Present and future utility of computed tomography scanning in the assessment and management of COPD

Expiratory Venous Volume and Arterial Tortuosity are Associated with Disease Severity and Mortality Risk in Patients with COPD: Results from COSYCONET

Purpose

The aim of this study was to evaluate the association between computed tomography (CT) quantitative pulmonary vessel morphology and lung function, disease severity, and mortality risk in patients with chronic obstructive pulmonary disease (COPD).

Patients and Methods

Participants of the prospective nationwide COSYCONET cohort study with paired inspiratory-expiratory CT were included. Fully automatic software, developed in-house, segmented arterial and venous pulmonary vessels and quantified volume and tortuosity on inspiratory and expiratory scans. The association between vessel volume normalised to lung volume and tortuosity versus lung function (forced expiratory volume in 1 sec [FEV1]), air trapping (residual volume to total lung capacity ratio [RV/TLC]), transfer factor for carbon monoxide (TLCO), disease severity in terms of Global Initiative for Chronic Obstructive Lung Disease (GOLD) group D, and mortality were analysed by linear, logistic or Cox proportional hazard regression.

Results

Complete data were available from 138 patients (39% female, mean age 65 years). FEV1, RV/TLC and TLCO, all as % predicted, were significantly (p < 0.05 each) associated with expiratory vessel characteristics, predominantly venous volume and arterial tortuosity. Associations with inspiratory vessel characteristics were absent or negligible. The patterns were similar for relationships between GOLD D and mortality with vessel characteristics. Expiratory venous volume was an independent predictor of mortality, in addition to FEV1.

Conclusion

By using automated software in patients with COPD, clinically relevant information on pulmonary vasculature can be extracted from expiratory CT scans (although not inspiratory scans); in particular, expiratory pulmonary venous volume predicted mortality.

Trial Registration

NCT01245933.

Spatial Resolution Fidelity Comparison Between Energy Integrating and Deep Silicon Photon Counting CT: Implications for Pulmonary Imaging

PURPOSE

We investigated spatial resolution loss away from isocenter for a prototype deep silicon photon-counting detector (PCD) CT scanner and compare with a clinical energy-integrating detector (EID) CT scanner.

MATERIALS AND METHODS

We performed three scans on a wire phantom at four positions (isocenter, 6.7, 11.8, and 17.1 cm off isocenter). The acquisition modes were 120 kV EID CT, 120 kV high-definition (HD) EID CT, and 120 kV PCD CT. HD mode used double the projection view angles per rotation as the "regular" EID scan mode. The diameter of the wire was calculated by taking the full width of half max (FWHM) of a profile drawn over the radial and azimuthal directions of the wire. Change in wire diameter appearance was assessed by calculating the ratio of the radial and azimuthal diameter relative to isocenter. t tests were used to make pairwise comparisons of the wire diameter ratio with each acquisition and mean ratios' difference from unity.

RESULTS

Deep silicon PCD CT had statistically smaller (P<0.05) changes in diameter ratio for both radial and azimuthal directions compared with both regular and HD EID modes and was not statistically different from unity (P<0.05). Maximum increases in FWMH relative to isocenter were 36%, 12%, and 1% for regular EID, HD EID, and deep silicon PCD, respectively.

CONCLUSION

Deep silicon PCD CT exhibits less change in spatial resolution in both the radial and azimuthal directions compared with EID CT.

Association between the Static and Dynamic Lung Function and CT-Derived Thoracic Skeletal Muscle Measurements-A Retrospective Analysis of a 12-Month Observational Follow-Up Pilot Study

BACKGROUND

Patients with chronic obstructive pulmonary disease (COPD) with low skeletal muscle mass and severe airway obstruction have higher mortality risks. However, the relationship between dynamic/static lung function (LF) and thoracic skeletal muscle measurements (SMM) remains unclear. This study explored patient characteristics (weight, BMI, exacerbations, dynamic/static LF, sex differences in LF and SMM, and the link between LF and SMM changes.

METHODS

A retrospective analysis of a 12-month prospective follow-up study patients with stable COPD undergoing standardized treatment, covering mild to severe stages, was conducted. The baseline and follow-up assessments included computed tomography and body plethysmography.

RESULTS

This study included 35 patients (17 females and 18 males). This study revealed that females had more stable LF but tended to have greater declines in SMM areas and indices than males (-5.4% vs. -1.9%, respectively), despite the fact that females were younger and had higher LF and less exacerbation than males. A multivariate linear regression showed a negative association between the inspiratory capacity/total lung capacity ratio (IC/TLC) and muscle fat area.

CONCLUSIONS

The findings suggest distinct LF and BC progression patterns between male and female patients with COPD. A low IC/TLC ratio may predict increased muscle fat. Further studies are necessary to understand these relationships better.

Clinical evaluation of pulmonary quantitative computed tomography parameters for diagnosing eosinophilic chronic obstructive pulmonary disease: Characteristics and diagnostic performance

Aims

To investigate the characteristics and diagnostic performance of quantitative computed tomography (QCT) parameters in eosinophilic chronic obstructive pulmonary disease (COPD) patients.

Methods

High-resolution CT scans of COPD patients were retrospectively analyzed, and various emphysematous parenchyma measurements, including lung volume (LC), lung mean density (LMD), lung standard deviation (LSD), full-width half maximum (FWHM), and lung relative voxel number (LRVN) were performed. The QCT parameters were compared between eosinophilic and noneosinophilic COPD patients, using a definition of eosinophilic COPD as blood eosinophil values ≥ 300 cells·µL-1 on at least three times. Receiver operating characteristic curves and area under the curve (ROC-AUC) and python were used to evaluate discriminative efficacy of QCT.

Results

Noneosinophilic COPD patients had a significantly lower TLMD (-846.3 ± 47.9 Hounsfield Unit [HU]) and TFWHM(162.5 ± 30.6 HU) compared to eosinophilic COPD patients (-817.8 ± 54.4, 177.3 ± 33.1 HU, respectively) (p = 0.018, 0.03, respectively). Moreover, the total LC (TLC) and TLSD were significantly lower in eosinophilic COPD group (3234.4 ± 1145.8, 183.8 ± 33.9 HU, respectively) than the noneosinophilic COPD group (5600.2 ± 1248.4, 203.5 ± 20.4 HU, respectively) (p = 0.009, 0.002, respectively). The ROC-AUC values for TLC, TLMD, TLSD, and TFWHM were 0.91 (95% confidence interval [CI], 0.828-0.936), 0.66 (95% CI, 0.546-0.761), 0.64 (95% CI, 0.524-0.742), and 0.63 (95% CI, 0.511-0.731), respectively. When the TLC value was 4110 mL, the sensitivity was 90.7% (95% CI, 79.7-96.9), specificity was 77.8% (95% CI, 57.7-91.4) and accuracy was 86.4%. Notably, TLC demonstrated the highest discriminative efficiency with an F1 Score of 0.79, diagnostic Odds Ratio of 34.3 and Matthews Correlation Coefficient of 0.69, surpassing TLMD (0.55, 3.66, 0.25), TLSD (0.56, 3.95, 0.26), and TFWHM (0.56, 4.16, 0.33).

Conclusion

Eosinophilic COPD patients exhibit lower levels of emphysema and a more uniform density distribution throughout the lungs compared to noneosinophilic COPD patients. Furthermore, TLC demonstrated the highest diagnostic efficiency and may serve as a valuable diagnostic marker for distinguishing between the two groups.

First magnetic particle imaging to assess pulmonary vascular leakage in vivo in the acutely injured and fibrotic lung

Increased pulmonary vascular permeability is a characteristic feature of lung injury. However, there are no established methods that allow the three-dimensional visualization and quantification of pulmonary vascular permeability in vivo. Evans blue extravasation test and total protein test of bronchoalveolar lavage fluid (BALF) are permeability assays commonly used in research settings. However, they lack the ability to identify the spatial and temporal heterogeneity of endothelial barrier disruption, which is typical in lung injuries. Magnetic resonance (MR) and near-infrared (NIR) imaging have been proposed to image pulmonary permeability, but suffer from limited sensitivity and penetration depth, respectively. In this study, we report the first use of magnetic particle imaging (MPI) to assess pulmonary vascular leakage noninvasively in vivo in mice. A dextran-coated superparamagnetic iron oxide (SPIO), synomag®, was employed as the imaging tracer, and pulmonary SPIO extravasation was imaged and quantified to evaluate the vascular leakage. Animal models of acute lung injury and pulmonary fibrosis (PF) were used to validate the proposed method. MPI sensitively detected the SPIO extravasation in both acutely injured and fibrotic lungs in vivo, which was confirmed by ex vivo imaging and Prussian blue staining. Moreover, 3D MPI illustrated the spatial heterogeneity of vascular leakage, which correlated well with CT findings. Based on the in vivo 3D MPI images, we defined the SPIO extravasation index (SEI) to quantify the vascular leakage. A significant increase in SEI was observed in the injured lungs, in consistent with the results obtained via ex vivo permeability assays. Overall, our results demonstrate that 3D quantitative MPI serves as a useful tool to examine pulmonary vascular integrity in vivo, which shows promise for future clinical translation.

