Assessment of the progression of emphysema by quantitative analysis of spirometrically gated computed tomography images

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

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

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

Computed tomography (CT) is the modality of choice for imaging the thorax and lung structure. In chronic obstructive pulmonary disease (COPD), it used to recognise the key morphological features of emphysema, bronchial wall thickening and gas trapping. Despite this, its place in the investigation and management of COPD is yet to be determined, and it is not routinely recommended. However, lung CT already has important clinical applications where it can be used to diagnose concomitant pathology and determine which patients with severe emphysema are appropriate for lung volume reduction procedures. Furthermore, novel quantitative analysis techniques permit objective measurements of pulmonary and extrapulmonary manifestations of the disease. These techniques can give important insights into COPD, and help explore the heterogeneity and underlying mechanisms of the condition. In time, it is hoped that these techniques can be used in clinical trials to help develop disease-specific therapy and, ultimately, as a clinical tool in identifying patients who would benefit most from new and existing treatments. This review discusses the current clinical applications for CT imaging in COPD and quantification techniques, and its potential future role in stratifying disease for optimal outcome.

Multivariate compensation of quantitative pulmonary emphysema metric variation from low-dose, whole-lung CT scans

OBJECTIVE

Emphysema is a disease of the lung characterized by the destruction of the alveolar sac walls. Several quantitative densitometric measures of emphysema from wholelung CT have been proposed for evaluating disease severity and progression. However, a concern with these quantitative measures has been the large interscan variability observed during longitudinal studies of emphysema. To account for and reduce inherent measure variability, this work implements and evaluates the use of a multivariate random-effects model for correcting longitudinal variation in densitometric scores of emphysema due to inspiration.

MATERIALS AND METHODS

The method of multivariate compensation was validated on three of the most commonly reported densitometric measures of emphysema: the emphysema index, histogram percentile, and fractal dimension. Two short-interval, zero-change datasets, one for model development (n = 105) and one for validation (n = 106), were retrospectively identified and used to ensure that all variation was caused by inherent measure variability.

RESULTS

A statistically significant (F test, p < 0.001) reduction of 42.40% in measurement limits of agreement could be obtained after model application, with compensated emphysema metric differences showing 31-33% of the variance compared with uncompensated metric variance.

CONCLUSION

Compensation was still effective when the trained model was applied to the second validation dataset. Multivariate compensation was found to be useful in reducing interscan measurement variability and should be applied to future longitudinal studies of emphysema.

Update on radiology of emphysema and therapeutic implications

Emerging treatments require appropriate CT targeting of a selected lobe or lobes and target airways to obtain a successful response. CT scan is used in pretreatment planning to select patients and plan treatment strategy and posttreatment to confirm correct deployment of devices and assess treatment response. Increasingly treatments are being developed to treat patients who have emphysema who require accurate quantitation of extent and distribution of the process. Functional assessment can be made by inference of detailed anatomic correlates and by direct measurement of regional function using dynamic scan protocols. This article summarizes the current role of imaging in the assessment of patients who have emphysema.

Quantitative computed tomography assessment of airway wall dimensions: current status and potential applications for phenotyping chronic obstructive pulmonary disease

Airway remodeling is extremely important in the pathophysiology of chronic obstructive pulmonary disease (COPD). Since the site and nature of airflow obstruction was described by Hogg, Thurlbeck, and Macklem, investigators have been looking for methods to noninvasively measure the airway wall dimensions in subjects with and at risk for COPD. The advent and proliferation of computed tomography (CT) initially allowed investigators to quantify changes in lung parenchymal structure in subjects with emphysema, and more recently attention has turned to the measurement of airway wall dimensions. Unfortunately, while the lung density is relatively easy to quantify, reliable airway measurements have proven to be more difficult to obtain. However, recent advances in CT technology and new computer algorithms have changed the way investigators have measured airways using CT, and it is now hoped that many of the early issues surrounding airway measurements can be resolved. The measurement of airway wall dimensions is important because it is well known that chronic airflow limitation can be caused by a combination of airway and parenchymal changes. The phenotypic expression of these different subtypes of COPD is vital because a therapy designed to modulate the inflammation in airways may be contraindicated in subjects with the emphysema phenotype and visa versa. Therefore, these new imaging techniques are very likely to play a front-line role in the study of COPD and will, hopefully, allow clinicians to phenotype individuals, thereby personalizing their treatment.

