Quantitative CT Scan Imaging of the Airways for Diagnosis and Management of Lung Disease

Quantitative evaluation of muscle mass based on chest high-resolution CT and its prognostic value for tuberculosis: a retrospective study

Objective

This study aims to explore the prognostic value of quantitatively evaluating muscle mass using chest high resolution computed tomography (HRCT) in patients with active tuberculosis (TB).

Methods

This retrospective cohort study collected data from 309 patients with active TB diagnosed at Ningbo No.2 Hospital from 2020 to 2023. Based on the skeletal muscle index (SMI) at the T12 vertebra (with thresholds of <28.8 cm2/m2 for men and <20.8 cm2/m2 for women), patients were divided into a low muscle mass group and a normal muscle mass group. The study compared baseline characteristics, muscle mass-related indicators, body mass index (BMI), and imaging features between the two groups. The correlation between muscle mass-related indicators, BMI, and TB imaging features and prognosis was analyzed. Receiver operating characteristic (ROC) curve analysis and multivariate logistic regression were used to assess the prognostic value of muscle mass-related indicators and BMI in patients undergoing anti-TB treatment.

Results

A total of 309 patients were included in the study, divided into a normal muscle mass group (n = 229) and a low muscle mass group (n = 80). There was a significant difference in prognosis between the two groups (χ 2 test, p < 0.05). Patients in the low muscle mass group were older, had a higher proportion of males, and had a lower BMI (p < 0.05). Additionally, these patients had a higher likelihood of developing pulmonary cavities (p < 0.05). In terms of imaging features, the two groups showed significant differences in the pre-treatment proportion of pulmonary fibrotic bands, ground-glass opacities, consolidation, lesion percentage, and lesion absorption ratio (all p < 0.05). Univariate analysis indicated that both the T12 skeletal muscle index (T12 SMI) and BMI were correlated with TB imaging characteristics (p < 0.05), with T12 SMI showing a stronger correlation than BMI. Multivariable linear regression analysis revealed that after adjusting for age, gender, and T12 skeletal muscle radiation attenuation (T12 SMRA), T12 SMI remained significantly correlated with the whole-lung lesion proportion (β: - 4.56, 95% CI [-5.45 to -3.67]) and lesion absorption ratio (β:0.036, 95% CI [0.031-0.041]). Multivariable logistic regression analysis demonstrated that after accounting for age, gender, T12 SMRA, T12 SMI was significantly associated with the prognosis of TB patients (OR: 20.10, 95% CI [8.81-51.56], p < 0.05), indicating that low T12 SMI is an independent risk factor associated with poor prognosis. ROC curve analysis indicated that T12 SMI may offer advantages over BMI, with an area under the ROC curve (AUC) of T12 SMI (0.761, 95% CI [0.690-0.832]) higher than the AUC of BMI (0.700, 95% CI [0.619-0.781].

Conclusion

Quantitative evaluation of muscle mass using chest HRCT, particularly the T12 SMI, may provide valuable prognostic information for tuberculosis patients, potentially offering advantages over BMI in assessing patient outcomes.

Airway tapering in COPD

BACKGROUND

Luminal narrowing is a hallmark feature of airway remodelling in COPD, but current measures focus on airway wall remodelling. Quantification of the natural increase in cumulative cross-sectional area along the length of the human airway tree can facilitate assessment of airway narrowing.

METHODS

We analysed the airway trees of 7641 subjects enrolled in the multicentre COPDGene cohort. Airway luminal tapering was assessed by estimating the slope of the change in cumulative cross-sectional area along the length of the airway tree over successive generations (T-Slope). We performed multivariable regression analyses to test the associations between T-Slope and lung function, St George's Respiratory Questionnaire score, modified Medical Research Council dyspnoea score, 6-min walk distance (6MWD), forced expiratory volume in 1 s (FEV1) change, exacerbations and all-cause mortality after adjusting for demographics, emphysema measured as the percentage of voxels with density <-950 HU on inspiratory computed tomography scans (%CT emphysema) and total airway count.