Cigarette smoking and disproportionate changes of thoracic skeletal muscles in low-dose chest computed tomography

Association between smoking intensity and the quantity and quality of thoracic skeletal muscles (TSMs) remains unexplored. Skeletal muscle index (SMI; skeletal muscle area/height2) and percentage of normal attenuation muscle area (NAMA%) were measured to represent the quantity and quality of the skeletal muscles, respectively, and quantification was performed in pectoralis muscle at aortic arch (AA-PM), TSM at carina (C-TSM), erector spinae muscle at T12 (T12-ESM), and skeletal muscle at L1 (L1-SM). Among the 258 men (median age, 62 years [IQR: 58-69]), 183 were current smokers (median smoking intensity, 40 pack-years [IQR: 30-46]). SMI and NAMA% of AA-PM significantly decreased with pack-year (β =  - 0.028 and - 0.076; P < 0.001 and P = 0.021, respectively). Smoking intensity was inversely associated with NAMA% of C-TSM (β =  - 0.063; P = 0.001), whereas smoking intensity showed a borderline association with SMI of C-TSM (β =  - 0.023; P = 0.057). Smoking intensity was associated with the change in NAMA% of L1-SM (β =  - 0.040; P = 0.027), but was not associated with SMI of L1-SM (P > 0.05). Neither NAMA% nor SMI of T12-ESM was affected by smoking intensity (P > 0.05). In conclusion, smoking intensity was associated with the change of TSMs. Its association varied according to the location of TSMs, with the most associated parts being the upper (AA-PM) and middle TSMs (C-TSM).

Lung volumes measurement using novel pressure derived method in participants with obstructive, restrictive and healthy lungs

Background.Lung volumes can be measured by body plethysmography (BP), by inert gas dilution during a single-breath or multiple breaths and by radiographic methods based on chest roentgenogram or CT scanning. Our objective was to analyze the concordance between several methods including a new pressure-derived method (PDM) in a variety of pulmonary conditions.Methods. We recruited four groups of adult volunteers at the chronic obstructive pulmonary disease and tobacco clinic of a respiratory referral hospital: patients with lung bullae, with obstructive lung diseases, with restrictive lung diseases and healthy controls; all subjects underwent lung volume measurements according to ATS/ERS standards in random order with each method and then CT scanning. Differences among groups were estimated by Kruskal-Wallis tests. Concordance correlation coefficients (CCC) and Bland-Altman plots were performed.Results. Sixty-two patients were studied including 15 with lung bullae, 14 with obstructive lung diseases, 12 with restrictive lung disease and 21 healthy subjects. Highest concordance was obtained between BP and CT scanning (CCC 0.95, mean difference -0.35 l) and the lowest, with TLC-DLCO_sb(CCC 0.65, difference -1.05 l). TLC measured by BP had a moderate concordance with the PDM (CCC = 0.91, mean difference -0.19 l). The PDM on the other hand had the lowest intra-test repeatability (2.7%) of all tested methods.Conclusions. Lung volumes measured by BP and CT had high concordance in the scenario of varied pulmonary conditions including lung bullae, restrictive and obstructive diseases. The new PDM device, had low intra-test variability, and was easy to perform, with a reasonable concordance with BP.

Preclinical MRI Using Hyperpolarized 129Xe

Although critical for development of novel therapies, understanding altered lung function in disease models is challenging because the transport and diffusion of gases over short distances, on which proper function relies, is not readily visualized. In this review we summarize progress introducing hyperpolarized ¹²⁹Xe imaging as a method to follow these processes in vivo. The work is organized in sections highlighting methods to observe the gas replacement effects of breathing (Gas Dynamics during the Breathing Cycle) and gas diffusion throughout the parenchymal airspaces (3). We then describe the spectral signatures indicative of gas dissolution and uptake (4), and how these features can be used to follow the gas as it enters the tissue and capillary bed, is taken up by hemoglobin in the red blood cells (5), re-enters the gas phase prior to exhalation (6), or is carried via the vasculature to other organs and body structures (7). We conclude with a discussion of practical imaging and spectroscopy techniques that deliver quantifiable metrics despite the small size, rapid motion and decay of signal and coherence characteristic of the magnetically inhomogeneous lung in preclinical models (8).

Early detection of COPD based on graph convolutional network and small and weakly labeled data

Chronic obstructive pulmonary disease (COPD) is a common disease with high morbidity and mortality, where early detection benefits the population. However, the early diagnosis rate of COPD is low due to the absence or slight early symptoms. In this paper, a novel method based on graph convolution network (GCN) for early detection of COPD is proposed, which uses small and weakly labeled chest computed tomography image data from the publicly available Danish Lung Cancer Screening Trial database. The key idea is to construct a graph using regions of interest randomly selected from the segmented lung parenchyma and then input it into the GCN model for COPD detection. In this way, the model can not only extract the feature information of each region of interest but also the topological structure information between regions of interest, that is, graph structure information. The proposed GCN model achieves an acceptable performance with an accuracy of 0.77 and an area under a curve of 0.81, which is higher than the previous studies on the same dataset. GCN model also outperforms several state-of-the-art methods trained at the same time. As far as we know, it is also the first time using the GCN model on this dataset for COPD detection.

Emphysema Quantification Using Ultra-Low-Dose Chest CT: Efficacy of Deep Learning-Based Image Reconstruction

Background and Objectives: Although reducing the radiation dose level is important during diagnostic computed tomography (CT) applications, effective image quality enhancement strategies are crucial to compensate for the degradation that is caused by a dose reduction. We performed this prospective study to quantify emphysema on ultra-low-dose CT images that were reconstructed using deep learning-based image reconstruction (DLIR) algorithms, and compared and evaluated the accuracies of DLIR algorithms versus standard-dose CT. Materials and Methods: A total of 32 patients were prospectively enrolled, and all underwent standard-dose and ultra-low-dose (120 kVp; CTDIvol < 0.7 mGy) chest CT scans at the same time in a single examination. A total of six image datasets (filtered back projection (FBP) for standard-dose CT, and FBP, adaptive statistical iterative reconstruction (ASIR-V) 50%, DLIR-low, DLIR-medium, DLIR-high for ultra-low-dose CT) were reconstructed for each patient. Image noise values, emphysema indices, total lung volumes, and mean lung attenuations were measured in the six image datasets and compared (one-way repeated measures ANOVA). Results: The mean effective doses for standard-dose and ultra-low-dose CT scans were 3.43 ± 0.57 mSv and 0.39 ± 0.03 mSv, respectively (p < 0.001). The total lung volume and mean lung attenuation of five image datasets of ultra-low-dose CT scans, emphysema indices of ultra-low-dose CT scans reconstructed using ASIR-V 50 or DLIR-low, and the image noise of ultra-low-dose CT scans that were reconstructed using DLIR-low were not different from those of standard-dose CT scans. Conclusions: Ultra-low-dose CT images that were reconstructed using DLIR-low were found to be useful for emphysema quantification at a radiation dose of only 11% of that required for standard-dose CT.

Performance of virtual non-contrast images generated on clinical photon-counting detector CT for emphysema quantification: proof of concept

OBJECTIVE

To evaluate the performance of virtual non-contrast images (VNC) compared to true non-contrast (TNC) images in photon-counting detector computed tomography (PCD-CT) for the evaluation of lung parenchyma and emphysema quantification.

METHODS

65 (mean age 73 years; 48 male) consecutive patients who underwent a three-phase (non-contrast, arterial and venous) chest/abdomen CT on a first-generation dual-source PCD-CT were retrospectively included. Scans were performed in the multienergy (QuantumPlus) mode at 120 kV with 70 ml intravenous contrast agent at an injection rate of 4 ml s-1. VNC were reconstructed from the arterial (VNCart) and venous phase (VNCven). TNC and VNC images of the lung were assessed quantitatively by calculating the global noise index (GNI) and qualitatively by two independent, blinded readers (overall image quality and emphysema assessment). Emphysema quantification was performed using a commercially available software tool at a threshold of -950 HU for all data sets. TNC images served as reference standard for emphysema quantification. Low attenuation values (LAV) were compared in a Bland-Altman plot.

RESULTS

GNI was similar in VNCart (103.0 ± 30.1) and VNCven (98.2 ± 22.2) as compared to TNC (100.9 ± 19.0, p = 0.546 and p = 0.272, respectively). Subjective image quality (emphysema assessment and overall image quality) was highest for TNC (p = 0.001), followed by VNCven and VNCart. Both, VNCart and VNCven showed no significant difference in emphysema quantification as compared to TNC (p = 0.409 vs. p = 0.093; respectively).