Automatic segmentation and recognition of lungs and lesion from CT scans of thorax

In this study, a fully automated texture-based segmentation and recognition system for lesion and lungs from CT of thorax is presented. For the segmentation part, we have extracted texture features by Gabor filtering the images, and, then combined these features to segment the target volume by using Fuzzy C Means (FCM) clustering. Since clustering is sensitive to initialization of cluster prototypes, optimal initialization of the cluster prototypes was done by using a Genetic Algorithm. For the recognition stage, we have used cortex like mechanism for extracting statistical features in addition to shape-based features. The segmented regions showed a high degree of imbalance between positive and negative samples, so we employed over and under sampling for balancing the data. Finally, the balanced and normalized data was subjected to Support Vector Machine (SimpleSVM) for training and testing. Results reveal an accuracy of delineation to be 94.06%, 94.32% and 89.04% for left lung, right lung and lesion, respectively. Average sensitivity of the SVM classifier was seen to be 89.48%.

Biomass exposure and the high resolution computed tomographic and spirometric findings

BACKGROUND

The adverse health effects of biomass fuel exposure (BFE) is complex and widespread. According to our knowledge, the interstitial lung disease due to BFE is not clear in literature.

OBJECTIVE

In this descriptive crossectional study, the main objective was to assess the effects of BFE on the respiratory system.

METHODS

Patient group was included non-smoker 21 woman and the control group was included non-smoker 22 woman. High resolution computed tomographic (HRCT) examinations were made with supin and prone positions in two groups. The spirometric measurements, including the diffusion capacity at rest for carbon monoxide, single breath (DLCO), were also made.

RESULTS

It was found that BFE caused obstructive and restrictive spirometric impairments. The prevalence of the fibrotic bands, peribronchovascular thickenings, nodular radio opacities, and curvilinear densities in the high resolution computed tomographic examinations were 7, 5, 7, and 16 times higher in the exposure group than the control group, respectively. There was a significant positive correlation between the forced vital capacity (FVC), forced expiratory volume first second (FEV(1)), FEV(1)/FVC, forced expiratory flow during middle half of forced vital capacity (FEF25-75), DLCO and the volumetric densities of the HRCT slices with deep expiration in prone position.

CONCLUSIONS

We think that, the findings due to BFE, pose a special situation and it can be named "biomass lung".

Alpha1-antitrypsin deficiency. 7: Computed tomographic imaging in alpha1-antitrypsin deficiency

Computed tomographic scanning may replace lung function tests as the golden standard for assessing the response to known and novel treatments for alpha1-antitrypsin deficiency.

Computer-aided diagnosis in high resolution CT of the lungs

A computer-aided diagnosis (CAD) system is presented to automatically distinguish normal from abnormal tissue in high-resolution CT chest scans acquired during daily clinical practice. From high-resolution computed tomography scans of 116 patients, 657 regions of interest are extracted that are to be classified as displaying either normal or abnormal lung tissue. A principled texture analysis approach is used, extracting features to describe local image structure by means of a multi-scale filter bank. The use of various classifiers and feature subsets is compared and results are evaluated with ROC analysis. Performance of the system is shown to approach that of two expert radiologists in diagnosing the local regions of interest, with an area under the ROC curve of 0.862 for the CAD scheme versus 0.877 and 0.893 for the radiologists.

Lung Density Measurements in Spontaneous Pneumothorax Demonstrate Airtrapping

PURPOSE

Idiopathic spontaneous pneumothorax (SP) is the result of leakage of air from the lung parenchyma through a ruptured visceral pleura into the pleural cavity. This rupture is thought to be caused by an increased pressure difference between parenchymal airspace and pleural cavity. We hypothesize that rather peripheral airway inflammation leads to obstruction with check valve phenomena and by that to airtrapping in the lung parenchyma, which precedes spontaneous pneumothorax.

SETTING

University hospital.

MATERIALS AND METHODS

Forty-one matched healthy volunteers (21 smokers and 20 nonsmokers), and 41 patients with SP (21 patients with and 20 patients without bullae) underwent spirometrically controlled high-resolution CT density measurements with automatic contour tracing at 10% and at 90% of vital capacity.