RESULTS

The mean±sd T-Slope decreased with increasing COPD severity: 2.69±0.70 mm-1 in non-smokers and 2.33±0.70, 2.11±0.65, 1.78±0.58, 1.60±0.53 and 1.57±0.52 mm-1 in GOLD stages 0 through 4, respectively (Jonckheere-Terpstra p=0.04). On multivariable analyses, T-Slope was independently associated with FEV1 (β=0.13 (95% CI 0.10-0.15) L; p<0.001), 6MWD (β=15.0 (95% CI 10.8-19.2) m; p<0.001), change in FEV1 (β= -4.50 (95% CI -7.32- -1.67) mL·year-1; p=0.001), exacerbations (incidence risk ratio 0.78 (95% CI 0.73-0.83); p<0.001) and mortality (hazard ratio 0.79 (95% CI 0.72-0.86); p<0.001).

CONCLUSION

T-Slope is a measure of airway luminal remodelling and is associated with respiratory morbidity and mortality.

It is high time to discard a cut-off of 0.70 in the diagnosis of COPD

INTRODUCTION

Chronic obstructive pulmonary disease (COPD) has traditionally been diagnosed based on the criterion of an FEV1/FVC <0.70. However, this definition has limitations as it may only detect patients with later-stage disease, when pathologic changes have become irreversible. Consequently, it potentially omits individuals with early-stage disease, in whom the pathologic changes could be delayed or reversed.

AREAS COVERED

This narrative review summarizes recent evidence regarding early-stage COPD, which may not fulfill the spirometric criteria but nonetheless exhibits features of COPD or is at risk of future COPD progression.

EXPERT OPINION

A comprehensive approach, including symptoms assessment, various physiologic tests, and radiologic features, is required to diagnose COPD. This approach is necessary to identify currently underdiagnosed patients and to halt disease progression in at- risk patients.

Artificial intelligence-assisted quantitative CT analysis of airway changes following SABR for central lung tumors

INTRODUCTION

Use of stereotactic ablative radiotherapy (SABR) for central lung tumors can result in up to a 35% incidence of late pulmonary toxicity. We evaluated an automated scoring method to quantify post-SABR bronchial changes by using artificial intelligence (AI)-based airway segmentation.

MATERIALS AND METHODS

Central lung SABR patients treated at Amsterdam UMC (AUMC, internal reference dataset) and Peter MacCallum Cancer Centre (PMCC, external validation dataset) were identified. Patients were eligible if they had pre- and post-SABR CT scans with ≤ 1 mm resolution. The first step of the automated scoring method involved AI-based airway auto-segmentation using MEDPSeg, an end-to-end deep learning-based model. The Vascular Modeling Toolkit in 3D Slicer was then used to extract a centerline curve through the auto-segmented airway lumen, and cross-sectional measurements were computed along each bronchus for all CT scans. For AUMC patients, airway stenosis/occlusion was evaluated by both visual assessment and automated scoring. Only the automated method was applied to the PMCC dataset.

RESULTS

Study patients comprised 26 from AUMC, and 33 from PMCC. Visual scoring identified stenosis/occlusion in 8 AUMC patients (31 %), most frequently in the segmental bronchi. After airway auto-segmentation, minor manual edits were needed in 9 % of patients. Segmentation for a single scan averaged 83sec (range 73-136). Automated scoring nearly doubled detected airway stenosis/occlusion (n = 15, 58 %), and allowed for earlier detection in 5/8 patients who had also visually scored changes. Estimated rates were 48 % and 66 % at 1- and 2-years, respectively, for the internal dataset. The automated detection rate was 52 % in the external dataset, with 1- and 2-year risks of 56 % and 61 %, respectively.

CONCLUSION

An AI-based automated scoring method allows for detection of more bronchial stenosis/occlusion after lung SABR, and at an earlier time-point. This tool can facilitate studies to determine early airway changes and establish more reliable airway tolerance doses.

Predicting Acute Exacerbation Phenotype in Chronic Obstructive Pulmonary Disease Patients Using VGG-16 Deep Learning

INTRODUCTION

Exacerbations of chronic obstructive pulmonary disease (COPD) have a significant impact on hospitalizations, morbidity, and mortality of patients. This study aimed to develop a model for predicting acute exacerbation in COPD patients (AECOPD) based on deep-learning (DL) features.

METHODS

We performed a retrospective study on 219 patients with COPD who underwent inspiratory and expiratory HRCT scans. By recording the acute respiratory events of the previous year, these patients were further divided into non-AECOPD group and AECOPD group according to the presence of acute exacerbation events. Sixty-nine quantitative CT (QCT) parameters of emphysema and airway were calculated by NeuLungCARE software, and 2,000 DL features were extracted by VGG-16 method. The logistic regression method was employed to identify AECOPD patients, and 29 patients of external validation cohort were used to access the robustness of the results.

