Texture-Based Quantification of Pulmonary Emphysema on High-Resolution Computed Tomography: Comparison With Density-Based Quantification and Correlation With Pulmonary Function Test:

Clustering analysis of HRCT parameters measured using a texture-based automated system: relationship with clinical outcomes of IPF

PURPOSE

The extent of honeycombing and reticulation predict the clinical prognosis of IPF. Emphysema, consolidation, and ground glass opacity are visible in HRCT scans. To date, there have been few comprehensive studies that have used these parameters. We conducted automated quantitative analysis to identify predictive parameters for clinical outcomes and then grouped the subjects accordingly.

METHODS

CT images were obtained while patients held their breath at full inspiration. Parameters were analyzed using an automated lung texture quantification system. Cluster analysis was conducted on 159 IPF patients and clinical profiles were compared between clusters in terms of survival.

RESULTS

Kaplan-Meier analysis revealed that survival rates declined as fibrosis, reticulation, honeycombing, consolidation, and emphysema scores increased. Cox regression analysis revealed that reticulation had the most significant impact on survival rate, followed by honeycombing, consolidation, and emphysema scores. Hierarchical and K-means cluster analyses revealed 3 clusters. Cluster 1 (n = 126) with the lowest values for all parameters had the longest survival duration, and relatively-well preserved FVC and DLCO. Cluster 2 (n = 15) with high reticulation and consolidation scores had the lowest FVC and DLCO values with a predominance of female, while cluster 3 (n = 18) with high honeycombing and emphysema scores predominantly consisted of male smokers. Kaplan-Meier analysis revealed that cluster 2 had the lowest survival rate, followed by cluster 3 and cluster 1.

CONCLUSION

Automated quantitative CT analysis provides valuable information for predicting clinical outcomes, and clustering based on these parameters may help identify the high-risk group for management.

Topologic Parametric Response Mapping Identifies Tissue Subtypes Associated with Emphysema Progression

RATIONALE AND OBJECTIVES

Small airways disease (SAD) and emphysema are significant components of chronic obstructive pulmonary disease (COPD), a heterogenous disease where predicting progression is difficult. SAD, a principal cause of airflow obstruction in mild COPD, has been identified as a precursor to emphysema. Parametric Response Mapping (PRM) of chest computed tomography (CT) can help distinguish SAD from emphysema. Specifically, topologic PRM can define local patterns of both diseases to characterize how and in whom COPD progresses. We aimed to determine if distribution of CT-based PRM of functional SAD (fSAD) is associated with emphysema progression.

MATERIALS AND METHODS

We analyzed paired inspiratory-expiratory chest CT scans at baseline and 5-year follow up in 1495 COPDGene subjects using topological analyses of PRM classifications. By spatially aligning temporal scans, we mapped local emphysema at year five to baseline lobar PRM-derived topological readouts. K-means clustering was applied to all observations. Subjects were subtyped based on predominant PRM cluster assignments and assessed using non-parametric statistical tests to determine differences in PRM values, pulmonary function metrics, and clinical measures.

RESULTS

We identified distinct lobar imaging patterns and classified subjects into three radiologic subtypes: emphysema-dominant (ED), fSAD-dominant (FD), and fSAD-transition (FT: transition from healthy lung to fSAD). Relative to year five emphysema, FT showed rapid local emphysema progression (-57.5% ± 1.1) compared to FD (-49.9% ± 0.5) and ED (-33.1% ± 0.4). FT consisted primarily of at-risk subjects (roughly 60%) with normal spirometry.

CONCLUSION

The FT subtype of COPD may allow earlier identification of individuals without spirometrically-defined COPD at-risk for developing emphysema.

Severity-stratification of interstitial lung disease by deep learning enabled assessment and quantification of lesion indicators from HRCT images

BACKGROUND

Interstitial lung disease (ILD) represents a group of chronic heterogeneous diseases, and current clinical practice in assessment of ILD severity and progression mainly rely on the radiologist-based visual screening, which greatly restricts the accuracy of disease assessment due to the high inter- and intra-subjective observer variability.

OBJECTIVE

To solve these problems, in this work, we propose a deep learning driven framework that can assess and quantify lesion indicators and outcome the prediction of severity of ILD.

METHODS

In detail, we first present a convolutional neural network that can segment and quantify five types of lesions including HC, RO, GGO, CONS, and EMPH from HRCT of ILD patients, and then we conduct quantitative analysis to select the features related to ILD based on the segmented lesions and clinical data. Finally, a multivariate prediction model based on nomogram to predict the severity of ILD is established by combining multiple typical lesions.

RESULTS

Experimental results showed that three lesions of HC, RO, and GGO could accurately predict ILD staging independently or combined with other HRCT features. Based on the HRCT, the used multivariate model can achieve the highest AUC value of 0.755 for HC, and the lowest AUC value of 0.701 for RO in stage I, and obtain the highest AUC value of 0.803 for HC, and the lowest AUC value of 0.733 for RO in stage II. Additionally, our ILD scoring model could achieve an average accuracy of 0.812 (0.736 - 0.888) in predicting the severity of ILD via cross-validation.

CONCLUSIONS

In summary, our proposed method provides effective segmentation of ILD lesions by a comprehensive deep-learning approach and confirms its potential effectiveness in improving diagnostic accuracy for clinicians.

Chest MRI and CT Predictors of 10-Year All-Cause Mortality in COPD

Pulmonary imaging measurements using magnetic resonance imaging (MRI) and computed tomography (CT) have the potential to deepen our understanding of chronic obstructive pulmonary disease (COPD) by measuring airway and parenchymal pathologic information that cannot be provided by spirometry. Currently, MRI and CT measurements are not included in mortality risk predictions, diagnosis, or COPD staging. We evaluated baseline pulmonary function, MRI and CT measurements alongside imaging texture-features to predict 10-year all-cause mortality in ex-smokers with (n = 93; 31 females; 70 ± 9years) and without (n = 69; 29 females, 69 ± 9years) COPD. CT airway and vessel measurements, helium-3 (3He) MRI ventilation defect percent (VDP) and apparent diffusion coefficients (ADC) were quantified. MRI and CT texture-features were extracted using PyRadiomics (version2.2.0). Associations between 10-year all-cause mortality and all clinical and imaging measurements were evaluated using multivariable regression model odds-ratios. Machine-learning predictive models for 10-year all-cause mortality were evaluated using area-under-receiver-operator-characteristic-curve (AUC), sensitivity and specificity analyses. DLCO (%pred) (HR = 0.955, 95%CI: 0.934-0.976, p < 0.001), MRI ADC (HR = 1.843, 95%CI: 1.260-2.871, p < 0.001), and CT informational-measure-of-correlation (HR = 3.546, 95% CI: 1.660-7.573, p = 0.001) were the strongest predictors of 10-year mortality. A machine-learning model trained on clinical, imaging, and imaging textures was the best predictive model (AUC = 0.82, sensitivity = 83%, specificity = 84%) and outperformed the solely clinical model (AUC = 0.76, sensitivity = 77%, specificity = 79%). In ex-smokers, regardless of COPD status, addition of CT and MR imaging texture measurements to clinical models provided unique prognostic information of mortality risk that can allow for better clinical management.Clinical Trial Registration: www.clinicaltrials.gov NCT02279329.

CT Imaging With Machine Learning for Predicting Progression to COPD in Individuals at Risk

BACKGROUND

Identifying individuals at risk of progressing to COPD may allow for initiation of treatment to potentially slow the progression of the disease or the selection of subgroups for discovery of novel interventions.

RESEARCH QUESTION

Does the addition of CT imaging features, texture-based radiomic features, and established quantitative CT scan to conventional risk factors improve the performance for predicting progression to COPD in individuals who smoke with machine learning?

STUDY DESIGN AND METHODS

Participants at risk (individuals who currently or formerly smoked, without COPD) from the Canadian Cohort Obstructive Lung Disease (CanCOLD) population-based study underwent CT imaging at baseline and spirometry at baseline and follow-up. Various combinations of CT scan features, texture-based CT scan radiomics (n = 95), and established quantitative CT scan (n = 8), as well as demographic (n = 5) and spirometry (n = 3) measurements, with machine learning algorithms were evaluated to predict progression to COPD. Performance metrics included the area under the receiver operating characteristic curve (AUC) to evaluate the models. DeLong test was used to compare the performance of the models.

