Artificial intelligence in CT for quantifying lung changes in the era of CFTR modulators

Paediatric Thoracic Imaging in Cystic Fibrosis in the Era of Cystic Fibrosis Transmembrane Conductance Regulator Modulation

Cystic fibrosis (CF) is one of the most common progressive life-shortening genetic conditions worldwide. Ground-breaking translational research has generated therapies that target the primary cystic fibrosis transmembrane conductance regulator (CFTR) defect, known as CFTR modulators. A crucial aspect of paediatric CF disease is the development and progression of irreversible respiratory disease in the absence of clinical symptoms. Accurate thoracic diagnostics have an important role to play in this regard. Chest radiographs are non-specific and insensitive in the context of subtle changes in early CF disease, with computed tomography (CT) providing increased sensitivity. Recent advancements in imaging hardware and software have allowed thoracic CTs to be acquired in paediatric patients at radiation doses approaching that of a chest radiograph. CFTR modulators slow the progression of CF, reduce the frequency of exacerbations and extend life expectancy. In conjunction with advances in CT imaging techniques, low-dose thorax CT will establish a central position in the routine care of children with CF. International guidelines regarding the choice of modality and timing of thoracic imaging in children with CF are lagging behind these rapid technological advances. The continued progress of personalised medicine in the form of CFTR modulators will promote the emergence of personalised radiological diagnostics.

[The contribution of artificial intelligence (AI) subsequent to the processing of thoracic imaging]

The contribution of artificial intelligence (AI) to medical imaging is currently the object of widespread experimentation. The development of deep learning (DL) methods, particularly convolution neural networks (CNNs), has led to performance gains often superior to those achieved by conventional methods such as machine learning. Radiomics is an approach aimed at extracting quantitative data not accessible to the human eye from images expressing a disease. The data subsequently feed machine learning models and produce diagnostic or prognostic probabilities. As for the multiple applications of AI methods in thoracic imaging, they are undergoing evaluation. Chest radiography is a practically ideal field for the development of DL algorithms able to automatically interpret X-rays. Current algorithms can detect up to 14 different abnormalities present either in isolation or in combination. Chest CT is another area offering numerous AI applications. Various algorithms have been specifically formed and validated for the detection and characterization of pulmonary nodules and pulmonary embolism, as well as segmentation and quantitative analysis of the extent of diffuse lung diseases (emphysema, infectious pneumonias, interstitial lung disease). In addition, the analysis of medical images can be associated with clinical, biological, and functional data (multi-omics analysis), the objective being to construct predictive approaches regarding disease prognosis and response to treatment.

Improvement in Lung Clearance Index and Chest Computed Tomography Scores with Elexacaftor/Tezacaftor/Ivacaftor Treatment in People with Cystic Fibrosis Aged 12 Years and Older - The RECOVER Trial

Rationale: Clinical trials have shown that use of elexacaftor/tezacaftor/ivacaftor (ETI) is associated with improvements in sweat chloride, pulmonary function, nutrition, and quality of life in people with cystic fibrosis (CF). Little is known about the impact of ETI on ventilation inhomogeneity and lung structure. Objectives: RECOVER is a real-world study designed to measure the impact of ETI in people with CF. The primary endpoints were lung clearance (lung clearance index; LCI2.5) and FEV1. Secondary endpoints included spirometry-controlled chest computed tomography (CT) scores. Methods: The study was conducted in seven sites in Ireland and the United Kingdom. Participants ages 12 years and older who were homozygous for the F508del mutation (F508del/F508del) or heterozygous for F508del and a minimum-function mutation (F508del/MF) were recruited before starting ETI and were followed up over 12 months. LCI2.5 was measured using nitrogen multiple breath washout (MBW) at baseline and at 6 and 12 months. Spirometry was performed as per the criteria of the American Thoracic Society and the European Respiratory Society. Spirometry-controlled chest CT scans were performed at baseline and at 12 months. CT scans were scored using the Perth Rotterdam Annotated Grid Morphometric Analysis (PRAGMA) system. Other outcome measures include weight, height, Cystic Fibrosis Quality of Life Questionnaire-Revised (CFQ-R), and sweat chloride. Measurements and Main Results: One hundred seventeen people with CF ages 12 and older were recruited to the study. Significant improvements were seen in LCI scores (-2.5; 95% confidence interval [CI], -3.0, -2.0) and in the percents predicted for FEV1 (8.9; 95% CI, 7.0, 10.9), FVC (6.6; 95% CI, 4.9, 8.3), and forced expiratory flow between 25% and 75% of expired volume (12.4; 95% CI, 7.8, 17.0). Overall PRAGMA-CF scores reflecting airway disease improved significantly (-3.46; 95% CI, -5.23, -1.69). Scores for trapped air, mucus plugging, and bronchial wall thickening improved significantly, but bronchiectasis scores did not. Sweat chloride levels decreased in both F508del/F508del (-43.1; 95% CI, -47.4, -38.9) and F508del/MF (-42.8; 95% CI, -48.5, -37.2) groups. Scores on the Respiratory Domain of the CFQ-R improved by 14.2 points (95% CI, 11.3, 17.2). At 1 year, sweat chloride levels were significantly lower for the F508del/F508del group compared with scores for the F508del/MF group (33.93 vs. 53.36, P < 0.001). Conclusions: ETI is associated with substantial improvements in LCI2.5, spirometry, and PRAGMA-CF CT scores in people with CF ages 12 years and older. ETI led to improved nutrition and quality of life. People in the F508del/F508del group had significantly lower sweat chloride on ETI treatment compared with the F508del/MF group. Clinical trial registered with www.clinicaltrials.gov (NCT04602468).

