronchi leading to chronic infection, airway inflammation, and progressive lung damage. Three specific patterns of bronchiectasis are distinguished in clinical practice: cylindrical, varicose, and cystic. The predominance and the extension of the type of bronchiectasis provide important clinical information. However, characterization is often challenging and is subject to high interobserver variability. The aim of this study is to provide an automatic tool for the detection and classification of bronchiectasis through convolutional neural networks.

MATERIALS AND METHODS

Two distinct approaches were adopted: (i) direct network performing a multilabel classification of 32×32 regions of interest (ROIs) into 4 classes: healthy, cylindrical, cystic, and varicose and (ii) a 2-network serial approach, where the first network performed a binary classification between normal tissue and bronchiectasis and the second one classified the ROIs containing abnormal bronchi into one of the 3 bronchiectasis typologies. Performances of the networks were compared with other architectures presented in the literature.

RESULTS

Computed tomography from healthy individuals (n=9, age=47±6, FEV1%pred=109±17, FVC%pred=116±17) and bronchiectasis patients (n=21, age=59±15, FEV1%pred=74±25, FVC%pred=91±22) were collected. A total of 19,059 manually selected ROIs were used for training and testing. The serial approach provided the best results with an accuracy and F1 score average of 0.84, respectively. Slightly lower performances were observed for the direct network (accuracy=0.81 and F1 score average=0.82). On the test set, cylindrical bronchiectasis was the subtype classified with highest accuracy, while most of the misclassifications were related to the varicose pattern, mainly to the cylindrical class.

CONCLUSION

The developed networks accurately detect and classify bronchiectasis disease, allowing to collect quantitative information regarding the radiologic severity and the topographical distribution of bronchiectasis subtype.

Radiology of Bronchiectasis

Bronchiectasis is a radiological diagnosis made using computed tomographic (CT) imaging. Although visual CT assessment is necessary for the diagnosis of bronchiectasis, visual assessment of disease severity and progression is challenging. Computer tools offer the potential to improve the characterization of lung damage in patients with bronchiectasis. Newer imaging techniques such as MRI with hyperpolarized gas inhalation have the potential to identify early forms of disease and are without the constraints of requiring ionizing radiation exposure.

Automatic airway segmentation from computed tomography using robust and efficient 3-D convolutional neural networks

This paper presents a fully automatic and end-to-end optimised airway segmentation method for thoracic computed tomography, based on the U-Net architecture. We use a simple and low-memory 3D U-Net as backbone, which allows the method to process large 3D image patches, often comprising full lungs, in a single pass through the network. This makes the method simple, robust and efficient. We validated the proposed method on three datasets with very different characteristics and various airway abnormalities: (1) a dataset of pediatric patients including subjects with cystic fibrosis, (2) a subset of the Danish Lung Cancer Screening Trial, including subjects with chronic obstructive pulmonary disease, and (3) the EXACT'09 public dataset. We compared our method with other state-of-the-art airway segmentation methods, including relevant learning-based methods in the literature evaluated on the EXACT'09 data. We show that our method can extract highly complete airway trees with few false positive errors, on scans from both healthy and diseased subjects, and also that the method generalizes well across different datasets. On the EXACT'09 test set, our method achieved the second highest sensitivity score among all methods that reported good specificity.

Imaging in non-cystic fibrosis bronchiectasis and current limitations

Non-cystic fibrosis bronchiectasis represents a heterogenous spectrum of disorders characterised by an abnormal and permanent dilatation of the bronchial tree associated with respiratory symptoms. To date, diagnosis relies on computed tomography (CT) evidence of dilated airways. Nevertheless, definite radiological criteria and standardised CT protocols are still to be defined. Although largely used, current radiological scoring systems have shown substantial drawbacks, mostly failing to correlate morphological abnormalities with clinical and prognostic data. In limited cases, bronchiectasis morphology and distribution, along with associated CT features, enable radiologists to confidently suggest an underlying cause. Quantitative imaging analyses have shown a potential to overcome the limitations of the current radiological criteria, but their application is still limited to a research setting.

In the present review, we discuss the role of imaging and its current limitations in non-cystic fibrosis bronchiectasis. The potential of automatic quantitative approaches and artificial intelligence in such a context will be also mentioned.

Refining diagnostic criteria for paediatric bronchiectasis using low-dose CT scan

BACKGROUND

There is a current lack of consensus amongst paediatric radiologists and respiratory paediatricians as to the correct CT definition of bronchiectasis in children. Using contemporary low-dose CT, our objectives were to determine the upper limit of normal for broncho-arterial ratio (BAR) in children and to evaluate the effect of age and general anaesthesia.

METHODS

Measurements of 330 broncho-arterial ratios from 51 children (0-19 years) undergoing low-dose CT chest for non-respiratory indications were performed by 3 blinded observers (two radiologists, one respiratory physician) using four different methods. Inter-observer reliability, mean BAR and reference ranges (mean±2SD) were calculated. Correlation between age and BARs were examined. Mean BAR for CT under general anaesthesia and CT awake were compared.

RESULTS

Inter-observer correlation was extremely high for all measurements (0.93-0.97). There was a weak positive correlation between age and BAR in the CT-awake group (r = 0.33, 95%CI: 0.03-0.57; p = 0.031) using the inner-bronchial wall to artery, short-axis measurement. CT under general anaesthesia showed significantly higher BAR compared to CT-awake [mean difference 0.13 (95%CI: 0.05-0.22; p = 0.004)]. For the CT-awake group, the mean BAR was 0.65 (range: 0.42 to 0.89), with no child having a BAR above 0.9.