RESULTS

Among the 294 at-risk participants who were evaluated (mean age, 65.6 ± 9.2 years; 42% female; mean pack-years, 17.9 ± 18.7), 52 participants (23.7%) in the training data set and 17 participants (23.0%) in the testing data set progressed to spirometric COPD at follow-up (2.5 ± 0.9 years from baseline). Compared with machine learning models with demographics alone (AUC, 0.649), the addition of CT imaging features to demographics (AUC, 0.730; P < .05) or CT imaging features and spirometry to demographics (AUC, 0.877; P < .05) significantly improved the performance for predicting progression to COPD.

INTERPRETATION

Heterogeneous structural changes occur in the lungs of individuals at risk that can be quantified using CT imaging features, and evaluation of these features together with conventional risk factors improves performance for predicting progression to COPD.

Impact of COVID-19 pneumonia on interstitial lung disease: semi-quantitative evaluation with computed tomography

OBJECTIVES

To evaluate the CT scores and fibrotic pattern changes in interstitial lung disease (ILD) patients, with and without previous COVID-19 pneumonia.

METHODS

Patients with ILD (idiopathic pulmonary fibrosis (IPF) and connective tissue disease-associated ILD (CTD-ILD)) were retrospectively enrolled in the study which consisted of patients who had COVID-19 pneumonia while the control group had not. All patients had two CT scans, initial and follow-up, which were evaluated semi-quantitatively for severity, extent, and total CT scores, fibrosis patterns, and traction bronchiectasis.

RESULTS

A total of 102 patients (pneumonia group n = 48; control group n = 54) were enrolled in the study. For both groups, baseline characteristics were similar and CT scores were increased. While there was a 4.5 ± 4.6 point change in the total CT score of the COVID-19 group, there was a 1.2 ± 2.7 point change in the control group (p < 0.001). In the IPF subgroup, the change in total CT score was 7.0 points (95% CI: 4.1 to 9.9) in the COVID-19 group and 2.1 points (95% CI: 0.8 to 3.4) in the control group. Seven patients (14.6%) in the COVID-19 group progressed to a higher fibrosis pattern, but none in the control group.

CONCLUSIONS

Semi-quantitative chest CT scores in ILD patients demonstrated a significant increase after having COVID-19 pneumonia compared to ILD patients who had not had COVID-19 pneumonia. The increase in CT scores was more prominent in the IPF subgroup. There was also a worsening in the fibrosis pattern in the COVID-19 group.

KEY POINTS

• The impact of COVID-19 pneumonia on existing interstitial lung diseases and fibrosis is unclear. • COVID-19 pneumonia may worsen existing interstitial lung involvement with direct lung damage and indirect inflammatory effect. • COVID-19 pneumonia may affect existing lung fibrosis by triggering inflammatory pathways.

Quantitative CT parameters correlate with lung function in chronic obstructive pulmonary disease: A systematic review and meta-analysis

Objective

This study aimed to analyze the correlation between quantitative computed tomography (CT) parameters and airflow obstruction in patients with COPD.

Methods

PubMed, Embase, Cochrane and Web of Knowledge were searched by two investigators from inception to July 2022, using a combination of pertinent items to discover articles that investigated the relationship between CT measurements and lung function parameters in patients with COPD. Five reviewers independently extracted data, and evaluated it for quality and bias. The correlation coefficient was calculated, and heterogeneity was explored. The following CT measurements were extracted: percentage of lung attenuation area <-950 Hounsfield Units (HU), mean lung density, percentage of airway wall area, air trapping index, and airway wall thickness. Two airflow obstruction parameters were extracted: forced expiratory volume in the first second as a percentage of prediction (FEV₁%pred) and FEV₁ divided by forced expiratory volume lung capacity.

Results

A total of 141 studies (25,214 participants) were identified, which 64 (6,341 participants) were suitable for our meta-analysis. Results from our analysis demonstrated that there was a significant correlation between quantitative CT parameters and lung function. The absolute pooled correlation coefficients ranged from 0.26 (95% CI, 0.18 to 0.33) to 0.70 (95% CI, 0.65 to 0.75) for inspiratory CT and 0.56 (95% CI, 0.51 to 0.60) to 0.74 (95% CI, 0.68 to 0.80) for expiratory CT.

Conclusions

Results from this analysis demonstrated that quantitative CT parameters are significantly correlated with lung function in patients with COPD. With recent advances in chest CT, we can evaluate morphological features in the lungs that cannot be obtained by other clinical indices, such as pulmonary function tests. Therefore, CT can provide a quantitative method to advance the development and testing of new interventions and therapies for patients with COPD.

Impact of image pre-processing methods on computed tomography radiomics features in chronic obstructive pulmonary disease

Computed tomography (CT) imaging texture-based radiomics analysis can be used to assess chronic obstructive pulmonary disease (COPD). However, different image pre-processing methods are commonly used, and how these different methods impact radiomics features and lung disease assessment, is unknown. The purpose of this study was to develop an image pre-processing pipeline to investigate how various pre-processing combinations impact radiomics features and their use for COPD assessment. Spirometry and CT images were obtained from the multi-centered Canadian Cohort of Obstructive Lung Disease study. Participants were divided based on assessment site and were further dichotomized as No COPD or COPD within their participant groups. An image pre-processing pipeline was developed, calculating 32 grey level co-occurrence matrix radiomics features. The pipeline included lung segmentation, airway segmentation or no segmentation, image resampling or no resampling, and either no pre-processing, binning, edgmentation, or thresholding pre-processing techniques. A three-way analysis of variance was used for method comparison. A nested 10-fold cross validation using logistic regression and multiple linear regression models were constructed to classify COPD and assess correlation with lung function, respectively. Logistic regression performance was evaluated using the area under the receiver operating characteristic curve (AUC). A total of 1210 participants (Sites 1-8: No COPD:n = 447, COPD:n = 413; and Site 9: No COPD:n = 155, COPD:n = 195) were evaluated. Between the two participant groups, at least 16/32 features were different between airway segmentation/no segmentation (P ≤ 0.04), at least 29/32 features were different between no resampling/resampling (P ≤ 0.04), and 32/32 features were different between the pre-processing techniques (P < 0.0001). Features generated using the resampling/edgmentation and resampling/thresholding pre-processing combinations, regardless of airway segmentation, performed the best in COPD classification (AUC ≥ 0.718), and explained the most variance with lung function (R² ≥ 0.353). Therefore, the image pre-processing methods completed prior to CT radiomics feature extraction significantly impacted extracted features and their ability to assess COPD.

New Method for Combined Quantitative Assessment of Air-Trapping and Emphysema on Chest Computed Tomography in Chronic Obstructive Pulmonary Disease: Comparison with Parametric Response Mapping

Objective

Emphysema and small-airway disease are the two major components of chronic obstructive pulmonary disease (COPD). We propose a novel method of quantitative computed tomography (CT) emphysema air-trapping composite (EAtC) mapping to assess each COPD component. We analyzed the potential use of this method for assessing lung function in patients with COPD.

Materials and Methods

A total of 584 patients with COPD underwent inspiration and expiration CTs. Using pairwise analysis of inspiration and expiration CTs with non-rigid registration, EAtC mapping classified lung parenchyma into three areas: Normal, functional air trapping (fAT), and emphysema (Emph). We defined fAT as the area with a density change of less than 60 Hounsfield units (HU) between inspiration and expiration CTs among areas with a density less than −856 HU on inspiration CT. The volume fraction of each area was compared with clinical parameters and pulmonary function tests (PFTs). The results were compared with those of parametric response mapping (PRM) analysis.

Results

The relative volumes of the EAtC classes differed according to the Global Initiative for Chronic Obstructive Lung Disease stages (p < 0.001). Each class showed moderate correlations with forced expiratory volume in 1 second (FEV₁) and FEV₁/forced vital capacity (FVC) (r = −0.659–0.674, p < 0.001). Both fAT and Emph were significant predictors of FEV₁ and FEV₁/FVC (R² = 0.352 and 0.488, respectively; p < 0.001). fAT was a significant predictor of mean forced expiratory flow between 25% and 75% and residual volume/total vital capacity (R² = 0.264 and 0.233, respectively; p < 0.001), while Emph and age were significant predictors of carbon monoxide diffusing capacity (R² = 0.303; p < 0.001). fAT showed better correlations with PFTs than with small-airway disease on PRM.

Conclusion

The proposed quantitative CT EAtC mapping provides comprehensive lung functional information on each disease component of COPD, which may serve as an imaging biomarker of lung function.