CONCLUSION

Emphysema evaluation is feasible using virtual non-contrast images from PCD-CT.

ADVANCES IN KNOWLEDGE

Emphysema quantification is feasible and accurate using VNC images in PCD-CT. Based on these findings, additional TNC scans for emphysema quantification could be omitted in the future.

A Challenge for Emphysema Quantification Using a Deep Learning Algorithm With Low-dose Chest Computed Tomography

PURPOSE

We aimed to identify clinically relevant deep learning algorithms for emphysema quantification using low-dose chest computed tomography (LDCT) through an invitation-based competition.

MATERIALS AND METHODS

The Korean Society of Imaging Informatics in Medicine (KSIIM) organized a challenge for emphysema quantification between November 24, 2020 and January 26, 2021. Seven invited research teams participated in this challenge. In total, 558 pairs of computed tomography (CT) scans (468 pairs for the training set, and 90 pairs for the test set) from 9 hospitals were collected retrospectively or prospectively. CT acquisition followed the hospitals' protocols to reflect the real-world clinical setting. Using the training set, each team developed an algorithm that generated converted LDCT by changing the pixel values of LDCT to simulate those of standard-dose CT (SDCT). The agreement between SDCT and LDCT was evaluated using the intraclass correlation coefficient (ICC; 2-way random effects, absolute agreement, and single rater) for the percentage of low-attenuated area below -950 HU (LAA-950 HU), κ value for emphysema categorization (LAA-950 HU, <5%, 5% to 10%, and ≥10%) and cosine similarity of LAA-950 HU.

RESULTS

The mean LAA-950 HU of the test set was 14.2%±10.5% for SDCT, 25.4%±10.2% for unconverted LDCT, and 12.9%±10.4%, 11.7%±10.8%, and 12.4%±10.5% for converted LDCT (top 3 teams). The agreement between the SDCT and converted LDCT of the first-place team was 0.94 (95% confidence interval: 0.90, 0.97) for ICC, 0.71 (95% confidence interval: 0.58, 0.84) for categorical agreement, and 0.97 (interquartile range: 0.94 to 0.99) for cosine similarity.

CONCLUSIONS

Emphysema quantification with LDCT was feasible through deep learning-based CT conversion strategies.

Multiple instance learning for lung pathophysiological findings detection using CT scans

Lung diseases affect the lives of billions of people worldwide, and 4 million people, each year, die prematurely due to this condition. These pathologies are characterized by specific imagiological findings in CT scans. The traditional Computer-Aided Diagnosis (CAD) approaches have been showing promising results to help clinicians; however, CADs normally consider a small part of the medical image for analysis, excluding possible relevant information for clinical evaluation. Multiple Instance Learning (MIL) approach takes into consideration different small pieces that are relevant for the final classification and creates a comprehensive analysis of pathophysiological changes. This study uses MIL-based approaches to identify the presence of lung pathophysiological findings in CT scans for the characterization of lung disease development. This work was focus on the detection of the following: Fibrosis, Emphysema, Satellite Nodules in Primary Lesion Lobe, Nodules in Contralateral Lung and Ground Glass, being Fibrosis and Emphysema the ones with more outstanding results, reaching an Area Under the Curve (AUC) of 0.89 and 0.72, respectively. Additionally, the MIL-based approach was used for EGFR mutation status prediction - the most relevant oncogene on lung cancer, with an AUC of 0.69. The results showed that this comprehensive approach can be a useful tool for lung pathophysiological characterization.

A Novel CT-Based Radiomics Features Analysis for Identification and Severity Staging of COPD

RATIONALE AND OBJECTIVES

To evaluate the role of radiomics based on Chest Computed Tomography (CT) in the identification and severity staging of chronic obstructive pulmonary disease (COPD).

MATERIALS AND METHODS

This retrospective analysis included 322 participants (249 COPD patients and 73 control subjects). In total, 1395 chest CT-based radiomics features were extracted from each participant's CT images. Three feature selection methods, including variance threshold, Select K Best method, and least absolute shrinkage and selection operator (LASSO), and two classification methods, including support vector machine (SVM) and logistic regression (LR), were used as identification and severity classification of COPD. Performance was compared by AUC, accuracy, sensitivity, specificity, precision, and F1-score.

RESULTS

38 and 10 features were selected to construct radiomics models to detect and stage COPD, respectively. For COPD identification, SVM classifier achieved AUCs of 0.992 and 0.970, while LR classifier achieved AUCs of 0.993 and 0.972 in the training set and test set, respectively. For the severity staging of COPD, the mentioned two machine learning classifiers can better differentiate less severity (GOLD1 + GOLD2) group from greater severity (GOLD3 + GOLD4) group. The AUCs of SVM and LR is 0.907 and 0.903 in the training set, and that of 0.799 and 0.797 in the test set.

CONCLUSION

The present study showed that the novel radiomics approach based on chest CT images that can be used for COPD identification and severity classification, and the constructed radiomics model demonstrated acceptable performance.

Towards Machine Learning-Aided Lung Cancer Clinical Routines: Approaches and Open Challenges

Advancements in the development of computer-aided decision (CAD) systems for clinical routines provide unquestionable benefits in connecting human medical expertise with machine intelligence, to achieve better quality healthcare. Considering the large number of incidences and mortality numbers associated with lung cancer, there is a need for the most accurate clinical procedures; thus, the possibility of using artificial intelligence (AI) tools for decision support is becoming a closer reality. At any stage of the lung cancer clinical pathway, specific obstacles are identified and "motivate" the application of innovative AI solutions. This work provides a comprehensive review of the most recent research dedicated toward the development of CAD tools using computed tomography images for lung cancer-related tasks. We discuss the major challenges and provide critical perspectives on future directions. Although we focus on lung cancer in this review, we also provide a more clear definition of the path used to integrate AI in healthcare, emphasizing fundamental research points that are crucial for overcoming current barriers.

Performance of an Artificial Intelligence-Based Platform Against Clinical Radiology Reports for the Evaluation of Noncontrast Chest CT

RATIONALE AND OBJECTIVES

Research on implementation of artificial intelligence (AI) in radiology workflows and its impact on reports remains scarce. In this study, we aim to assess if an AI platform would perform better than clinical radiology reports in evaluating noncontrast chest computed tomography (CT) scans.

MATERIALS AND METHODS

Consecutive patients who had undergone noncontrast chest CT were retrospectively identified. The radiology reports were reviewed in a binary fashion for reporting of pulmonary lesions, pulmonary emphysema, aortic dilatation, coronary artery calcifications (CAC), and vertebral compression fractures (VCF). CT scans were then processed using an AI platform. The reports' findings and the AI results were subsequently compared to a consensus read by two board-certificated radiologists as reference.

RESULTS

A total of 100 patients (mean age: 64.2 ± 14.8 years; 57% males) were included in this study. Aortic segmentation and calcium quantification failed to be processed by AI in 2 and 3 cases, respectively. AI showed superior diagnostic performance in identifying aortic dilatation (AI: sensitivity: 96.3%, specificity: 81.4%, AUC: 0.89) vs (Reports: sensitivity: 25.9%, specificity: 100%, AUC: 0.63), p <0.001; and CAC (AI: sensitivity: 89.8%, specificity: 100, AUC: 0.95) vs (Reports: sensitivity: 75.4%, specificity: 94.9%, AUC: 0.85), p = 0.005. Reports had better performance than AI in identifying pulmonary lesions (Reports: sensitivity: 97.6%, specificity: 100%, AUC: 0.99) vs (AI: sensitivity: 92.8%, specificity: 82.4%, AUC: 0.88), p = 0.024; and VCF (Reports: sensitivity:100%, specificity: 100%, AUC: 1.0) vs (AI: sensitivity: 100%, specificity: 63.7%, AUC: 0.82), p <0.001. A comparable diagnostic performance was noted in identifying pulmonary emphysema on AI (sensitivity: 80.6%, specificity: 66.7%. AUC: 0.74) and reports (sensitivity: 74.2%, specificity: 97.1%, AUC: 0.86), p = 0.064.

CONCLUSION

Our results demonstrate that incorporating AI support platforms into radiology workflows can provide significant added value to clinical radiology reporting.

Association of Total Airway Count on Computed Tomography with Pulmonary Function Decline in Early-Stage COPD: A Population-Based Prospective Cohort Study

Background

It has been found that the degree of terminal bronchiole destruction is associated with the severity of COPD. However, total airway count (TAC) of CT-visible and its relationship with COPD lung function severity and pulmonary function decline remains controversial. The present study aimed to determine whether TAC is significantly reduced in early-stage COPD (GOLD stage I–II) compared with healthy control subjects and whether TAC is associated with annual decline in pulmonary function in Chinese patients with early-stage COPD.