CONCLUSION

Using a standardised approach, we have shown that a broncho-arterial ratio above 0.9 in children undergoing awake CT is abnormal and suggests airway widening or radiological bronchiectasis. Children undergoing CT under anaesthesia have higher BARs than those undergoing awake CT. A weak positive correlation between broncho-arterial ratio and age was observed, hence, age-adjusted cut-offs for BAR warrant further study.

Diagnosis and Initial Investigation of Bronchiectasis

Bronchiectasis refers to both the name of a disease and a single radiological appearance that may, or may not, be associated with disease. As chronic respiratory disease, bronchiectasis is characterized by a variable range of signs and symptoms that may overlap with other chronic respiratory conditions. The proper identification of bronchiectasis as a disease in both primary and secondary care is of paramount importance. However, a standardized definition of radiologically and clinically significant bronchiectasis is still missing. Disease heterogeneity is a hallmark of bronchiectasis and applies not only to radiological features and clinical manifestations but also to other aspects of the disease, including the etiological and microbiological diagnosis as well as the evaluation of pulmonary function. Although the guidelines suggest a "minimum bundle" of tests, the diagnostic approach to bronchiectasis is challenging and may be driven by the "treatable traits" approach based on endotypes and biological characteristics. A broad spectrum of diagnostic tests could be used to investigate the etiology of bronchiectasis as well as other pulmonary, extrapulmonary, and environmental traits. Individualizing bronchiectasis workup according to the site of care (e.g., primary, secondary, and tertiary care) could help optimize patients' management and reduce healthcare costs.

Novel imaging techniques for cystic fibrosis lung disease

With an increasing number of patients with cystic fibrosis (CF) receiving highly effective CFTR (cystic fibrosis transmembrane regulator protein) modulator therapy, particularly at a young age, there is an increasing need to identify imaging tools that can detect and regionally visualize mild CF lung disease and subtle changes in disease state. In this review, we discuss the latest developments in imaging modalities for both structural and functional imaging of the lung available to CF clinicians and researchers, from the widely available, clinically utilized imaging methods for assessing CF lung disease-chest radiography and computed tomography-to newer techniques poised to become the next phase of clinical tools-structural/functional proton and hyperpolarized gas magnetic resonance imaging (MRI). Finally, we provide a brief discussion of several newer lung imaging techniques that are currently available only in selected research settings, including chest tomosynthesis, and fluorinated gas MRI. We provide an update on the clinical and/or research status of each technique, with a focus on sensitivity, early disease detection, and possibilities for monitoring treatment efficacy.

Relationship between clinical and radiological signs of bronchiectasis in COPD patients: Results from COSYCONET

Bronchiectasis (BE) might be frequently present in COPD but masked by COPD symptoms. We studied the relationship of clinical signs of bronchiectasis to the presence and extent of its radiological signs in patients of different COPD severity. Visit 4 data (GOLD grades 1-4) of the COSYCONET cohort was used. Chest CT scans were evaluated for bronchiectasis in 6 lobes using a 3-point scale (0: absence, 1: ≤50%, 2: >50% BE-involvement for each lobe). 1176 patients were included (61%male, age 67.3y), among them 38 (3.2%) with reported physicians' diagnosis of bronchiectasis and 76 (6.5%) with alpha1-antitrypsin deficiency (AA1D). CT scans were obtained in 429 patients. Within this group, any signs of bronchiectasis were found in 46.6% of patients, whereby ≤50% BE occurred in 18.6% in ≤2 lobes, in 10.0% in 3-4 lobes, in 15.9% in 5-6 lobes; >50% bronchiectasis in at least 1 lobe was observed in 2.1%. Scores ≥4 correlated with an elevated ratio FRC/RV. The clinical diagnosis of bronchiectasis correlated with phlegm and cough and with radiological scores of at least 3, optimally ≥5. In COPD patients, clinical diagnosis and radiological signs of BE showed only weak correlations. Correlations became significant with increasing BE-severity implying radiological alterations in several lobes. This indicates the importance of reporting both presence and extent of bronchiectasis on CT. Further research is warranted to refine the criteria for CT scoring of bronchiectasis and to determine the relevance of radiologically but not clinically detectible bronchiectasis and their possible implications for therapy in COPD patients.

The radiological diagnosis of bronchiectasis: what's in a name?

Diagnosis of bronchiectasis is usually made using chest computed tomography (CT) scan, the current gold standard method. A bronchiectatic airway can show abnormal widening and thickening of its airway wall. In addition, it can show an irregular wall and lack of tapering, and/or can be visible in the periphery of the lung. Its diagnosis is still largely expert based. More recently, it has become clear that airway dimensions on CT and therefore the diagnosis of bronchiectasis are highly dependent on lung volume. Hence, control of lung volume is required during CT acquisition to standardise the evaluation of airways. Automated image analysis systems are in development for the objective analysis of airway dimensions and for the diagnosis of bronchiectasis. To use these systems, clear and objective definitions for the diagnosis of bronchiectasis are needed. Furthermore, the use of these systems requires standardisation of CT protocols and of lung volume during chest CT acquisition. In addition, sex- and age-specific reference values are needed for image analysis outcome parameters. This review focusses on today's issues relating to the radiological diagnosis of bronchiectasis using state-of-the-art CT imaging techniques.

Bronchiectasis diagnosis is expert based. Clear definitions, standardisation of lung volume and CT protocols, and reference values are needed to allow automated image analysis for its diagnosis and to be used for clinical management and clinical studies.http://bit.ly/35vASqz