Unraveling the interplay of image formation, data representation and learning in CT-based COPD phenotyping automation: The need for a meta-strategy

PURPOSE

In the literature on automated phenotyping of chronic obstructive pulmonary disease (COPD), there is a multitude of isolated classical machine learning and deep learning techniques, mostly investigating individual phenotypes, with small study cohorts and heterogeneous meta-parameters, e.g., different scan protocols or segmented regions. The objective is to compare the impact of different experimental setups, i.e., varying meta-parameters related to image formation and data representation, with the impact of the learning technique for subtyping automation for a variety of phenotypes. The identified associations of these parameters with automation performance and their interactions might be a first step towards a determination of optimal meta-parameters, i.e., a meta-strategy.

METHODS

A clinical cohort of 981 patients (53.8 ± 15.1 years, 554 male) was examined. The inspiratory CT images were analyzed to automate the diagnosis of 13 COPD phenotypes given by two radiologists. A benchmark feature set that integrates many quantitative criteria was extracted from the lung and trained a variety of learning algorithms on the first 654 patients (two thirds) and the respective algorithm retrospectively assessed the remaining 327 patients (one third). The automation performance was evaluated by the area under the receiver operating characteristic curve (AUC). 1717 experiments were conducted with varying meta-parameters such as reconstruction kernel, segmented regions and input dimensionality, i.e., number of extracted features. The association of the meta-parameters with the automation performance was analyzed by multivariable general linear model decomposition of the automation performance in the contributions of meta-parameters and the learning technique.

RESULTS

The automation performance varied strongly for varying meta-parameters. For emphysema-predominant phenotypes, an AUC of 93%-95% could be achieved for the best meta-configuration. The airways-predominant phenotypes led to a lower performance of 65%-85%, while smooth kernel configurations on average were unexpectedly superior to those with sharp kernels. The performance impact of meta-parameters, even that of often neglected ones like the missing-data imputation, was in general larger than that of the learning technique. Advanced learning techniques like 3D deep learning or automated machine learning yielded inferior automation performance for non-optimal meta-configurations in comparison to simple techniques with suitable meta-configurations. The best automation performance was achieved by a combination of modern learning techniques and a suitable meta-configuration.

CONCLUSIONS

Our results indicate that for COPD phenotype automation, study design parameters such as reconstruction kernel and the model input dimensionality should be adapted to the learning technique and may be more important than the technique itself. To achieve optimal automation and prediction results, the interaction between input those meta-parameters and the learning technique should be considered. This might be particularly relevant for the development of specific scan protocols for novel learning algorithms, and towards an understanding of good study design for automated phenotyping.

Classification of CT Scan Images of Lungs Using Deep Convolutional Neural Network with External Shape-Based Features

In this paper, a simplified yet efficient architecture of a deep convolutional neural network is presented for lung image classification. The images used for classification are computed tomography (CT) scan images obtained from two scientifically used databases available publicly. Six external shape-based features, viz. solidity, circularity, discrete Fourier transform of radial length (RL) function, histogram of oriented gradient (HOG), moment, and histogram of active contour image, have also been identified and embedded into the proposed convolutional neural network. The performance is measured in terms of average recall and average precision values and compared with six similar methods for biomedical image classification. The average precision obtained for the proposed system is found to be 95.26% and the average recall value is found to be 69.56% in average for the two databases.

Semi-Supervised Learning for Semantic Segmentation of Emphysema With Partial Annotations

Segmentation and quantification of each subtype of emphysema is helpful to monitor chronic obstructive pulmonary disease. Due to the nature of emphysema (diffuse pulmonary disease), it is very difficult for experts to allocate semantic labels to every pixel in the CT images. In practice, partially annotating is a better choice for the radiologists to reduce their workloads. In this paper, we propose a new end-to-end trainable semi-supervised framework for semantic segmentation of emphysema with partial annotations, in which a segmentation network is trained from both annotated and unannotated areas. In addition, we present a new loss function, referred to as Fisher loss, to enhance the discriminative power of the model and successfully integrate it into our proposed framework. Our experimental results show that the proposed methods have superior performance over the baseline supervised approach (trained with only annotated areas) and outperform the state-of-the-art methods for emphysema segmentation.

Diagnostic performance of machine learning applied to texture analysis-derived features for breast lesion characterisation at automated breast ultrasound: a pilot study

Background

Our aims were to determine if features derived from texture analysis (TA) can distinguish normal, benign, and malignant tissue on automated breast ultrasound (ABUS); to evaluate whether machine learning (ML) applied to TA can categorise ABUS findings; and to compare ML to the analysis of single texture features for lesion classification.

Methods

This ethically approved retrospective pilot study included 54 women with benign (n = 38) and malignant (n = 32) solid breast lesions who underwent ABUS. After manual region of interest placement along the lesions’ margin as well as the surrounding fat and glandular breast tissue, 47 texture features (TFs) were calculated for each category. Statistical analysis (ANOVA) and a support vector machine (SVM) algorithm were applied to the texture feature to evaluate the accuracy in distinguishing (i) lesions versus normal tissue and (ii) benign versus malignant lesions.

Results

Skewness and kurtosis were the only TF significantly different among all the four categories (p < 0.000001). In subsets (i) and (ii), a maximum area under the curve of 0.86 (95% confidence interval [CI] 0.82–0.88) for energy and 0.86 (95% CI 0.82–0.89) for entropy were obtained. Using the SVM algorithm, a maximum area under the curve of 0.98 for both subsets was obtained with a maximum accuracy of 94.4% in subset (i) and 90.7% in subset (ii).

Conclusions

TA in combination with ML might represent a useful diagnostic tool in the evaluation of breast imaging findings in ABUS. Applying ML techniques to TFs might be superior compared to the analysis of single TF.

Electronic supplementary material

The online version of this article (10.1186/s41747-019-0121-6) contains supplementary material, which is available to authorized users.

Comparison of Shallow and Deep Learning Methods on Classifying the Regional Pattern of Diffuse Lung Disease

This study aimed to compare shallow and deep learning of classifying the patterns of interstitial lung diseases (ILDs). Using high-resolution computed tomography images, two experienced radiologists marked 1200 regions of interest (ROIs), in which 600 ROIs were each acquired using a GE or Siemens scanner and each group of 600 ROIs consisted of 100 ROIs for subregions that included normal and five regional pulmonary disease patterns (ground-glass opacity, consolidation, reticular opacity, emphysema, and honeycombing). We employed the convolution neural network (CNN) with six learnable layers that consisted of four convolution layers and two fully connected layers. The classification results were compared with the results classified by a shallow learning of a support vector machine (SVM). The CNN classifier showed significantly better performance for accuracy compared with that of the SVM classifier by 6-9%. As the convolution layer increases, the classification accuracy of the CNN showed better performance from 81.27 to 95.12%. Especially in the cases showing pathological ambiguity such as between normal and emphysema cases or between honeycombing and reticular opacity cases, the increment of the convolution layer greatly drops the misclassification rate between each case. Conclusively, the CNN classifier showed significantly greater accuracy than the SVM classifier, and the results implied structural characteristics that are inherent to the specific ILD patterns.

Chronic Obstructive Pulmonary Disease: Thoracic CT Texture Analysis and Machine Learning to Predict Pulmonary Ventilation

Background Fixed airflow limitation and ventilation heterogeneity are common in chronic obstructive pulmonary disease (COPD). Conventional noncontrast CT provides airway and parenchymal measurements but cannot be used to directly determine lung function. Purpose To develop, train, and test a CT texture analysis and machine-learning algorithm to predict lung ventilation heterogeneity in participants with COPD. Materials and Methods In this prospective study (ClinicalTrials.gov: NCT02723474; conducted from January 2010 to February 2017), participants were randomized to optimization (n = 1), training (n = 67), and testing (n = 27) data sets. Hyperpolarized (HP) helium 3 (³He) MRI ventilation maps were co-registered with thoracic CT to provide ground truth labels, and 87 quantitative imaging features were extracted and normalized to lung averages to generate 174 features. The volume-of-interest dimension and the training data sampling method were optimized to maximize the area under the receiver operating characteristic curve (AUC). Forward feature selection was performed to reduce the number of features; logistic regression, linear support vector machine, and quadratic support vector machine classifiers were trained through fivefold cross validation. The highest-performing classification model was applied to the test data set. Pearson coefficients were used to determine the relationships between the model, MRI, and pulmonary function measurements. Results The quadratic support vector machine performed best in training and was applied to the test data set. Model-predicted ventilation maps had an accuracy of 88% (95% confidence interval [CI]: 88%, 88%) and an AUC of 0.82 (95% CI: 0.82, 0.83) when the HP ³He MRI ventilation maps were used as the reference standard. Model-predicted ventilation defect percentage (VDP) was correlated with VDP at HP ³He MRI (r = 0.90, P < .001). Both model-predicted and HP ³He MRI VDP were correlated with forced expiratory volume in 1 second (FEV₁) (model: r = -0.65, P < .001; MRI: r = -0.70, P < .001), ratio of FEV₁ to forced vital capacity (model: r = -0.73, P < .001; MRI: r = -0.75, P < .001), diffusing capacity (model: r = -0.69, P < .001; MRI: r = -0.65, P < .001), and quality-of-life score (model: r = 0.59, P = .001; MRI: r = 0.65, P < .001). Conclusion Model-predicted ventilation maps generated by using CT textures and machine learning were correlated with MRI ventilation maps (r = 0.90, P < .001). © RSNA, 2019 Online supplemental material is available for this article. See also the editorial by Fain in this issue.