RESULTS

The model 3-B achieved an area under the receiver operating characteristic curve (AUC) of 0.933 and 0.865 in the testing cohort and external validation cohort, respectively. Model 3-I obtained AUC of 0.895 in the testing cohort and AUC of 0.774 in the external validation cohort. Model 7-B combined clinical characteristics, QCT parameters, and DL features achieved the best performance with an AUC of 0.979 in the testing cohort and demonstrating robust predictability with an AUC of 0.932 in the external validation cohort. Likewise, model 7-I achieved an AUC of 0.938 and 0.872 in the testing cohort and external validation cohort, respectively.

CONCLUSIONS

DL features extracted from HRCT scans can effectively predict acute exacerbation phenotype in COPD patients.

3D airway geometry analysis of factors in airway navigation failure for lung nodules

BACKGROUND

This study aimed to quantitatively reveal contributing factors to airway navigation failure during radial probe endobronchial ultrasound (R-EBUS) by using geometric analysis in a three-dimensional (3D) space and to investigate the clinical feasibility of prediction models for airway navigation failure.

METHODS

We retrospectively reviewed patients who underwent R-EBUS between January 2017 and December 2018. Geometric quantification was analyzed using in-house software built with open-source python libraries including the Vascular Modeling Toolkit ( http://www.vmtk.org ), simple insight toolkit ( https://sitk.org ), and sci-kit image ( https://scikit-image.org ). We used a machine learning-based approach to explore the utility of these significant factors.

RESULTS

Of the 491 patients who were eligible for analysis (mean age, 65 years +/- 11 [standard deviation]; 274 men), the target lesion was reached in 434 and was not reached in 57. Twenty-seven patients in the failure group were matched with 27 patients in the success group based on propensity scores. Bifurcation angle at the target branch, the least diameter of the last section, and the curvature of the last section are the most significant and stable factors for airway navigation failure. The support vector machine can predict airway navigation failure with an average area under the curve of 0.803.

CONCLUSIONS

Geometric analysis in 3D space revealed that a large bifurcation angle and a narrow and tortuous structure of the closest bronchus from the lesion are associated with airway navigation failure during R-EBUS. The models developed using quantitative computer tomography scan imaging show the potential to predict airway navigation failure.

Machine learning and magnetic resonance image texture analysis predicts accelerated lung function decline in ex-smokers with and without chronic obstructive pulmonary disease

Purpose

Our objective was to train machine-learning algorithms on hyperpolarizedHe 3 magnetic resonance imaging (MRI) datasets to generate models of accelerated lung function decline in participants with and without chronic-obstructive-pulmonary-disease. We hypothesized that hyperpolarized gas MRI ventilation, machine-learning, and multivariate modeling could be combined to predict clinically-relevant changes in forced expiratory volume in 1 s (FEV 1 ) across 3 years.

Approach

HyperpolarizedHe 3 MRI was acquired using a coronal Cartesian fast gradient recalled echo sequence with a partial echo and segmented using a k-means clustering algorithm. A maximum entropy mask was used to generate a region-of-interest for texture feature extraction using a custom-developed algorithm and the PyRadiomics platform. The principal component and Boruta analyses were used for feature selection. Ensemble-based and single machine-learning classifiers were evaluated using area-under-the-receiver-operator-curve and sensitivity-specificity analysis.

Results

We evaluated 88 ex-smoker participants with 31 ± 7 months follow-up data, 57 of whom (22 females/35 males, 70 ± 9 years) had negligible changes inFEV 1 and 31 participants (7 females/24 males, 68 ± 9 years) with worseningFEV 1 ≥ 60    mL / year . In addition, 3/88 ex-smokers reported a change in smoking status. We generated machine-learning models to predictFEV 1 decline using demographics, spirometry, and texture features, with the later yielding the highest classification accuracy of 81%. The combined model (trained on all available measurements) achieved the overall best classification accuracy of 82%; however, it was not significantly different from the model trained on MRI texture features alone.

Conclusion

For the first time, we have employed hyperpolarizedHe 3 MRI ventilation texture features and machine-learning to identify ex-smokers with accelerated decline inFEV 1 with 82% accuracy.