Methods

A total of 176 participants were enrolled in this study, of which 139 participants had undergone at least two spirometry measurements within 7 years (average 5.5 [standard deviation 0.8] years) after baseline data acquisition. CT-visible TAC was measured by summing all airway segments using semi-automated software. Average lumen diameter, average inner area, emphysema index, air trapping, and inspiratory Pi10 were also measured. Multivariable linear analysis was performed to evaluate variables that were significantly related to pulmonary function parameters and to evaluate the correlation between TAC and annual decline in longitudinal pulmonary function.

Results

Compared with healthy control subjects, CT-visible TAC was significantly reduced by 51% in GOLD II and by 31% in GOLD I after adjustment. TAC had the greatest impact on pre-bronchodilator FEV₁, pre-bronchodilator FVC, post-bronchodilator FEV₁, and post-bronchodilator FEV₁/FVC (both p<0.001) among all CT indicators measured. TAC has the best correlation with inspiratory Pi10 (ρ=−0.751, p<0.001), an evaluation indicator of the degree of airway remodeling. TAC was independently associated with annual decline in pre-bronchodilator FEV₁ (p=0.023), post-bronchodilator FEV₁ (p=0.018), and post-bronchodilator FEV₁/FVC (p<0.001).

Conclusion

This finding suggests that CT-visible TAC may be an evaluation indicator of the degree of airway remodeling, and was diminished in greater COPD lung function severity, and independently associated with disease progression. Early-stage COPD patients have already occurred lung structural changes and early intervention may be needed to ameliorate the progression of disease.

Clinical Trial Registration

ChiCTR-OO-14004264.

Early Diagnosis and Real-Time Monitoring of Regional Lung Function Changes to Prevent Chronic Obstructive Pulmonary Disease Progression to Severe Emphysema

First- and second-hand exposure to smoke or air pollutants is the primary cause of chronic obstructive pulmonary disease (COPD) pathogenesis, where genetic and age-related factors predispose the subject to the initiation and progression of obstructive lung disease. Briefly, airway inflammation, specifically bronchitis, initiates the lung disease, leading to difficulty in breathing (dyspnea) and coughing as initial symptoms, followed by air trapping and inhibition of the flow of air into the lungs due to damage to the alveoli (emphysema). In addition, mucus obstruction and impaired lung clearance mechanisms lead to recurring acute exacerbations causing progressive decline in lung function, eventually requiring lung transplant and other lifesaving interventions to prevent mortality. It is noteworthy that COPD is much more common in the population than currently diagnosed, as only 16 million adult Americans were reported to be diagnosed with COPD as of 2018, although an additional 14 million American adults were estimated to be suffering from COPD but undiagnosed by the current standard of care (SOC) diagnostic, namely the spirometry-based pulmonary function test (PFT). Thus, the main issue driving the adverse disease outcome and significant mortality for COPD is lack of timely diagnosis in the early stages of the disease. The current treatment regime for COPD emphysema is most effective when implemented early, on COPD onset, where alleviating symptoms and exacerbations with timely intervention(s) can prevent steep lung function decline(s) and disease progression to severe emphysema. Therefore, the key to efficiently combatting COPD relies on early detection. Thus, it is important to detect early regional pulmonary function and structural changes to monitor modest disease progression for implementing timely interventions and effectively eliminating emphysema progression. Currently, COPD diagnosis involves using techniques such as COPD screening questionnaires, PFT, arterial blood gas analysis, and/or lung imaging, but these modalities are limited in their capability for early diagnosis and real-time disease monitoring of regional lung function changes. Hence, promising emerging techniques, such as X-ray phase contrast, photoacoustic tomography, ultrasound computed tomography, electrical impedance tomography, the forced oscillation technique, and the impulse oscillometry system powered by robust artificial intelligence and machine learning analysis capability are emerging as novel solutions for early detection and real time monitoring of COPD progression for timely intervention. We discuss here the scope, risks, and limitations of current SOC and emerging COPD diagnostics, with perspective on novel diagnostics providing real time regional lung function monitoring, and predicting exacerbation and/or disease onset for prognosis-based timely intervention(s) to limit COPD–emphysema progression.

Similarities in Quantitative Computed Tomography Imaging of the Lung in Severe Asthma with Persistent Airflow Limitation and Chronic Obstructive Pulmonary Disease

Background: Severe asthma with persistent airflow limitation (SA-PAL) and chronic obstructive pulmonary disease (COPD) are characterised by irreversible airflow limitation and the remodelling of the airways. The phenotypes of the diseases overlap and may cause diagnostic and therapeutic concerns. Methods: There were 10 patients with SA-PAL, 11 patients with COPD, and 10 healthy volunteers (HV) enrolled in this study. The patients were examined with a 128-multislice scanner at full inspiration. Measurements were taken from the third to ninth bronchial generations. Results: The thickness of the bronchial wall was greater in the SA-PAL than in the COPD group for most bronchial generations (p < 0.05). The mean lung density was the lowest in the SA-PAL group (−846 HU), followed by the COPD group (−836 HU), with no statistical difference between these two groups. The low-attenuation volume percentage (LAV% < −950 HU) was significantly higher in the SA-PAL group (15.8%) and COPD group (10.4%) compared with the HV group (7%) (p = 0.03). Conclusion: Severe asthma with persistent airflow limitation and COPD become similar with time within the functional and morphological dimensions. Emphysema qualities are present in COPD and in SA-PAL patients.

Role of the Emphysema Index Combined with the Chronic Obstructive Pulmonary Disease Assessment Test Score in the Evaluation of Chronic Obstructive Pulmonary Disease

Background

This study aimed to evaluate the efficacy of the emphysema index (EI) in distinguishing chronic bronchitis (CB) from chronic obstructive pulmonary disease (COPD) and its role, combined with the COPD Assessment Test (CAT) score, in the evaluation of COPD.

Methods

A total of 92 patients with CB and 277 patients with COPD were enrolled in this study. Receiver operating characteristic (ROC) curves were analyzed to evaluate whether the EI can preliminarily distinguish chronic bronchitis from COPD. Considering the heterogeneity of COPD, there might be missed diagnosis of some patients with bronchitis type when differentiating COPD patients only by EI. Therefore, patients with COPD were classified according to the CAT score and EI into four groups: Group 1 (EI < 16%, CAT < 10), Group 2 (EI < 16%, CAT ≥ 10), Group 3 (EI ≥ 16%, CAT < 10), and Group 4 (EI ≥ 16%, CAT ≥ 10). The records of pulmonary function and quantitative computed tomography findings were retrospectively analyzed.

Results

ROC curve analysis showed that EI = 16.2% was the cutoff value for distinguishing COPD from CB. Groups 1 and 2 exhibited significantly higher maximal voluntary ventilation (MVV) percent predicted (pred), forced expiratory volume in 1 second (FEV1)/forced vital capacity (FVC), maximal midexpiratory flow of 25-75% pred, carbon monoxide-diffusing capacity (DLCO)/alveolar ventilation (VA), FEV1 % pred (p ≤ 0.013), and maximal expiratory flow 50% pred (all p < 0.05) than Group 4. FEV1/FVC and DLCO/VA were significantly lower in Group 3 than in Group 2 (p=0.002 and p < 0.001, respectively). The residual volume/total lung capacity was higher in Group 3 than in Groups 1 and 2 (p < 0.05).

Conclusions

The combination of EI and CAT was effective in the evaluation of COPD.

Artificial Intelligence has Similar Performance to Subjective Assessment of Emphysema Severity on Chest CT

RATIONALE AND OBJECTIVES

To compare an artificial intelligence (AI)-based prototype and subjective grading for predicting disease severity in patients with emphysema.

METHODS

Our IRB approved HIPAA-compliant study included 113 adults (71±8 years; 47 females, 66 males) who had both non-contrast chest CT and pulmonary function tests performed within a span of 2 months. The disease severity was classified based on the forced expiratory volume in 1 second (FEV1 as % of predicted) into mild, moderate, and severe. 2 thoracic radiologists (RA), blinded to the clinical and AI results, graded severity of emphysema on a 5-point scale suggested by the Fleischner Society for each lobe. The whole lung scores were derived from the summation of lobar scores. Thin-section CT images were processed with the AI-Rad Companion Chest prototype (Siemens Healthineers) to quantify low attenuation areas (LAA < - 950 HU) in whole lung and each lobe separately. Bronchial abnormality was assessed by both radiologists and a fully automated software (Philips Healthcare).

RESULTS

Both AI (AUC of 0.77; 95% CI: 0.68 - 0.85) and RA (AUC: 0.76, 95% CI: 0.65 - 0.84) emphysema quantification could differentiate mild, moderate, and severe disease based on FEV1. There was a strong positive correlation between AI and RA (r = 0.72 - 0.80; p <0.001). The combination of emphysema and bronchial abnormality quantification from radiologists' and AI assessment could differentiate between different severities with AUC of 0.80 - 0.82 and 0.87, respectively.