Qualitative and quantitative evaluation of computed tomography changes in adults with cystic fibrosis treated with elexacaftor-tezacaftor-ivacaftor: a retrospective observational study

Introduction: The availability of highly effective triple cystic fibrosis transmembrane conductance regulator (CFTR) modulator combination therapy with elexacaftor-tezacaftor-ivacaftor (ETI) has improved pulmonary outcomes and quality of life of people with cystic fibrosis (pwCF). The aim of this study was to assess computed tomography (CT) changes under ETI visually with the Brody score and quantitatively with dedicated software, and to correlate CT measures with parameters of clinical response. Methods: Twenty two adult pwCF with two consecutive CT scans before and after ETI treatment initiation were retrospectively included. CT was assessed visually employing the Brody score and quantitatively by YACTA, a well-evaluated scientific software computing airway dimensions and lung parenchyma with wall percentage (WP), wall thickness (WT), lumen area (LA), bronchiectasis index (BI), lung volume and mean lung density (MLD) as parameters. Changes in CT metrics were evaluated and the visual and quantitative parameters were correlated with each other and with clinical changes in sweat chloride concentration, spirometry [percent predicted of forced expiratory volume in one second (ppFEV1)] and body mass index (BMI). Results: The mean (SD) Brody score improved with ETI [55 (12) vs. 38 (15); p < 0.001], incl. sub-scores for mucus plugging, peribronchial thickening, and parenchymal changes (all p < 0.001), but not for bronchiectasis (p = 0.281). Quantitatve WP (p < 0.001) and WT (p = 0.004) were reduced, conversely LA increased (p = 0.003), and BI improved (p = 0.012). Lung volume increased (p < 0.001), and MLD decreased (p < 0.001) through a reduction of ground glass opacity areas (p < 0.001). Changes of the Brody score correlated with those of quantitative parameters, exemplarily WT with the sub-score for mucus plugging (r = 0.730, p < 0.001) and peribronchial thickening (r = 0.552, p = 0.008). Changes of CT parameters correlated with those of clinical response parameters, in particular ppFEV1 with the Brody score (r = -0.606, p = 0.003) and with WT (r = -0.538, p = 0.010). Discussion: Morphological treatment response to ETI can be assessed using the Brody score as well as quantitative CT parameters. Changes in CT correlated with clinical improvements. The quantitative analysis with YACTA proved to be an objective, reproducible and simple method for monitoring lung disease, particularly with regard to future interventional clinical trials.

Chest radiography and computed tomography imaging in cystic fibrosis: current challenges and new perspectives

Imaging plays a pivotal role in the noninvasive assessment of cystic fibrosis (CF)-related lung damage, which remains the main cause of morbidity and mortality in children with CF. The development of new imaging techniques has significantly changed clinical practice, and advances in therapies have posed diagnostic and monitoring challenges. The authors summarise these challenges and offer new perspectives in the use of imaging for children with CF for both clinicians and radiologists. This article focuses on chest radiography and CT, which are the two main radiologic techniques used in most cystic fibrosis centres. Advantages and disadvantages of radiography and CT for imaging in CF are described, with attention to new developments in these techniques, such as the use of artificial intelligence (AI) image analysis strategies to improve the sensitivity of radiography and CT and the introduction of the photon-counting detector CT scanner to increase spatial resolution at no dose expense.

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.

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.

State-of-the-art review of lung imaging in cystic fibrosis with recommendations for pulmonologists and radiologists from the "iMAging managEment of cySTic fibROsis" (MAESTRO) consortium

OBJECTIVE

Imaging represents an important noninvasive means to assess cystic fibrosis (CF) lung disease, which remains the main cause of morbidity and mortality in CF patients. While the development of new imaging techniques has revolutionised clinical practice, advances have posed diagnostic and monitoring challenges. The authors aim to summarise these challenges and make evidence-based recommendations regarding imaging assessment for both clinicians and radiologists.