Potential role of CT-textural features for differentiation between viral interstitial pneumonias, pneumocystis jirovecii pneumonia and diffuse alveolar hemorrhage in early stages of disease: a proof of principle

Background

Pulmonary involvement is common in several infectious and non-infectious diagnostic settings. Imaging findings consistently overlap and are therefore difficult to differentiate by chest-CT. The aim of this study was to evaluate the role of CT-textural features(CTTA) for discrimination between atypical viral (respiratory-syncitial-virus(RSV) and herpes-simplex-1-virus (HSV1)), fungal (pneumocystis-jirovecii-pneumonia(PJP)) interstitial pneumonias and alveolar hemorrhage.

Methods

By retrospective single-centre analysis we identified 46 consecutive patients (29 m) with RSV(n = 5), HSV1(n = 6), PJP(n = 21) and lung hemorrhage(n = 14) who underwent unenhanced chest CTs in early stages of the disease between 01/2016 and 02/2017. All cases were confirmed by microbiologic direct analysis of bronchial lavage. On chest-CT-scans, the presence of imaging features like ground-glass opacity(GGO), crazy-paving, air-space consolidation, reticulation, bronchial wall thickening and centrilobular nodules were described. A representative large area was chosen in both lungs and used for CTTA-parameters (included heterogeneity, intensity, average, deviation, skewness).

Results

Discriminatory CTTA-features were found between alveolar hemorrhage and PJP consisting of differences in mean heterogeneity(p < 0.015) and uniformity of skewness(p < 0.006). There was no difference between CT-textural features of diffuse alveolar hemorrhage and viral pneumonia or PJP and viral pneumonia. Visual HRCT-assessment yielded great overlap of imaging findings with predominance of GGO for PJP and airspace consolidation for pneumonia/alveolar hemorrhage. Significant correlations between HRCT-based imaging findings and CT-textural features were found for all three disease groups.

Conclusion

CT-textural features showed significant differences in mean heterogeneity and uniformity of skewness. HRCT-based imaging findings correlated with certain CT-textural features showing that the latter have the potential to characterize structural properties of lung parenchyma and related abnormalities.

Electronic supplementary material

The online version of this article (10.1186/s12880-019-0338-0) contains supplementary material, which is available to authorized users.

Machine Learning for Diagnosis of Hematologic Diseases in Magnetic Resonance Imaging of Lumbar Spines

We aimed to assess feasibility of a support vector machine (SVM) texture classifier to discriminate pathologic infiltration patterns from the normal bone marrows in MRI. This retrospective study included 467 cases, which were split into a training (n = 360) and a test set (n = 107). A sagittal T1-weighted lumbar spinal MR image was normalized by an intervertebral disk, and bone marrows were segmented. The various kernel functions and SVM input dimensions were experimented to construct the most optimal classifier model. The accuracy and sensitivity increased as the number of training set sizes increased from 180 to 360. The test set was analyzed by SVM and two independent readers, and the accuracy and sensitivity of the SVM classifier, reader 1 and reader 2 were 82.2% and 85.5%, 79.4% and 82.3%, and 82.2% and 83.9%, respectively. The area under receiver operating characteristic curve (AUC) of the SVM classifier, reader 1 and reader 2 were 0.895, 0.879 and 0.880, respectively. The SVM texture classifier produced comparable performance to radiologists in isolating the hematologic diseases, which could support inexperienced physicians with spinal MRI to screen patients with marrow diseases, who need further diagnostic work-ups to make final decisions.

Automatic emphysema detection using weakly labeled HRCT lung images

PURPOSE

A method for automatically quantifying emphysema regions using High-Resolution Computed Tomography (HRCT) scans of patients with chronic obstructive pulmonary disease (COPD) that does not require manually annotated scans for training is presented.

METHODS

HRCT scans of controls and of COPD patients with diverse disease severity are acquired at two different centers. Textural features from co-occurrence matrices and Gaussian filter banks are used to characterize the lung parenchyma in the scans. Two robust versions of multiple instance learning (MIL) classifiers that can handle weakly labeled data, miSVM and MILES, are investigated. Weak labels give information relative to the emphysema without indicating the location of the lesions. The classifiers are trained with the weak labels extracted from the forced expiratory volume in one minute (FEV1) and diffusing capacity of the lungs for carbon monoxide (DLCO). At test time, the classifiers output a patient label indicating overall COPD diagnosis and local labels indicating the presence of emphysema. The classifier performance is compared with manual annotations made by two radiologists, a classical density based method, and pulmonary function tests (PFTs).

RESULTS

The miSVM classifier performed better than MILES on both patient and emphysema classification. The classifier has a stronger correlation with PFT than the density based method, the percentage of emphysema in the intersection of annotations from both radiologists, and the percentage of emphysema annotated by one of the radiologists. The correlation between the classifier and the PFT is only outperformed by the second radiologist.

CONCLUSIONS

The presented method uses MIL classifiers to automatically identify emphysema regions in HRCT scans. Furthermore, this approach has been demonstrated to correlate better with DLCO than a classical density based method or a radiologist, which is known to be affected in emphysema. Therefore, it is relevant to facilitate assessment of emphysema and to reduce inter-observer variability.

EMPHYSEMA CLASSIFICATION USING A MULTI-VIEW CONVOLUTIONAL NETWORK

In this article we propose and validate a fully automatic tool for emphysema classification in Computed Tomography (CT) images. We hypothesize that a relatively simple Convolutional Neural Network (CNN) architecture can learn even better discriminative features from the input data compared with more complex and deeper architectures. The proposed architecture is comprised of only 4 convolutional and 3 pooling layers, where the input corresponds to a 2.5D multiview representation of the pulmonary segment tissue to classify, corresponding to axial, sagittal and coronal views. The proposed architecture is compared to similar 2D CNN and 3D CNN, and to more complex architectures which involve a larger number of parameters (up to six times larger). This method has been evaluated in 1553 tissue samples, and achieves an overall sensitivity of 81.78 % and a specificity of 97.34%, and results show that the proposed method outperforms deeper state-of-the-art architectures particularly designed for lung pattern classification. The method shows satisfactory results in full-lung classification.

Chest CT texture analysis for response assessment in systemic sclerosis

PURPOSE

To evaluate the role of CT-textural features for monitoring lung involvement in subjects with systemic sclerosis(SSc) undergoing autologous stem cell transplantation(SCT) by comparison with semi-quantitative chest-CT, pulmonary function tests(PFT) and clinical parameters (modified Rodnan skin score[mRSS]).

METHODS

In a retrospective single centre analysis, we identified 23 consecutive subjects(11male) with SSc between 07/2005 and 11/2016 that underwent chest CTs before, 6 and 12 months post-SCT. Response to therapy was defined at 6 months after transplantation as stabilisation or improvement in FVC > 10% and DLCO_SB > 10%. CT-texture analysis(CTTA) including mean, entropy and uniformity were calculated.

RESULTS

PFT classified the subjects into responders(18/23;78%) and non-responders(5/23;22%). mRSS improved in responders from 28.46 ± 9.53 to 15.70 ± 10.07 6 months after auto-SCT(p = .001) whereas in non-responders no significant improvement was registered. Fibrosis score increased significantly(mean2.33 ± 1.23 vs.1.41 ± 0.78; p = .005) in non-responders after 6 and 12months. Significant lower mean intensity and entropy of skewness and higher uniformity of skewness was found in responders vs. non-responders at baseline. Significant changes in CTTA-parameters were found in both responders and non-responders at 6months and only in responders also at 12months post-SCT.