CONCLUSION

The assessed AI-prototypes can predict the disease severity in patients with emphysema with the same predictive value as the radiologists.

Late phase of COVID-19 pandemic in General Cardiology. A position paper of the ESC Council for Cardiology Practice

Cardiovascular (CV) engagement in coronavirus disease 2019 (COVID-19) is a huge determinant of prognosis during the acute phase of the disease. However, little is known about the potential chronic implications of the late phase of COVID-19 and about the appropriate approach to these patients. Heart failure, type 1 and type 2 myocardial infarction, arrhythmias, myocarditis, pulmonary fibrosis, and thrombosis have been shown to be related to severe acute respiratory syndrome coronavirus 2 infection, and a 'long COVID-19' illness has been recognized with fatigue, chest pain, and dyspnoea among the most frequent symptoms reported after discharge from hospital. This paper focuses on some open questions that cardiologists are going to face during the next months in a general cardiology outpatient clinic, in particular how to evaluate a 'post-COVID' patient during follow-up of CV complications of the acute phase and how to manage new CV symptoms that could be the consequence, at least in part, of heart/vessels and/or lung involvement of the previous virus infection. Present symptoms and signs, history of previous CV disease (both preceding COVID-19 and occurring during viral infection), and specific laboratory and imaging measurements during the acute phase may be of interest in focusing on how to approach the clinical evaluation of a post-COVID patient and how to integrate in our standard of care the new information on COVID-19, possibly in a multidisciplinary view. Dealing with the increased COVID-associated CV risk burden and becoming acquainted with potential new e-cardiology approaches aimed at integrating the cardiology practice are relevant new challenges brought by severe acute respiratory syndrome coronavirus 2 infection and its sequelae.

Computed tomography-identified phenotypes of small airway obstructions in chronic obstructive pulmonary disease

ABSTRACT

Chronic obstructive pulmonary disease (COPD) is a heterogeneous disease characteristic of small airway inflammation, obstruction, and emphysema. It is well known that spirometry alone cannot differentiate each separate component. Computed tomography (CT) is widely used to determine the extent of emphysema and small airway involvement in COPD. Compared with the pulmonary function test, small airway CT phenotypes can accurately reflect disease severity in patients with COPD, which is conducive to improving the prognosis of this disease. CT measurement of central airway morphology has been applied in clinical, epidemiologic, and genetic investigations as an inference of the presence and severity of small airway disease. This review will focus on presenting the current knowledge and methodologies in chest CT that aid in identifying discrete COPD phenotypes.

Difference in the airway luminal area between the standing and supine positions using upright and conventional computed tomography

No clinical studies to date have compared the airway luminal area between supine and standing positions. Our aim was therefore to compare the airway luminal area between these two positions on computed tomography (CT) and to determine its correlation with forced expiratory volume in 1 s (FEV1). Thirty-two asymptomatic volunteers underwent both conventional (supine position) and upright (standing position) CT during deep inspiration breath-holding. Pulmonary function tests were conducted on the same day. We measured the airway luminal area on CT in each position. Paired t-tests and Pearson's correlation coefficients were used for statistical analysis. The average luminal areas of the trachea, right and left main bronchi, and average third-generation airway were greater in the standing than the supine position by 3.4%, 6.1%, 5.5%, and 5.2%, respectively. The correlation coefficients between airway luminal areas and FEV1 tended to be higher in the standing than the supine position; this correlation was highest for the average third-generation airway (r = 0.70, P < 0.0001). The airway luminal areas of the trachea, bilateral main bronchi, and average third-generation airway were greater in the standing than the supine position. The average third-generation airway area in the standing position had the highest correlation with FEV1.

Bronchial Diseases are Insufficiently Defined with the Term COPD

This paper discusses the basic thoughts behind the so-called diagnosis of COPD in relation to cause and course of the disease and questions the value of this functional defined terminology. Instead, the terminology should be based on morphology in the broadest sense including all methods suitable to describe pathological processes to understand the cause of bronchial diseases. The diagnosis COPD is only helpful in relation to therapeutic measures.

Automated CT Staging of Chronic Obstructive Pulmonary Disease Severity for Predicting Disease Progression and Mortality with a Deep Learning Convolutional Neural Network

Purpose

To develop a deep learning-based algorithm to stage the severity of chronic obstructive pulmonary disease (COPD) through quantification of emphysema and air trapping on CT images and to assess the ability of the proposed stages to prognosticate 5-year progression and mortality.

Materials and Methods

In this retrospective study, an algorithm using co-registration and lung segmentation was developed in-house to automate quantification of emphysema and air trapping from inspiratory and expiratory CT images. The algorithm was then tested in a separate group of 8951 patients from the COPD Genetic Epidemiology study (date range, 2007-2017). With measurements of emphysema and air trapping, bivariable thresholds were determined to define CT stages of severity (mild, moderate, severe, and very severe) and were evaluated for their ability to prognosticate disease progression and mortality using logistic regression and Cox regression.

Results

On the basis of CT stages, the odds of disease progression were greatest among patients with very severe disease (odds ratio [OR], 2.67; 95% CI: 2.02, 3.53; P < .001) and were elevated in patients with moderate disease (OR, 1.50; 95% CI: 1.22, 1.84; P = .001). The hazard ratio of mortality for very severe disease at CT was 2.23 times the normal ratio (95% CI: 1.93, 2.58; P < .001). When combined with Global Initiative for Chronic Obstructive Lung Disease (GOLD) staging, patients with GOLD stage 2 disease had the greatest odds of disease progression when the CT stage was severe (OR, 4.48; 95% CI: 3.18, 6.31; P < .001) or very severe (OR, 4.72; 95% CI: 3.13, 7.13; P < .001).

Conclusion

Automated CT algorithms can facilitate staging of COPD severity, have diagnostic performance comparable with that of spirometric GOLD staging, and provide further prognostic value when used in conjunction with GOLD staging.Supplemental material is available for this article.© RSNA, 2021See also commentary by Kalra and Ebrahimian in this issue.

Machine Learning and Feature Selection Methods for EGFR Mutation Status Prediction in Lung Cancer

The evolution of personalized medicine has changed the therapeutic strategy from classical chemotherapy and radiotherapy to a genetic modification targeted therapy, and although biopsy is the traditional method to genetically characterize lung cancer tumor, it is an invasive and painful procedure for the patient. Nodule image features extracted from computed tomography (CT) scans have been used to create machine learning models that predict gene mutation status in a noninvasive, fast, and easy-to-use manner. However, recent studies have shown that radiomic features extracted from an extended region of interest (ROI) beyond the tumor, might be more relevant to predict the mutation status in lung cancer, and consequently may be used to significantly decrease the mortality rate of patients battling this condition. In this work, we investigated the relation between image phenotypes and the mutation status of Epidermal Growth Factor Receptor (EGFR), the most frequently mutated gene in lung cancer with several approved targeted-therapies, using radiomic features extracted from the lung containing the nodule. A variety of linear, nonlinear, and ensemble predictive classification models, along with several feature selection methods, were used to classify the binary outcome of wild-type or mutant EGFR mutation status. The results show that a comprehensive approach using a ROI that included the lung with nodule can capture relevant information and successfully predict the EGFR mutation status with increased performance compared to local nodule analyses. Linear Support Vector Machine, Elastic Net, and Logistic Regression, combined with the Principal Component Analysis feature selection method implemented with 70% of variance in the feature set, were the best-performing classifiers, reaching Area Under the Curve (AUC) values ranging from 0.725 to 0.737. This approach that exploits a holistic analysis indicates that information from more extensive regions of the lung containing the nodule allows a more complete lung cancer characterization and should be considered in future radiogenomic studies.

Correlation Between Pulmonary Sclerosing Pneumocytoma Features and MSCT Imaging Manifestations in 34 Patients: Implications for Precision Medicine

Objective: To identify and analyze the multi-slice computed tomography (MSCT) imaging manifestations and clinicopathological features of PSP to improve the preoperative and intraoperative diagnosis of the disease. Method: This was a retrospective study conducted on the imaging and clinicopathological data of the PSP patients treated in two major hospitals in China from October 2001 to December 2019. The locations of lung lesions, clinical symptoms, surgical complications, MSCT imaging features, and the corresponding relationship with clinicopathological features were assessed. Then, a new diagnostic approach was defined and used to train imaging and pathological doctors (experimental group). Then, the diagnostic accuracy of the experimental group was evaluated in preoperative and intraoperative diagnosis of PSP. Results: Thirty-four PSP cases were analyzed (mean: 51.42; range: 39-69 years old). The peripheral type was more common, while 92% of the lesions located in the middle lobe of the right lung and the lower lobe of bilateral lungs. The shortest lesion edge-pleura distance ranged 0 to 30 mm and 46% of the lesions (16/34) were attached to the pleura, 62% (21/34) located at 0-5 mm, 92% (31/34) within 20 mm from the pleura. Diameters of the lesions ranged 8.58 to 68.41 mm, while most of them were 20-40 mm. All lesions showed enhancement, and 97% (33/34) were unevenly enhanced. PSP volume was negatively correlated with the total degree of enhancement (r = -0.587, p < 0.01), and the volume difference between the obvious enhancement zone and the slight enhancement zone (r = -0.795, p < 0.01). Welt vessel sign was observed in 61.7% (21/34) of cases, and none of welt vessels entered into the lesions. Vascular-like enhancement area inside the lesion showed no significant correlation with the welt vessels outside the lesion, and no case showed entrance of bronchus into the lesion. The trained experimental group showed significantly greater diagnostic accuracy than the control group. In particular, the accuracy rate of intraoperative frozen section diagnosis was 60% higher in the experimental group than the control group. Conclusion: PSP has characteristic imaging manifestations, which can be utilized to improve the preoperative and intraoperative diagnostic coincidence rate of PSP.