RESULTS

Patients with SP showed lower mean lung density (MLD) values and higher percentages of Hounsfield units (HU) below - 900 HU (pixel index [PI]) compared to the healthy volunteers on expiratory scans. This enhanced airtrapping phenomenon is seen in both the SP lung (MLD, p = 002; PI, p = 0.01) and the contralateral lung (MLD, p = 0.009; PI, p = 0.05) compared to the control subjects. The difference with control subjects is independent of smoking behavior and bullae.

CONCLUSIONS

Peripheral airway obstruction with airtrapping was found, and it is supposed to play an important role in the pathogenesis of spontaneous pneumothorax.

Characterization of the interstitial lung diseases via density-based and texture-based analysis of computed tomography images of lung structure and function1

RATIONALE AND OBJECTIVES

Efforts to establish a quantitative approach to the computed tomography (CT)-based character ization of the lung parenchyma in interstitial lung disease (including emphysema) has been sought. The accuracy of these tools must be site independent. Multi-detector row CT has remained the gold standard for imaging the lung, and it provides the ability to image both lung structure as well as lung function.

MATERIAL AND METHODS

Imaging is via multi-detector row CT and protocols include careful control of lung volume during scanning. Characterization includes not only anatomic-based measures but also functional measures including regional parameters derived from measures of pulmonary blood flow and ventilation. Image processing includes the automated detection of the lungs, lobes, and airways. The airways provide the road map to the lung parenchyma. Software automatically detects the airways, the airway centerlines, and the branch points, and then automatically labels the airway tree segments with a standardized set of labels, allowing for intersubject as well intrasubject comparisons across time. By warping all lungs to a common atlas, the atlas provides the range of normality for the various parameters provided by CT imaging.

RESULTS

Imaged density and textural changes mark underlying structural changes at the most peripheral regions of the lung. Additionally, texture-based alterations in the parameters of blood flow may provide early evidence of pathologic processes. Imaging of stable xenon gas provides a regional measure of ventilation which, when coupled with measures of flow, provide for a textural analysis regional of ventilation-perfusion matching.

CONCLUSION

With the improved resolution and speed of CT imaging, the patchy nature of regional parenchymal pathology can be imaged as texture of structure and function. With careful control of imaging protocols and the use of objective image analysis methods it is possible to provide site-independent tools for the assessment of interstitial lung disease. There remains a need to validate these methods, which requires interdisciplinary and cross-institutional efforts to gather appropriate data bases of images along with a consensus on appropriate ground truths associated with the images. Furthermore, there is the growing need for scanner manufacturers to focus on not just visually pleasing images, but on quantitatifiably accurate images.

Lung attenuation measurements in healthy young adults

BACKGROUND

High-resolution computed tomography (HRCT) attenuation measurements may be more sensitive in finding early emphysematous changes in relatively young subjects than lung function measurements.

OBJECTIVES

To define lung attenuation parameters in smokers and never-smokers.

METHODS

A prospective comparative study in a university hospital setting was designed with 20 healthy smoking and 20 nonsmoking volunteers. Attenuation measurements on spirometrically controlled HRCT at three levels in the upper half of the lungs at 10% and 90% of vital capacity (VC10% and VD90%) were done, and lung function measurements were performed.

RESULTS

Mean lung attenuation (MLD) and pixel index (PI) were correlated with lung function and smoking history. Small attenuation differences in the left and right lung were found but no sex-related differences. At main carina (MC) level, the PI was higher at VC90% (p < 0.0001) but lower at VC10% (p < 0.01) compared to the apex. Age correlated with attenuation parameters at VC10%, whereas for pack-years no correlation was found. There were attenuation correlations with VC (PI: R = 0.31, p < 0.05 at VC10%/90%), residual volume (MLD: R = -0.31, p < 0.05 at VC10%), and total lung capacity (PI: R = 0.31, p < 0.05 at VC10%/VC90%).

CONCLUSIONS

Lung attenuation during inspiration was lower at the MC level than at the top, but higher on expiratory scans. No sex-related differences were found. Lung attenuation decreases with age on expiratory scans. This seemed to be of more importance than the amount of pack-years of smoking. A relationship with lung function parameters is not uniformly proven.

Chronic obstructive pulmonary disease. 4: imaging the lungs in patients with chronic obstructive pulmonary disease

The role of chest radiography and computed tomography in the evaluation of pulmonary emphysema and chronic bronchitis is reviewed.