CONCLUSIONS

Changes in CT-textural features after SCT are associated with visual CT evaluation of SSc-related lung abnormalities, but complementary provide information about therapy-induced, structural pulmonary changes.

CT Texture Analysis: Definitions, Applications, Biologic Correlates, and Challenges

This review discusses potential oncologic and nononcologic applications of CT texture analysis ( CTTA CT texture analysis ), an emerging area of "radiomics" that extracts, analyzes, and interprets quantitative imaging features. CTTA CT texture analysis allows objective assessment of lesion and organ heterogeneity beyond what is possible with subjective visual interpretation and may reflect information about the tissue microenvironment. CTTA CT texture analysis has shown promise in lesion characterization, such as differentiating benign from malignant or more biologically aggressive lesions. Pretreatment CT texture features are associated with histopathologic correlates such as tumor grade, tumor cellular processes such as hypoxia or angiogenesis, and genetic features such as KRAS or epidermal growth factor receptor (EGFR) mutation status. In addition, and likely as a result, these CT texture features have been linked to prognosis and clinical outcomes in some tumor types. CTTA CT texture analysis has also been used to assess response to therapy, with decreases in tumor heterogeneity generally associated with pathologic response and improved outcomes. A variety of nononcologic applications of CTTA CT texture analysis are emerging, particularly quantifying fibrosis in the liver and lung. Although CTTA CT texture analysis seems to be a promising imaging biomarker, there is marked variability in methods, parameters reported, and strength of associations with biologic correlates. Before CTTA CT texture analysis can be considered for widespread clinical implementation, standardization of tumor segmentation and measurement techniques, image filtration and postprocessing techniques, and methods for mathematically handling multiple tumors and time points is needed, in addition to identification of key texture parameters among hundreds of potential candidates, continued investigation and external validation of histopathologic correlates, and structured reporting of findings. ^©RSNA, 2017.

Transfer Learning for Multicenter Classification of Chronic Obstructive Pulmonary Disease

Chronic obstructive pulmonary disease (COPD) is a lung disease that can be quantified using chest computed tomography scans. Recent studies have shown that COPD can be automatically diagnosed using weakly supervised learning of intensity and texture distributions. However, up till now such classifiers have only been evaluated on scans from a single domain, and it is unclear whether they would generalize across domains, such as different scanners or scanning protocols. To address this problem, we investigate classification of COPD in a multicenter dataset with a total of 803 scans from three different centers, four different scanners, with heterogenous subject distributions. Our method is based on Gaussian texture features, and a weighted logistic classifier, which increases the weights of samples similar to the test data. We show that Gaussian texture features outperform intensity features previously used in multicenter classification tasks. We also show that a weighting strategy based on a classifier that is trained to discriminate between scans from different domains can further improve the results. To encourage further research into transfer learning methods for the classification of COPD, upon acceptance of this paper we will release two feature datasets used in this study on http://bigr.nl/research/projects/copd.

Multivariate modeling using quantitative CT metrics may improve accuracy of diagnosis of bronchiolitis obliterans syndrome after lung transplantation

BACKGROUND

To assess how quantitative CT (qCT) metrics compare to pulmonary function testing (PFT) and semi-quantitative image scores (SQS) to diagnose bronchiolitis obliterans syndrome (BOS), manifestation of chronic lung allograft dysfunction after lung transplantation (LTx), according to the type of LTx (unilateral or bilateral).

METHODS

Paired inspiratory-expiratory CT scans and PFTs of 176 LTx patients were analyzed retrospectively, and separated into BOS (78) and non-BOS (98) cohorts. SQS were assessed by 2 radiologists and graded (0-3) for features including mosaic attenuation and bronchiectasis. qCT metrics included lung volumes and air trapping volumes. Multivariate logistic regression (MVLR) and support vector machines (SVM) were used for the classification task.

RESULTS

MVLR and SVM models using PFT metrics demonstrated highest accuracy for bilateral LTx (max AUC 0.771), whereas models using qCT metrics-only outperformed models using SQS or PFTs in unilateral LTx (max AUC 0.817), to diagnose BOS. Adding PC (principal components) from qCT on top of PFT improved model diagnostic accuracy for all transplant types.

CONCLUSIONS

Combinations of qCT metrics augment the diagnostic performance of PFTs, are superior to SQS to predict BOS status, and outperform PFTs in the unilateral LTx group. This suggests that latent information on paired volumetric CT may allow early diagnosis of BOS in LTx patients, particularly in unilateral LTx.

Asynchrony in respiratory movements between the pulmonary lobes in patients with COPD: continuous measurement of lung density by 4-dimensional dynamic-ventilation CT

Purpose

Four-dimensional dynamic-ventilation CT imaging demonstrates continuous movement of the lung. The aim of this study was to assess the correlation between interlobar synchrony in lung density and spirometric values in COPD patients and smokers, by measuring the continuous changes in lung density during respiration on the dynamic-ventilation CT.

Materials and methods

Thirty-two smokers, including ten with COPD, underwent dynamic-ventilation CT during free breathing. CT data were continuously reconstructed every 0.5 sec. Mean lung density (MLD) of the five lobes (right upper [RU], right middle [RM], right lower [RL], left upper [LU], and left lower [LL]) was continuously measured by commercially available software using a fixed volume of volume of interest which was placed and tracked on a single designated point in each lobe. Concordance between the MLD time curves of six pairs of lung lobes (RU-RL, RU-RM, RM-RL, LU-LL, RU-LU, and RL-LL lobes) was expressed by cross-correlation coefficients. The relationship between these cross-correlation coefficients and the forced expiratory volume in one second/forced vital capacity (FEV_1.0/FVC) values was assessed by Spearman rank correlation analysis.

Results

In all six pairs of the pulmonary lobes, the cross-correlation coefficients of the two MLD curves were significantly positively correlated with FEV_1.0/FVC (ρ =0.60–0.73, P<0.001). The mean value of the six coefficients strongly correlated with FEV_1.0/FVC (ρ =0.80, P<0.0001).

Conclusion

The synchrony of respiratory movements between the pulmonary lobes is limited or lost in patients with more severe airflow limitation.

Risk factors for FEV1 decline in mild COPD and high-risk populations

Background

Early diagnosis of COPD is often not achieved due to limited recognition and limited access to the pulmonary function test. Our hypothesis was that lung function decline may be different between populations with mild COPD and those who are at high risk and do not receive treatment.

Patients and methods

Subjects with mild COPD and those from a high-risk COPD population were recruited from a community-based COPD epidemiological study after obtaining consent. Baseline clinical characteristics, symptom questionnaire, spirometry, low-dose computed tomography (LDCT) chest scan, and blood plasma biomarker data were collected initially and then 1 year later.

Results

A total of 617 participants were recruited, and 438 eventually completed the first-year follow-up visit; 72 participants (46 males) were in the mild COPD group, and 225 participants (165 males) were in the high-risk group. The mean forced expiratory volume in the first second of expiration (FEV₁) decline in the mild COPD group was 129 mL, which was significantly higher than the 30 mL decline in the high-risk population group (P=0.005). Group category (odds ratio [OR] =0.230) and COPD Assessment Test (CAT) score (OR =9.912) were independent risk factors for an FEV₁% predicted decline of >15% for all participants. In the mild COPD group, patients with a higher CAT (OR =5.310) and Emphysema Index (OR =5.681) were associated with a FEV₁% predicted decline of >15% at the first-year follow-up. No factor showed a significantly predictive effect on FEV₁ decline in the high-risk COPD group.

Conclusion

Group category was an independent influential factor associated with FEV₁ decline.

A Bayesian Nonparametric Model for Disease Subtyping: Application to Emphysema Phenotypes

We introduce a novel Bayesian nonparametric model that uses the concept of disease trajectories for disease subtype identification. Although our model is general, we demonstrate that by treating fractions of tissue patterns derived from medical images as compositional data, our model can be applied to study distinct progression trends between population subgroups. Specifically, we apply our algorithm to quantitative emphysema measurements obtained from chest CT scans in the COPDGene Study and show several distinct progression patterns. As emphysema is one of the major components of chronic obstructive pulmonary disease (COPD), the third leading cause of death in the United States [1], an improved definition of emphysema and COPD subtypes is of great interest. We investigate several models with our algorithm, and show that one with age , pack years (a measure of cigarette exposure), and smoking status as predictors gives the best compromise between estimated predictive performance and model complexity. This model identified nine subtypes which showed significant associations to seven single nucleotide polymorphisms (SNPs) known to associate with COPD. Additionally, this model gives better predictive accuracy than multiple, multivariate ordinary least squares regression as demonstrated in a five-fold cross validation analysis. We view our subtyping algorithm as a contribution that can be applied to bridge the gap between CT-level assessment of tissue composition to population-level analysis of compositional trends that vary between disease subtypes.