Specialist respiratory outreach: a case-finding initiative for identifying undiagnosed COPD in primary care

COPD remains largely undiagnosed or is diagnosed late in the course of disease. We report findings of a specialist outreach programme to identify undiagnosed COPD in primary care. An electronic case-finding algorithm identified 1602 at-risk patients from 12 practices who were invited to attend the clinic. Three hundred and eighty-three (23.9%) responded and 288 were enrolled into the study. Forty-eight (16.6%) had undiagnosed mild and 28 (9.7%) had moderate airway obstruction, meeting spirometric diagnostic criteria for COPD. However, at 12 months only 8 suspected COPD patients (10.6%) had received a diagnostic label in their primary care record. This constituted 0.38% of the total patient population, as compared with 0.31% of control practices, p = 0.306. However, if all patients with airway obstruction received a coding of COPD, then the diagnosis rate in the intervention group would have risen by 0.84%. Despite the low take-up and diagnostic yield, this programme suggests that integrated case-finding strategies could improve COPD recognition.

Case-finding for COPD clinic acceptability to patients in GPs across Hampshire: a qualitative study

Despite high mortality and morbidity, COPD remains under-diagnosed. Case-finding strategies are possible, but patients' perspectives are unexplored. Using qualitative methods, we explored the patient perspective of a case-finding intervention among at-risk patients in primary care. Semi-structured telephone interviews were transcribed and thematic analysis utilised. Seven patients without (mean age 64.5 years (58-74), n = 4) and 8 with obstructed spirometry (mean age 63.5 (53-75), n = 4) were interviewed. Themes identified were motives, challenges and concerns regarding attending the clinic. These included wanting to be well; to help with research; concern over negative impact to life from COPD diagnosis; perceived utility of the clinic; quality of information given; staff manner, approachability and knowledge; and perceived effects of the clinic on lifestyle, self-management and symptoms. The intervention was generally deemed useful and reassuring, although shared information was too detailed or irrelevant for some. Several reported positive lifestyle changes, improved symptoms and improved self-management.

A 3D-CNN model with CT-based parametric response mapping for classifying COPD subjects

Chronic obstructive pulmonary disease (COPD) is a respiratory disorder involving abnormalities of lung parenchymal morphology with different severities. COPD is assessed by pulmonary-function tests and computed tomography-based approaches. We introduce a new classification method for COPD grouping based on deep learning and a parametric-response mapping (PRM) method. We extracted parenchymal functional variables of functional small airway disease percentage (fSAD%) and emphysema percentage (Emph%) with an image registration technique, being provided as input parameters of 3D convolutional neural network (CNN). The integrated 3D-CNN and PRM (3D-cPRM) achieved a classification accuracy of 89.3% and a sensitivity of 88.3% in five-fold cross-validation. The prediction accuracy of the proposed 3D-cPRM exceeded those of the 2D model and traditional 3D CNNs with the same neural network, and was comparable to that of 2D pretrained PRM models. We then applied a gradient-weighted class activation mapping (Grad-CAM) that highlights the key features in the CNN learning process. Most of the class-discriminative regions appeared in the upper and middle lobes of the lung, consistent with the regions of elevated fSAD% and Emph% in COPD subjects. The 3D-cPRM successfully represented the parenchymal abnormalities in COPD and matched the CT-based diagnosis of COPD.

Respiratory viral infections in the elderly

With the global over 60-year-old population predicted to more than double over the next 35 years, caring for this aging population has become a major global healthcare challenge. In 2016 there were over 1 million deaths in >70 year olds due to lower respiratory tract infections; 13-31% of these have been reported to be caused by viruses. Since then, there has been a global COVID-19 pandemic, which has caused over 2.3 million deaths so far; increased age has been shown to be the biggest risk factor for morbidity and mortality. Thus, the burden of respiratory viral infections in the elderly is becoming an increasing unmet clinical need. Particular challenges are faced due to the interplay of a variety of factors including complex multimorbidities, decreased physiological reserve and an aging immune system. Moreover, their atypical presentation of symptoms may lead to delayed necessary care, prescription of additional drugs and prolonged hospital stay. This leads to morbidity and mortality and further nosocomial spread. Clinicians currently have limited access to sensitive detection methods. Furthermore, a lack of effective antiviral treatments means there is little incentive to diagnose and record specific non-COVID-19 viral infections. To meet this unmet clinical need, it is first essential to fully understand the burden of respiratory viruses in the elderly. Doing this through prospective screening research studies for all respiratory viruses will help guide preventative policies and clinical trials for emerging therapeutics. The implementation of multiplex point-of-care diagnostics as a mainstay in all healthcare settings will be essential to understand the burden of respiratory viruses, diagnose patients and monitor outbreaks. The further development of novel targeted vaccinations as well as anti-viral therapeutics and new ways to augment the aging immune system is now also essential.The reviews of this paper are available via the supplemental material section.

Interrelationships Among Small Airways Dysfunction, Neutrophilic Inflammation, and Exacerbation Frequency in COPD

BACKGROUND

Small airways disease (SAD) is a key component of COPD and is a main contributing factor to lung function decline.

RESEARCH QUESTION

Is SAD a key feature of frequent COPD exacerbators and is this related to airway inflammation?

STUDY DESIGN AND METHODS

Thirty-nine COPD patients defined as either frequent exacerbator (FE) group (≥ 2 exacerbations/y; n = 17) and infrequent exacerbator (IFE) group (≤ 1 exacerbation/y; n = 22) underwent the forced oscillation technique (resistance at 5 Hz minus 19 Hz [R5-R19], area of reactance [AX]), multiple breath nitrogen washout (conducting airways ventilation heterogeneity, acinar ventilation heterogeneity [S_acin]), plethysmography (ratio of residual volume to total lung capacity), single-breath transfer factor of the lung for carbon monoxide, spirometry (FEV₁, FEV₁/FVC), and paired inspiratory-expiratory CT scans to ascertain SAD. A subpopulation underwent bronchoscopy to enable enumeration of BAL cell proportions.

RESULTS

S_acin was significantly higher in the COPD FE group compared with the IFE group (P = .027). In the FE group, markers of SAD were associated strongly with BAL neutrophil proportions, R5-R19 (P = .001, r = 0.795), AX (P = .049, ρ = 0.560), residual volume to total lung capacity ratio (P = .004, r = 0.730), and the mean lung density of the paired CT scans (P = .018, r = 0.639).

INTERPRETATION

Increased S_acin may be a consequence of previous exacerbations or may highlight a group of patients prone to exacerbations. Measures of SAD were associated strongly with neutrophilic inflammation in the small airways of FE patients, supporting the hypothesis that frequent exacerbations are associated with SAD related to increased cellular inflammation.

Increased chemokines levels in patients with chronic obstructive pulmonary disease: correlation with quantitative computed tomography metrics

OBJECTIVE

We sought to explore the relationships between multiple chemokines with spirometry, inflammatory mediators and CT findings of emphysema, small airways disease and bronchial wall thickness.

METHODS

All patients with COPD (n = 65) and healthy control subjects (n = 23) underwent high-resolution CT, with image analysis determining the low attenuation area (LAA), ratio of mean lung attenuation on expiratory and inspiratory scans (E/I MLD) and bronchial wall thickness of inner perimeter of a 10-mm diameter airway (Pi10). At enrollment, subjects underwent pulmonary function studies, chemokines and inflammatory mediators measurements.

RESULTS

Multiple chemokines (CCL2, CCL3, CCL5, CX3CL1, CXCL8, CXCL9, CXCL10, CXCL11 and CXCL12) and inflammatory mediators (MMP-9, MMP-12, IL-18 and neutrophil count) were markedly increased in the serum of COPD patients compared with healthy controls. There were associations between small airway disease (E/I MLD) and CCL11, CXCL8, CXCL10, CXCL11, CXCL12 and CX3CL1. Especially CXCL8 and CX3CL1 are strongly associated with E/I MLD (r = 0.74, p < 0.001; r = 0.76, p < 0.001, respectively). CXCL8, CXCL12 and CX3CL1 were moderately positively correlated with emphysema (%LAA) (r = 0.49, p < 0.05; r = 0.51, p < 0.05; r = 0.54, p < 0.01, respectively). Bronchial wall thickness (Pi10）showed no significant differences between the COPD and healthy controls,，but there was an association between Pi10 and FEV₁% in COPD patients (r=-0.420, p = 0.048). Our statistical results showed that there were not any associations between airway wall thickness (Pi10) and chemokines.