STUDY DESIGN

A committee of 21 experts in CF from the 10 largest specialist centres in Italy was convened, including a radiologist and a pulmonologist from each centre, with the overall aim of developing clear and actionable recommendations for lung imaging in CF. An a priori threshold of at least 80% of the votes was required for acceptance of each statement of recommendation.

RESULTS

After a systematic review of the relevant literature, the committee convened to evaluate 167 articles. Following five RAND conferences, consensus statements were developed by an executive subcommittee. The entire consensus committee voted and approved 28 main statements.

CONCLUSIONS

There is a need for international guidelines regarding the appropriate timing and selection of imaging modality for patients with CF lung disease; timing and selection depends upon the clinical scenario, the patient's age, lung function and type of treatment. Despite its ubiquity, the use of the chest radiograph remains controversial. Both computed tomography and magnetic resonance imaging should be routinely used to monitor CF lung disease. Future studies should focus on imaging protocol harmonisation both for computed tomography and for magnetic resonance imaging. The introduction of artificial intelligence imaging analysis may further revolutionise clinical practice by providing fast and reliable quantitative outcomes to assess disease status. To date, there is no evidence supporting the use of lung ultrasound to monitor CF lung disease.

Deep Learning for the Automatic Quantification of Pleural Plaques in Asbestos-Exposed Subjects

Objective: This study aimed to develop and validate an automated artificial intelligence (AI)-driven quantification of pleural plaques in a population of retired workers previously occupationally exposed to asbestos. Methods: CT scans of former workers previously occupationally exposed to asbestos who participated in the multicenter APEXS (Asbestos PostExposure Survey) study were collected retrospectively between 2010 and 2017 during the second and the third rounds of the survey. A hundred and forty-one participants with pleural plaques identified by expert radiologists at the 2nd and the 3rd CT screenings were included. Maximum Intensity Projection (MIP) with 5 mm thickness was used to reduce the number of CT slices for manual delineation. A Deep Learning AI algorithm using 2D-convolutional neural networks was trained with 8280 images from 138 CT scans of 69 participants for the semantic labeling of Pleural Plaques (PP). In all, 2160 CT images from 36 CT scans of 18 participants were used for AI testing versus ground-truth labels (GT). The clinical validity of the method was evaluated longitudinally in 54 participants with pleural plaques. Results: The concordance correlation coefficient (CCC) between AI-driven and GT was almost perfect (>0.98) for the volume extent of both PP and calcified PP. The 2D pixel similarity overlap of AI versus GT was good (DICE = 0.63) for PP, whether they were calcified or not, and very good (DICE = 0.82) for calcified PP. A longitudinal comparison of the volumetric extent of PP showed a significant increase in PP volumes (p < 0.001) between the 2nd and the 3rd CT screenings with an average delay of 5 years. Conclusions: AI allows a fully automated volumetric quantification of pleural plaques showing volumetric progression of PP over a five-year period. The reproducible PP volume evaluation may enable further investigations for the comprehension of the unclear relationships between pleural plaques and both respiratory function and occurrence of thoracic malignancy.

Management of respiratory tract exacerbations in people with cystic fibrosis: Focus on imaging

Respiratory tract exacerbations play a crucial role in progressive lung damage of people with cystic fibrosis, representing a major determinant in the loss of functional lung tissue, quality of life and patient survival. Detection and monitoring of respiratory tract exacerbations are challenging for clinicians, since under- and over-treatment convey several risks for the patient. Although various diagnostic and monitoring tools are available, their implementation is hampered by the current definition of respiratory tract exacerbation, which lacks objective "cut-offs" for clinical and lung function parameters. In particular, the latter shows a large variability, making the current 10% change in spirometry outcomes an unreliable threshold to detect exacerbation. Moreover, spirometry cannot be reliably performed in preschool children and new emerging tools, such as the forced oscillation technique, are still complementary and need more validation. Therefore, lung imaging is a key in providing respiratory tract exacerbation-related structural and functional information. However, imaging encompasses several diagnostic options, each with different advantages and limitations; for instance, conventional chest radiography, the most used radiological technique, may lack sensitivity and specificity in respiratory tract exacerbations diagnosis. Other methods, including computed tomography, positron emission tomography and magnetic resonance imaging, are limited by either radiation safety issues or the need for anesthesia in uncooperative patients. Finally, lung ultrasound has been proposed as a safe bedside option but it is highly operator-dependent and there is no strong evidence of its possible use during respiratory tract exacerbation. This review summarizes the clinical challenges of respiratory tract exacerbations in patients with cystic fibrosis with a special focus on imaging. Firstly, the definition of respiratory tract exacerbation is examined, while diagnostic and monitoring tools are briefly described to set the scene. This is followed by advantages and disadvantages of each imaging technique, concluding with a diagnostic imaging algorithm for disease monitoring during respiratory tract exacerbation in the cystic fibrosis patient.