Texture-based Quantification of Centrilobular Emphysema and Centrilobular Nodularity in Longitudinal CT Scans of Current and Former Smokers

RATIONALE AND OBJECTIVES

The effect of smoking cessation on centrilobular emphysema (CLE) and centrilobular nodularity (CN), two manifestations of smoking-related lung injury on computed tomography (CT) images, has not been clarified. The objective of this study is to leverage texture analysis to investigate differences in extent of CLE and CN between current and former smokers.

MATERIALS AND METHODS

Chest CT scans from 350 current smokers, 401 former smokers, and 25 control subjects were obtained from the multicenter COPDGene Study, a Health Insurance Portability and Accountability Act-compliant study approved by the institutional review board of each participating clinical study center. Additionally, for 215 of these subjects, a follow-up CT scan was obtained approximately 5 years later. For each CT scan, 5000 circular regions of interest (ROIs) of 35-pixel diameter were randomly selected throughout the lungs. The patterns present in each ROI were summarized by 50 computer-extracted texture features. A logistic regression classifier was leveraged to classify each ROI as normal lung, CLE, or CN, and differences in the percentages of normal lung, CLE, and CN by study group were assessed.

RESULTS

Former smokers had significantly more CLE (P <0.01) but less CN (P <0.001) than did current smokers, even after adjustment for important covariates such as patient age, GOLD stage, smoking history, forced expiratory volume in 1 second, gas trapping, and scanner model. Among patients with longitudinal CT scans, continued smoking led to a slight increase in CLE (P = 0.13), whereas sustained abstinence from smoking led to further reduction in CN (P <0.05).

CONCLUSIONS

The proposed texture-based approach quantifies the extent of CN and CLE with high precision. Differences in smoking-related lung disease between longitudinal scans of current smokers and longitudinal scans of former smokers suggest that CN may be reversible on smoking cessation.

A Robust Emphysema Severity Measure Based on Disease Subtypes

RATIONALE AND OBJECTIVES

We propose a novel single index for the quantification of emphysema severity based on an aggregation of multiple computed tomographic features evident in the lung parenchyma of smokers. Our goal was to demonstrate that this single index provides complementary information to the current standard measure of emphysema, percent emphysema (percent low attenuation areas [LAA%]), and may be superior in its association with clinically relevant outcomes.

MATERIALS AND METHODS

The inputs to our algorithm were objective assessments of multiple emphysema subtypes (normal tissue; panlobular; paraseptal; and mild, moderate, and severe centrilobular emphysema). We applied dimensionality reduction techniques to the emphysema quantities to find a space that maximizes the variance of these subtypes. A single emphysema severity index was then derived from a parametrization of the reduced space, and the clinical utility of the measure was explored in a large cross-sectional cohort of 8914 subjects from the COPDGene Study.

RESULTS

There was a statistically significant association between the severity index and the LAA%. Subjects with more severe chronic obstructive pulmonary disease (higher Global initiative for Obstructive Lung Disease stage) tended to have a higher computed tomography severity index. Finally, the severity index was associated with clinical outcomes such as lung function and provided a stronger association to these measures than the LAA%.

CONCLUSIONS

The method provides a single clinically relevant index that can assess the severity of emphysema and that provides information that is complimentary to the more commonly used LAA%.

Computer-aided pulmonary image analysis in small animal models

PURPOSE

To develop an automated pulmonary image analysis framework for infectious lung diseases in small animal models.

METHODS

The authors describe a novel pathological lung and airway segmentation method for small animals. The proposed framework includes identification of abnormal imaging patterns pertaining to infectious lung diseases. First, the authors' system estimates an expected lung volume by utilizing a regression function between total lung capacity and approximated rib cage volume. A significant difference between the expected lung volume and the initial lung segmentation indicates the presence of severe pathology, and invokes a machine learning based abnormal imaging pattern detection system next. The final stage of the proposed framework is the automatic extraction of airway tree for which new affinity relationships within the fuzzy connectedness image segmentation framework are proposed by combining Hessian and gray-scale morphological reconstruction filters.

RESULTS

133 CT scans were collected from four different studies encompassing a wide spectrum of pulmonary abnormalities pertaining to two commonly used small animal models (ferret and rabbit). Sensitivity and specificity were greater than 90% for pathological lung segmentation (average dice similarity coefficient > 0.9). While qualitative visual assessments of airway tree extraction were performed by the participating expert radiologists, for quantitative evaluation the authors validated the proposed airway extraction method by using publicly available EXACT'09 data set.

CONCLUSIONS

The authors developed a comprehensive computer-aided pulmonary image analysis framework for preclinical research applications. The proposed framework consists of automatic pathological lung segmentation and accurate airway tree extraction. The framework has high sensitivity and specificity; therefore, it can contribute advances in preclinical research in pulmonary diseases.

Automated classification of usual interstitial pneumonia using regional volumetric texture analysis in high-resolution computed tomography

OBJECTIVES

We propose a novel computational approach for the automated classification of classic versus atypical usual interstitial pneumonia (UIP).

MATERIALS AND METHODS

Thirty-three patients with UIP were enrolled in this study. They were classified as classic versus atypical UIP by a consensus of 2 thoracic radiologists with more than 15 years of experience using the American Thoracic Society evidence-based guidelines for computed tomography diagnosis of UIP. Two cardiothoracic fellows with 1 year of subspecialty training provided independent readings. The system is based on regional characterization of the morphological tissue properties of lung using volumetric texture analysis of multiple-detector computed tomography images. A simple digital atlas with 36 lung subregions is used to locate texture properties, from which the responses of multidirectional Riesz wavelets are obtained. Machine learning is used to aggregate and to map the regional texture attributes to a simple score that can be used to stratify patients with UIP into classic and atypical subtypes.

RESULTS

We compared the predictions on the basis of regional volumetric texture analysis with the ground truth established by expert consensus. The area under the receiver operating characteristic curve of the proposed score was estimated to be 0.81 using a leave-one-patient-out cross-validation, with high specificity for classic UIP. The performance of our automated method was found to be similar to that of the 2 fellows and to the agreement between experienced chest radiologists reported in the literature. However, the errors of our method and the fellows occurred on different cases, which suggests that combining human and computerized evaluations may be synergistic.

CONCLUSIONS

Our results are encouraging and suggest that an automated system may be useful in routine clinical practice as a diagnostic aid for identifying patients with complex lung disease such as classic UIP, obviating the need for invasive surgical lung biopsy and its associated risks.

Automatic left and right lung separation using free-formed surface fitting on volumetric CT

This study presents a completely automated method for separating the left and right lungs using free-formed surface fitting on volumetric computed tomography (CT). The left and right lungs are roughly divided using iterative 3-dimensional morphological operator and a Hessian matrix analysis. A point set traversing between the initial left and right lungs is then detected with a Euclidean distance transform to determine the optimal separating surface, which is then modeled from the point set using a free-formed surface-fitting algorithm. Subsequently, the left and right lung volumes are smoothly and directly separated using the separating surface. The performance of the proposed method was estimated by comparison with that of a human expert on 44 CT examinations. For all data sets, averages of the root mean square surface distance, maximum surface distance, and volumetric overlap error between the results of the automatic and the manual methods were 0.032 mm, 2.418 mm, and 0.017 %, respectively. Our study showed the feasibility of automatically separating the left and right lungs by identifying the 3D continuous separating surface on volumetric chest CT images.

A generic approach to pathological lung segmentation

In this study, we propose a novel pathological lung segmentation method that takes into account neighbor prior constraints and a novel pathology recognition system. Our proposed framework has two stages; during stage one, we adapted the fuzzy connectedness (FC) image segmentation algorithm to perform initial lung parenchyma extraction. In parallel, we estimate the lung volume using rib-cage information without explicitly delineating lungs. This rudimentary, but intelligent lung volume estimation system allows comparison of volume differences between rib cage and FC based lung volume measurements. Significant volume difference indicates the presence of pathology, which invokes the second stage of the proposed framework for the refinement of segmented lung. In stage two, texture-based features are utilized to detect abnormal imaging patterns (consolidations, ground glass, interstitial thickening, tree-inbud, honeycombing, nodules, and micro-nodules) that might have been missed during the first stage of the algorithm. This refinement stage is further completed by a novel neighboring anatomy-guided segmentation approach to include abnormalities with weak textures, and pleura regions. We evaluated the accuracy and efficiency of the proposed method on more than 400 CT scans with the presence of a wide spectrum of abnormalities. To our best of knowledge, this is the first study to evaluate all abnormal imaging patterns in a single segmentation framework. The quantitative results show that our pathological lung segmentation method improves on current standards because of its high sensitivity and specificity and may have considerable potential to enhance the performance of routine clinical tasks.