Repeatability of lung density measurements with low-dose computed tomography in subjects with alpha-1-antitrypsin deficiency-associated emphysema

RATIONALE AND OBJECTIVES

Multislice computed tomography (MSCT) of the lungs provides a new opportunity for longitudinal assessment of lung densities because of shorter scan duration. The aim of the present study was to assess the intraindividual variation of lung densities measured by MSCT of patients with emphysema.

METHODS

Ten patients with emphysema participated in a study in which MSCT was obtained on two occasions, approximately 2 weeks apart. Scanning parameters were 140 kV, 20 mAs, 4 x 2.5-mm collimation, and effective slice thickness of 2.5 mm. Lung density was measured as the 15th percentile point and the relative area below -910 Hounsfield units (HU) by using Pulmo-LKEB software.

RESULTS

The mean difference of the 15th percentile point was -1.29 +/- 3.2 HU, and that for the relative area below the -910-HU parameter was -1.02% +/- 3.09%. Intraclass coefficients of variation were 0.96 (0.86-0.99) and 0.94 (0.8-0.98), respectively (95% confidence interval).

CONCLUSIONS

Lung density parameters of emphysema derived by MSCT provide an opportunity for analysis of the treatment effects of new drugs on the progression of emphysema.

A randomized clinical trial of alpha(1)-antitrypsin augmentation therapy

We have investigated whether restoration of the balance between neutrophil elastase and its inhibitor, alpha(1)-antitrypsin, can prevent the progression of pulmonary emphysema in patients with alpha(1)-antitrypsin deficiency. Twenty-six Danish and 30 Dutch ex-smokers with alpha(1)-antitrypsin deficiency of PI*ZZ phenotype and moderate emphysema (FEV(1) between 30% and 80% of predicted) participated in a double-blind trial of alpha(1)-antitrypsin augmentation therapy. The patients were randomized to either alpha(1)-antitrypsin (250 mg/kg) or albumin (625 mg/kg) infusions at 4-wk intervals for at least 3 yr. Self-administered spirometry performed every morning and evening at home showed no significant difference in decline of FEV(1) between treatment and placebo. Each year, the degree of emphysema was quantified by the 15th percentile point of the lung density histogram derived from computed tomography (CT). The loss of lung tissue measured by CT (mean +/- SEM) was 2.6 +/- 0.41 g/L/yr for placebo as compared with 1.5 +/- 0.41 g/L/yr for alpha(1)-antitrypsin infusion (p = 0.07). Power analysis showed that this protective effect would be significant in a similar trial with 130 patients. This is in contrast to calculations based on annual decline of FEV(1) showing that 550 patients would be needed to show a 50% reduction of annual decline. We conclude that lung density measurements by CT may facilitate future randomized clinical trials of investigational drugs for a disease in which little progress in therapy has been made in the past 30 yr.

Computer recognition of regional lung disease patterns

We have developed an objective, reproducible, and automated means for the regional evaluation of the pulmonary parenchyma from computed tomography (CT) scans. This method, known as the Adaptive Multiple Feature Method (AMFM) assesses as many as 22 independent texture features in order to classify a tissue pattern. In this study, the six tissue patterns characterized were: honeycombing, ground glass, bronchovascular, nodular, emphysemalike, and normal. The lung slices were evaluated regionally using 31 x 31 pixel regions of interest. In each region of interest, an optimal subset of texture features was evaluated to determine which of the six patterns the region could be characterized as. The computer output was validated against experienced observers in three settings. In the first two readings, when the observers were blinded to the primary diagnosis of the subject, the average computer versus observer agreement was 44.4 +/- 8.7% and 47.3 +/- 9.0%, respectively. The average interobserver agreement for the same two readings were 48.8 +/- 9.1% and 52.2 +/- 10.0%, respectively. In the third reading, when the observers were provided the primary diagnosis, the average computer versus observer agreement was 51.7 +/- 2.9% where as the average interobserver agreement was 53.9 +/- 6.2%. The kappa statistic of agreement between the regions, for which the majority of the observers agreed on a pattern type, versus the computer was found to be 0.62. For regional tissue characterization, the AMFM is 100% reproducible and performs as well as experienced human observers who have been told the patient diagnosis.