CONCLUSION

Pulmonary chemokines levels are closely associated with the extent of gas trapping, small airways disease and emphysema identified on high-resolution chest CT scan.

ADVANCES IN KNOWLEDGE

This study combines quantitative CT analysis with multiplex chemokines and inflammatory mediators to identify a new role of pathological changes in COPD.

Machine learning for lung CT texture analysis: Improvement of inter-observer agreement for radiological finding classification in patients with pulmonary diseases

PURPOSE

To evaluate the capability ML-based CT texture analysis for improving interobserver agreement and accuracy of radiological finding assessment in patients with COPD, interstitial lung diseases or infectious diseases.

MATERIALS AND METHODS

Training cases (n = 28), validation cases (n = 17) and test cases (n = 89) who underwent thin-section CT at a 320-detector row CT with wide volume scan and two 64-detector row CTs with helical scan were enrolled in this study. From 89 CT data, a total of 350 computationally selected ROI including normal lung, emphysema, nodular lesion, ground-glass opacity, reticulation and honeycomb were evaluated by three radiologists as well as by the software. Inter-observer agreements between consensus reading with and without using the software or software alone and standard references determined by consensus of pulmonologists and chest radiologists were determined using κ statistics. Overall distinguishing accuracies were compared among all methods by McNemar's test.

RESULTS

Agreements for consensus readings obtained with and without the software or the software alone with standard references were determined as significant and substantial or excellent (with the software: κ = 0.91, p < 0.0001; without the software: κ = 0.81, p < 0.0001; the software alone: κ = 0.79, p < 0.0001). Overall differentiation accuracy of consensus reading using the software (94.9 [332/350] %) was significantly higher than that of consensus reading without using the software (84.3 [295/350] %, p < 0.0001) and the software alone (82.3 [288/350] %, p < 0.0001).

CONCLUSION

ML-based CT texture analysis software has potential for improving interobserver agreement and accuracy for radiological finding assessments in patients with COPD, interstitial lung diseases or infectious diseases.

A randomised controlled feasibility trial of E-health application supported care vs usual care after exacerbation of COPD: the RESCUE trial

Exacerbations of COPD are one of the commonest causes of admission and readmission to hospital. The role of digital interventions to support self-management in improving outcomes is uncertain. We conducted an open, randomised controlled trial of a digital health platform application (app) in 41 COPD patients recruited following hospital admission with an acute exacerbation. Subjects were randomised to either receive usual care, including a written self-management plan (n = 21), or the myCOPD app (n = 20) for 90 days. The primary efficacy outcome was recovery rate of symptoms measured by COPD assessment test (CAT) score. Exacerbations, readmission, inhaler technique quality of life and patient activation (PAM) scores were also captured by a blinded team. The app was acceptable in this care setting and was used by 17 of the 20 patients with sustained use over the study period. The treatment effect on the CAT score was 4.49 (95% CI: -8.41, -0.58) points lower in the myCOPD arm. Patients' inhaler technique improved in the digital intervention arm (101 improving to 20 critical errors) compared to usual care (100 to 72 critical errors). Exacerbations tended to be less frequent in the digital arm compared to usual care; 34 vs 18 events. Hospital readmissions risk was numerically lower in the digital intervention arm: OR for readmission 0.383 (95% CI: 0.074, 1.987; n = 35). In this feasibility study of the digital self-management platform myCOPD, the app has proven acceptable to patients to use and use has improved exacerbation recovery rates, with strong signals of lower re-exacerbation and readmission rates over 90 days. myCOPD reduced the number of critical errors in inhaler technique compared to usual care with written self-management. This provides a strong basis for further exploration of the use of app interventions in the context of recently hospitalised patients with COPD and informs the potential design of a large multi-centre trial.

Using Novel Computed Tomography Analysis to Describe the Contribution and Distribution of Emphysema and Small Airways Disease in Chronic Obstructive Pulmonary Disease

Rationale: Chronic obstructive pulmonary disease (COPD) is characterized by airflow limitation, caused by emphysema and small airways disease (SAD). Computed tomography (CT) coupled with image analysis enables the quantification of these abnormalities; however, the optimum method for doing so has not been determined.Objectives: This study aims to compare two CT quantitative analysis techniques, disease probability measure (DPM) and parametric response mapping (PRM), and assess their relationship with specific physiological measures of SAD.Methods: Subjects with mild to moderate COPD, never smokers, and healthy ex-smokers were recruited. Each had airway oscillometry and multiple-breath nitrogen washout, measuring peripheral airway resistance, peripheral airway reactance, and acinar airway inhomogeneity. Subjects also had an inspiratory and expiratory chest CT, with DPM and PRM analysis performed by coregistering images and classifying each voxel as normal, emphysema, or nonemphysematous gas trapping related to SAD.Results: Thirty-eight subjects with COPD, 18 never smokers, and 23 healthy ex-smokers were recruited. There were strong associations between DPM and PRM analysis when measuring gas trapping (ρ = 0.87; P < 0.001) and emphysema (ρ = 0.99; P < 0.001). DPM assigned significantly more voxels as emphysema and gas trapped than PRM (P < 0.001). Both techniques showed significantly greater emphysema and gas trapping in subjects with COPD than in never smokers and ex-smokers (P < 0.001). All CT measures had significant associations with peripheral airway resistance and reactance, with disease probability measure of nonemphysematous gas trapping related to SAD having the strongest independent association with peripheral airway resistance (β = 0.42; P = 0.001) and peripheral airway reactance (β = 0.41; P = 0.001). Emphysema measures had the strongest associations with acinar airway inhomogeneity (β = 0.35-0.38).Conclusions: These results provide further validation for the use of DPM/PRM analysis in COPD by demonstrating significant relationships with specific physiological measures of SAD.

Objective quantitative multidetector computed tomography assessments in patients with combined pulmonary fibrosis with emphysema: Relationship with pulmonary function and clinical events

BACKGROUND

Combined pulmonary fibrosis with emphysema (CPFE) is a clinically meaningful syndrome characterized by coexisting upper-lobe emphysema and lower-lobe interstitial fibrosis. However, ambiguous diagnostic criteria and, particularly, the absence of objective methods to quantify emphysematous/fibrotic lesions in patients with CPFE confound the interpretation of the pathophysiology of this syndrome. We analyzed the relationship between objectively quantified computed tomography (CT) measurements and the results of pulmonary function testing (PFT) and clinical events in CPFE patients.

MATERIALS AND METHODS

We enrolled 46 CPFE patients who underwent CT and PFT. The extent of emphysematous lesions was obtained by calculating the percent of low attenuation area (%LAA). The extent of fibrotic lesions was calculated as the percent of high attenuation area (%HAA). %LAA and %HAA values were combined to yield the percent of abnormal area (%AA). We assessed the relationships between CT parameters and other clinical indices, including PFT results. Multivariate analysis was performed to examine the association between the CT parameters and clinical events.

RESULTS

A greater negative correlation with percent predicted diffusing capacity of the lung for carbon monoxide (DLCO %predicted) existed for %AA (r = -0.73, p < 0.001) than for %LAA or %HAA alone. The %HAA value was inversely correlated with percent predicted forced vital capacity (r = -0.48, p < 0.001), percent predicted total lung capacity (r = -0.48, p < 0.01), and DLCO %predicted (r = -0.47, p < 0.01). Multivariate logistic regression analysis found that %AA showed the strongest association with hospitalization events (odds ratio = 1.20, 95% confidence interval = 1.01-1.54, p = 0.029).

CONCLUSION

Quantitative CT measurements reflected deterioration in pulmonary function and were associated with hospitalization in patients with CPFE. This approach could serve as a useful method to determine the extent of lung morphology, pathophysiology, and the clinical course of patients with CPFE.

Patient perceived barriers to exercise and their clinical associations in difficult asthma

BACKGROUND

Exercise is recommended in guidelines for asthma management and has beneficial effects on symptom control, inflammation and lung function in patients with sub-optimally controlled asthma. Despite this, physical activity levels in patients with difficult asthma are often impaired. Understanding the barriers to exercise in people with difficult asthma is crucial for increasing their activity, and in implementing successful, disease modifying, and holistic approaches to improve their health.

METHODS

62 Patients within the WATCH Difficult Asthma Cohort (Southampton, UK) completed an Exercise Therapy Burden Questionnaire (ETBQ). The results were analyzed with contemporaneous asthma-related data to determine relationships between perceived exercise barriers and asthma and comorbidity characteristics.