The value of CT for disease detection and prognosis determination in combined pulmonary fibrosis and emphysema (CPFE)

BACKGROUND AND PURPOSE

Several imaging-based indices were constructed quantitatively using the emphysema index (EI) and fibrosis score (FS) on high-resolution computed tomography (HRCT). We evaluated the ability of these indices to predict mortality compared to physiologic results. Additionally, prognostic predictive factors were compared among subgroups with biopsy-proven fibrotic idiopathic interstitial pneumonia (IIP) (biopsy-proven CPFE) and in a separate cohort with subclinical CPFE.

MATERIALS AND METHODS

Three chest radiologists independently determined FS. EI was automatically quantified. PFTs, smoking history, and composite physiologic index (CPI) were reviewed. Predictors of time to death were determined based on clinico-physiologic factors and CT-based CPFE indices.

RESULTS

The prevalence of biopsy-proven CPFE was 26% (66/254), with an EI of 9.1±7.1 and a FS of 19.3±14.2. In patients with CPFE, median survival and 5-year survival rates were 6.0 years and 34.8%, respectively, whereas those in fibrotic IIP without emphysema were 10.0 years and 60.9% (p = 0.013). However, the extent of fibrosis did not differ significantly between the two cohorts. In subclinical CPFE, prevalence was 0.04% (93/20,372), EI was 11.3±10.4, and FS was 9.1±7.1. FVC and a fibrosis-weighted CT index were independent predictors of survival in the biopsy-proven CPFE cohort, whereas only the fibrosis-weighted CT index was a significant prognostic factor in the subclinical CPFE cohort.

CONCLUSIONS

Recognition and stratification using CT quantification can be utilized as a prognostic predictor. Prognostic factors vary according to fibrosis severity and among cohorts of patients with biopsy-proven and subclinical CPFE.

Clinical correlations of computed tomography imaging in chronic obstructive pulmonary disease

Chronic obstructive pulmonary disease is a complex disease with heterogeneous presentation, progression, and structural abnormality that is currently graded solely on clinical and physiologic parameters. Thoracic computed tomography imaging holds promise for phenotyping in chronic obstructive pulmonary disease, but despite increasing availability, this methodology has yet to be incorporated into clinical guidelines or routine clinical practice. However, the unique clinical implications of emphysema and airways disease are becoming clearer. Emphysema has a strong association with more rapid disease progression and mortality. Airways disease has a strong relationship with symptoms and health status. It is hoped that future refinement of emphysema assessment allowing for quantitative subtyping will also increase our ability to define clinically meaningful subgroups, as will development of methodologies to assess airways disease and, in particular, small airways through inspiratory/expiratory image registration techniques. Most important, however, is the need for longitudinal data, in not only observational but also therapeutic settings, such that the impact of interventions on radiographically defined phenotypes can be assessed.

Correlation of pulmonary function indexes determined by low-dose MDCT with spirometric pulmonary function tests in patients with chronic obstructive pulmonary disease

OBJECTIVE

The objective of our study was to evaluate the correlation between pulmonary function indexes determined by low-dose MDCT and those obtained from routine spirometric pulmonary function tests (PFTs) in patients with chronic obstructive pulmonary disease (COPD).

MATERIALS AND METHODS

Lung function of patients with COPD stages 0-III was evaluated by both MDCT and spirometric PFTs. Scanning was performed at maximum end-inspiration and maximum end-expiration.

RESULTS

A very strong correlation was found between extrapolated expiratory lung volume (LVex) and COPD stage (r = 0.802, p < 0.001) and between extrapolated LVex and the ratio of forced expiratory volume in 1 second and percentage forced vital capacity (FEV1/FVC%) (r = -0.831, p < 0.001). Moreover, strong positive correlations were found between inspiratory lung volume (LVin) and total lung capacity (TLC) (r = 0.658, p < 0.001), LVex and residual volume (RV) (r = 0.683, p < 0.001), extrapolated LVex and RV (r = 0.640, p < 0.001), LVex and RV/TLC (r = 0.602, p < 0.001), LVex/LVin and RV/TLC (r = 0.622, p < 0.001), extrapolated LVex and RV/TLC (r = 0.663, p < 0.001), and LVex and COPD stage (r = 0.697, p < 0.001).

CONCLUSION

Low-dose MDCT lung function indexes correlate well with spirometric PFT results, and the highest correlation is at end-expiration. Low-dose MDCT may be useful for evaluating lung function in patients with COPD.

Distinct quantitative computed tomography emphysema patterns are associated with physiology and function in smokers

RATIONALE

Emphysema occurs in distinct pathologic patterns, but little is known about the epidemiologic associations of these patterns. Standard quantitative measures of emphysema from computed tomography (CT) do not distinguish between distinct patterns of parenchymal destruction.

OBJECTIVES

To study the epidemiologic associations of distinct emphysema patterns with measures of lung-related physiology, function, and health care use in smokers.

METHODS

Using a local histogram-based assessment of lung density, we quantified distinct patterns of low attenuation in 9,313 smokers in the COPDGene Study. To determine if such patterns provide novel insights into chronic obstructive pulmonary disease epidemiology, we tested for their association with measures of physiology, function, and health care use.

MEASUREMENTS AND MAIN RESULTS

Compared with percentage of low-attenuation area less than -950 Hounsfield units (%LAA-950), local histogram-based measures of distinct CT low-attenuation patterns are more predictive of measures of lung function, dyspnea, quality of life, and health care use. These patterns are strongly associated with a wide array of measures of respiratory physiology and function, and most of these associations remain highly significant (P < 0.005) after adjusting for %LAA-950. In smokers without evidence of chronic obstructive pulmonary disease, the mild centrilobular disease pattern is associated with lower FEV1 and worse functional status (P < 0.005).

CONCLUSIONS

Measures of distinct CT emphysema patterns provide novel information about the relationship between emphysema and key measures of physiology, physical function, and health care use. Measures of mild emphysema in smokers with preserved lung function can be extracted from CT scans and are significantly associated with functional measures.

Computed tomography density histogram analysis to evaluate pulmonary emphysema in ex-smokers

RATIONALE AND OBJECTIVES

High-resolution computed tomography (CT) measurements of emphysema typically use Hounsfield unit (HU) density histogram thresholds or observer scores based on regions of low x-ray attenuation. Our objective was to develop an automated measurement of emphysema using principal component analysis (PCA) of the CT density histogram.

MATERIALS AND METHODS

Ninety-seven ex-smokers, including 53 subjects with chronic obstructive pulmonary disease (COPD) and 44 asymptomatic subjects (AEs), provided written informed consent to imaging as well as plethysmography and spirometry. We applied PCA to the CT density histogram to generate whole lung and regional density histogram principal components including the first and second components and the sum of both principal components (density histogram principal component score [DHPCS]). Significant relationships for DHPCS with single HU thresholds, pulmonary function measurements, an expert's emphysema score, and hyperpolarized (3)He magnetic resonance imaging apparent diffusion coefficients (ADCs) were determined using linear regression and Pearson coefficients. Receiver operator characteristics analysis was performed using forced expiratory volume in 1 second (FEV1)/forced vital capacity (FVC) as the independent diagnostic.

RESULTS

There was a significant difference (P < .0001) between AE and COPD subjects for DHPCS; FEV1/FVC; diffusing capacity of lung for carbon monoxide%predicted; attenuation values below -950, -910, and -856 HU; and (3)He ADCs. There were significant correlations for DHPCS with FEV1/FVC (r = -0.85, P < .0001); diffusing capacity of lung for carbon monoxide%predicted (r = -0.67, P < .0001); attenuation values below -950/-910/-856 HU (r = 0.93/0.96/0.76, P < .0001); and (3)He ADCs (r = 0.85, P < .0001). Receiver operator characteristics analysis showed a 91% classification rate for DHPCS.

CONCLUSIONS

We generated an automated emphysema score using PCA of the CT density histogram with a 91% COPD classification rate that showed strong and significant correlations with pulmonary function tests, single HU thresholds, and (3)He magnetic resonance imaging ADCs.

Quantifying heterogeneity in emphysema from high-resolution computed tomography: a lung tissue research consortium study

RATIONALE AND OBJECTIVES

To quantify spatial distribution of emphysema using high-resolution computed tomography (HRCT), we applied semiautomated analysis with internal attenuation calibration to measure regional air volume, tissue volume, and fractional tissue volume (FTV = tissue/[air + tissue] volume) in well-characterized patients studied by the Lung Tissue Research Consortium (LTRC).

METHODS

HRCT was obtained at supine end-inspiration and end-expiration, and prone end-inspiration from 31 patients with mild, moderate, severe, or very severe emphysema (stages II-V, forced expiratory volume at 1 second >75%, 51%-75%, 21%-50% and ≤20% predicted, respectively). Control data were from 20 healthy non-smokers (stage I). Each lobe was analyzed separately. Heterogeneity of FTV was assessed from coefficients of variation (CV) within and among lobes, and the kurtosis and skewness of FTV histograms.

RESULTS

In emphysema, lobar air volume increased up to 177% above normal except in the right middle lobe. Lobar tissue volume increased up to 107% in mild-moderate stages then normalized in advanced stages. Normally, FTV was up to 82% higher in lower than upper lobes. In mild-moderate emphysema, lobar FTV increased by up to 74% above normal at supine inspiration. In severe emphysema, FTV declined below normal in all lobes and positions in correlation with pulmonary function (P < .05). Markers of FTV heterogeneity increased steadily with disease stage in correlation with pulmonary function (P < .05); the pattern is distinct from that seen in interstitial lung disease (ILD).

CONCLUSION

CT-derived biomarkers differentiate the spatial patterns of emphysema distribution and heterogeneity from that in ILD. Early emphysema is associated with elevated tissue volume and FTV, consistent with hyperemia, inflammation or atelectasis.

Multiscale lung texture signature learning using the Riesz transform

Texture-based computerized analysis of high-resolution computed tomography images from patients with interstitial lung diseases is introduced to assist radiologists in image interpretation. The cornerstone of our approach is to learn lung texture signatures using a linear combination of N-th order Riesz templates at multiple scales. The weights of the linear combination are derived from one-versus-all support vector machines. Steerability and multiscale properties of Riesz wavelets allow for scale and rotation covariance of the texture descriptors with infinitesimal precision. Orientations are normalized among texture instances by locally aligning the Riesz templates, which is carried out analytically. The proposed approach is compared with state-of-the-art texture attributes and shows significant improvement in classification performance with an average area under receiver operating characteristic curves of 0.94 for five lung tissue classes. The derived lung texture signatures illustrate optimal class wise discriminative properties.

Chronic obstructive pulmonary disease: lobe-based visual assessment of volumetric CT by Using standard images--comparison with quantitative CT and pulmonary function test in the COPDGene study

PURPOSE

To provide a new detailed visual assessment scheme of computed tomography (CT) for chronic obstructive pulmonary disease (COPD) by using standard reference images and to compare this visual assessment method with quantitative CT and several physiologic parameters.

MATERIALS AND METHODS

This research was approved by the institutional review board of each institution. CT images of 200 participants in the COPDGene study were evaluated. Four thoracic radiologists performed independent, lobar analysis of volumetric CT images for type (centrilobular, panlobular, and mixed) and extent (on a six-point scale) of emphysema, the presence of bronchiectasis, airway wall thickening, and tracheal abnormalities. Standard images for each finding, generated by two radiologists, were used for reference. The extent of emphysema, airway wall thickening, and luminal area were quantified at the lobar level by using commercial software. Spearman rank test and simple and multiple regression analyses were performed to compare the results of visual assessment with physiologic and quantitative parameters.

RESULTS

The type of emphysema, determined by four readers, showed good agreement (κ = 0.63). The extent of the emphysema in each lobe showed good agreement (mean weighted κ = 0.70) and correlated with findings at quantitative CT (r = 0.75), forced expiratory volume in 1 second (FEV(1)) (r = -0.68), FEV(1)/forced vital capacity (FVC) ratio (r = -0.74) (P < .001). Agreement for airway wall thickening was fair (mean κ = 0.41), and the number of lobes with thickened bronchial walls correlated with FEV(1) (r = -0.60) and FEV(1)/FVC ratio (r = -0.60) (P < .001).

CONCLUSION

Visual assessment of emphysema and airways disease in individuals with COPD can provide reproducible, physiologically substantial information that may complement that provided by quantitative CT assessment.

Fast and efficient lung disease classification using hierarchical one-against-all support vector machine and cost-sensitive feature selection

To improve time and accuracy in differentiating diffuse interstitial lung disease for computer-aided quantification, we introduce a hierarchical support vector machine which selects a class by training a binary classifier at each node in a hierarchy, thus allowing each classifier to use a class-specific quasi-optimal feature set. In addition, the computational cost-sensitive group-feature selection criterion combined with the sequential forward selection is applied in order to obtain a useful and computationally inexpensive quasi-optimal feature set for the purpose of accelerating the classification time. The classification time was reduced by up to 57% and the overall accuracy was significantly improved in comparison with the one-against-all and one-against-one support vector machine methods with sequential forward selection (paired t-test, p<0.001). The reduction of classification time as well as the improvement of overall accuracy demonstrates promise for the proposed classification method to be adopted in various real-time and on-line image-based clinical applications.

Automated texture-based quantification of centrilobular nodularity and centrilobular emphysema in chest CT images

RATIONALE AND OBJECTIVES

Characterization of smoking-related lung disease typically consists of visual assessment of chest computed tomographic (CT) images for the presence and extent of emphysema and centrilobular nodularity (CN). Quantitative analysis of emphysema and CN may improve the accuracy, reproducibility, and efficiency of chest CT scoring. The purpose of this study was to develop a fully automated texture-based system for the detection and quantification of centrilobular emphysema (CLE) and CN in chest CT images.

MATERIALS AND METHODS

A novel approach was used to prepare regions of interest (ROIs) within the lung parenchyma for representation by texture features associated with the gray-level run-length and gray-level gap-length methods. These texture features were used to train a multiple logistic regression classifier to discriminate between normal lung tissue, CN or "smoker's lung," and CLE. This classifier was trained and evaluated on 24 and 71 chest CT scans, respectively.

RESULTS

During training, the classifier correctly classified 89% of ROIs depicting normal lung tissue, 74% of ROIs depicting CN, and 95% of ROIs manifesting CLE. When the performance of the classifier in quantifying extent of CN and CLE was evaluated on 71 chest CT scans, 65% of ROIs in smokers without CLE were classified as CN, compared to 31% in nonsmokers (P < .001) and 28% in smokers with CLE (P < .001).

CONCLUSIONS

The texture-based framework described herein facilitates successful discrimination among normal lung tissue, CN, and CLE and can be used for the automated quantification of smoking-related lung disease.

Quantitative assessment of change in regional disease patterns on serial HRCT of fibrotic interstitial pneumonia with texture-based automated quantification system

OBJECTIVES

To evaluate the usefulness of a texture-based automated quantification system (AQS) for evaluating the extent and interval change of regional disease patterns on initial and follow-up high-resolution computed tomographies (HRCTs) of fibrotic interstitial pneumonia (FIP).

METHODS

Eighty-nine patients with clinically and/or biopsy confirmed usual interstitial pneumonia (UIP) (n = 71) and non-specific interstitial pneumonia (NSIP) (n = 18) were included. An AQS to quantify five disease patterns (ground-glass opacity [GGO], reticular opacity [RO], honeycombing [HC], emphysema [EMPH], consolidation [CONS]) and normal lung was developed. The extent and interval changes of each disease pattern, FS (fibrosis score), TA (total abnormal lung fraction) of entire lung on initial and 1-year follow-up HRCTs were quantified. The agreement between the results of AQS and two readers was assessed. Results of AQS were correlated with forced vital capacity (FVC) and carbon monoxide diffusing capacity (DLco).

RESULTS

The Intraclass correlation coefficient (ICC) study revealed acceptable agreement between visual assessment and AQS (r = 0.78, 0.66 for HC; 0.76, 0.61 for FS; 0.64, 0.68 for TA, initial and follow-up HRCTs, respectively). Linear regression analysis revealed the extent of HC, TA on initial CT, interval changes of FS contributed negatively to DLco, and interval changes of FS, TA contributed negatively to FVC.

CONCLUSIONS

Our AQS is comparable with visual assessment for evaluating the disease extent and the interval changes of FIP on HRCT.