RESULTS

Patients were reflective of a difficult asthma cohort, 66% were female, and 63% were atopic. They had a high BMI (median [inter-quartile range]) of 29.3 [25.5-36.2], age of 53.5 [38.75, 65.25], impaired spirometry with FEV1 73% predicted [59.5, 86.6%] and FEV/FVC ratio of 72 [56.5, 78.0] and poor symptom control, as defined by an Asthma Control Questionnaire (ACQ6) result of 2.4 [1.28, 3.2]. A high perceived barriers to exercise score was significantly correlated with increased asthma symptoms (r = 0.452, p < 0.0001), anxiety (r = 0.375, p = 0.005) and depression (r = 0.363, p = 0.008), poor quality of life (r = 0.345, p = 0.015) and number of rescue oral steroid courses in the past 12 months (r = 0.257, p = 0.048). Lung function, blood eosinophil count, FeNO, Njimegen and SNOT22 scores, BMI and hospitalisations in the previous year were not related to exercise perceptions.

CONCLUSION

In difficult asthma, perceived barriers to exercise are related to symptom burden and psychological morbidity. Therefore, exercise interventions combined with psychological input such as CBT to restructure thought processes around these perceived barriers may be useful in facilitating adoption of exercise.

Predicting and preventing hospital readmission for exacerbations of COPD

More than a third of patients hospitalised for acute exacerbation of COPD are readmitted to hospital within 90 days. Healthcare professionals and service providers are expected to collaboratively drive efforts to improve hospital readmission rates, which can be challenging due to the lack of clear consensus and guidelines on how best to predict and prevent readmissions. This review identifies these risk factors, highlighting the contribution of multimorbidity, frailty and poor socioeconomic status. Predictive models of readmission that address the multifactorial nature of readmissions and heterogeneity of the disease are reviewed, recognising that in an era of precision medicine, in-depth understanding of the intricate biological mechanisms that heighten the risk of COPD exacerbation and re-exacerbation is needed to derive modifiable biomarkers that can stratify accurately the highest risk groups for targeted treatment. We evaluate conventional and emerging strategies to reduce these potentially preventable readmissions. Here, early recognition of exacerbation symptoms and the delivery of prompt treatment can reduce risk of hospital admissions, while patient education can improve treatment adherence as a key component of self-management strategies. Care bundles are recommended to ensure high-quality care is provided consistently, but evidence for their benefit is limited to date. The search continues for interventions which are effective, sustainable and applicable to a diverse population of patients with COPD exacerbations. Further research into mechanisms that drive exacerbation and affect recovery is crucial to improve our understanding of this complex, highly prevalent disease and to advance the development of more effective treatments.

Comparison of Artificial Intelligence-Based Fully Automatic Chest CT Emphysema Quantification to Pulmonary Function Testing

OBJECTIVE. The purpose of this study was to evaluate an artificial intelligence (AI)-based prototype algorithm for fully automated quantification of emphysema on chest CT compared with pulmonary function testing (spirometry). MATERIALS AND METHODS. A total of 141 patients (72 women, mean age ± SD of 66.46 ± 9.7 years [range, 23-86 years]; 69 men, mean age of 66.72 ± 11.4 years [range, 27-91 years]) who underwent both chest CT acquisition and spirometry within 6 months were retrospectively included. The spirometry-based Tiffeneau index (TI; calculated as the ratio of forced expiratory volume in the first second to forced vital capacity) was used to measure emphysema severity; a value less than 0.7 was considered to indicate airway obstruction. Segmentation of the lung based on two different reconstruction methods was carried out by using a deep convolution image-to-image network. This multilayer convolutional neural network was combined with multilevel feature chaining and depth monitoring. To discriminate the output of the network from ground truth, an adversarial network was used during training. Emphysema was quantified using spatial filtering and attenuation-based thresholds. Emphysema quantification and TI were compared using the Spearman correlation coefficient. RESULTS. The mean TI for all patients was 0.57 ± 0.13. The mean percentages of emphysema using reconstruction methods 1 and 2 were 9.96% ± 11.87% and 8.04% ± 10.32%, respectively. AI-based emphysema quantification showed very strong correlation with TI (reconstruction method 1, ρ = -0.86; reconstruction method 2, ρ = -0.85; both p < 0.0001), indicating that AI-based emphysema quantification meaningfully reflects clinical pulmonary physiology. CONCLUSION. AI-based, fully automated emphysema quantification shows good correlation with TI, potentially contributing to an image-based diagnosis and quantification of emphysema severity.

Early COPD: current evidence for diagnosis and management

Chronic obstructive pulmonary disease (COPD) affects one-tenth of the world's population and has been identified as a major global unmet health need by the World Health Organisation, which predicts that within 10 years, COPD will become the third leading cause of death. Despite active research, there have been no recent major strides in terms of disease modifying treatment for COPD; smoking cessation remains the only intervention known to alter disease progression and improve mortality. As established COPD is a key driver of disease burden, earlier diagnosis coupled with disease-modifying intervention carries promise as a route to address this global health priority. The concept of early COPD is emerging as an area of focus for research and consideration of new treatment modalities, as it has been hypothesised that intervention at this stage may potentially halt or reverse the disease process. However, at present, a globally accepted criteria for defining early COPD does not exist. Several studies propose small airways disease as the earliest stage in the development of COPD, and this has been demonstrated to be a precursor to development of emphysema and to correlate with subsequent development of airflow obstruction. However, treatment strategies for early disease, which pre-date the development of airflow obstruction, remain uncertain. This review addresses the rationale and current evidence base for the diagnosis and treatment of early COPD and highlights the challenges of implementing trials and clinical pathways to address COPD earlier in the life course, particularly in the absence of a universally accepted definition of COPD.The reviews of this paper are available via the supplemental material section.

Predicting Pulmonary Function Testing from Quantified Computed Tomography Using Machine Learning Algorithms in Patients with COPD

Introduction: Quantitative computed tomography (qCT) is an emergent technique for diagnostics and research in patients with chronic obstructive pulmonary disease (COPD). qCT parameters demonstrate a correlation with pulmonary function tests and symptoms. However, qCT only provides anatomical, not functional, information. We evaluated five distinct, partial-machine learning-based mathematical models to predict lung function parameters from qCT values in comparison with pulmonary function tests. Methods: 75 patients with diagnosed COPD underwent body plethysmography and a dose-optimized qCT examination on a third-generation, dual-source CT with inspiration and expiration. Delta values (inspiration—expiration) were calculated afterwards. Four parameters were quantified: mean lung density, lung volume low-attenuated volume, and full width at half maximum. Five models were evaluated for best prediction: average prediction, median prediction, k-nearest neighbours (kNN), gradient boosting, and multilayer perceptron. Results: The lowest mean relative error (MRE) was calculated for the kNN model with 16%. Similar low MREs were found for polynomial regression as well as gradient boosting-based prediction. Other models led to higher MREs and thereby worse predictive performance. Beyond the sole MRE, distinct differences in prediction performance, dependent on the initial dataset (expiration, inspiration, delta), were found. Conclusion: Different, partially machine learning-based models allow the prediction of lung function values from static qCT parameters within a reasonable margin of error. Therefore, qCT parameters may contain more information than we currently utilize and can potentially augment standard functional lung testing.

Emphysema quantification using chest CT: influence of radiation dose reduction and reconstruction technique

BACKGROUND

Computed tomography (CT) emphysema quantification is affected by both radiation dose (i.e. image noise) and reconstruction technique. At reduced dose, filtered back projection (FBP) results in an overestimation of the amount of emphysema due to higher noise levels, while the use of iterative reconstruction (IR) can result in an underestimation due to reduced noise. The objective of this study was to determine the influence of dose reduction and hybrid IR (HIR) or model-based IR (MIR) on CT emphysema quantification.

METHODS

Twenty-two patients underwent inspiratory chest CT scan at routine radiation dose and at 45%, 60% and 75% reduced radiation dose. Acquisitions were reconstructed with FBP, HIR and MIR. Emphysema was quantified using the 15th percentile of the attenuation curve and the percentage of voxels below -950 HU. To determine whether the use of a different percentile or HU threshold is more accurate at reduced dose levels and with IR, additional measurements were performed using different percentiles and HU thresholds to determine the optimal combination.

RESULTS

Dose reduction resulted in a significant overestimation of emphysema, while HIR and MIR resulted in an underestimation. Lower HU thresholds with FBP at reduced dose and higher HU thresholds with HIR and MIR resulted in emphysema percentages comparable to the reference. The 15th percentile quantification method showed similar results as the HU threshold method.

CONCLUSIONS

This within-patients study showed that CT emphysema quantification is significantly affected by dose reduction and IR. This can potentially be solved by adapting commonly used thresholds.