Equating quantitative emphysema measurements on different CT image reconstructions

A systematic assessment and optimization of photon-counting CT for lung density quantifications

BACKGROUND

Photon-counting computed tomography (PCCT) has recently emerged into clinical use; however, its optimum imaging protocols and added benefits remains unknown in terms of providing more accurate lung density quantification compared to energy-integrating computed tomography (EICT) scanners.

PURPOSE

To systematically assess the performance of a clinical PCCT scanner for lung density quantifications and compare it against EICT.

METHODS

This cross-sectional study involved a retrospective analysis of subjects scanned (August-December 2021) using a clinical PCCT system. The influence of altering reconstruction parameters was studied (reconstruction kernel, pixel size, slice thickness). A virtual CT dataset of anthropomorphic virtual subjects was acquired to demonstrate the correspondence of findings to clinical dataset, and to perform systematic imaging experiments, not possible using human subjects. The virtual subjects were imaged using a validated, scanner-specific CT simulator of a PCCT and two EICT (defined as EICT A and B) scanners. The images were evaluated using mean absolute error (MAE) of lung and emphysema density against their corresponding ground truth.

RESULTS

Clinical and virtual PCCT datasets showed similar trends, with sharper kernels and smaller voxel sizes increasing percentage of low-attenuation areas below -950 HU (LAA-950) by up to 15.7 ± 6.9% and 11.8 ± 5.5%, respectively. Under the conditions studied, higher doses, thinner slices, smaller pixel sizes, iterative reconstructions, and quantitative kernels with medium sharpness resulted in lower lung MAE values. While using these settings for PCCT, changes in the dose level (13 to 1.3 mGy), slice thickness (0.4 to 1.5 mm), pixel size (0.49 to 0.98 mm), reconstruction technique (70 keV-VMI to wFBP), and kernel (Qr48 to Qr60) increased lung MAE by 15.3 ± 2.0, 1.4 ± 0.6, 2.2 ± 0.3, 4.2 ± 0.8, and 9.1 ± 1.6 HU, respectively. At the optimum settings identified per scanner, PCCT images exhibited lower lung and emphysema MAE than those of EICT scanners (by 2.6 ± 1.0 and 9.6 ± 3.4 HU, compared to EICT A, and by 4.8 ± 0.8 and 7.4 ± 2.3 HU, compared to EICT B). The accuracy of lung density measurements was correlated with subjects' mean lung density (p < 0.05), measured by PCCT at optimum setting under the conditions studied.

CONCLUSION

Photon-counting CT demonstrated superior performance in density quantifications, with its influences of imaging parameters in line with energy-integrating CT scanners. The technology offers improvement in lung quantifications, thus demonstrating potential toward more objective assessment of respiratory conditions.

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

PURPOSE

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

MATERIALS AND METHODS

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

RESULTS

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

CONCLUSIONS

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

CT kernel conversions using convolutional neural net for super-resolution with simplified squeeze-and-excitation blocks and progressive learning among smooth and sharp kernels

PURPOSE

Computed tomography (CT) volume sets reconstructed with different kernels are helping to increase diagnostic accuracy. However, several CT volumes reconstructed with different kernels are difficult to sustain, due to limited storage and maintenance issues. A CT kernel conversion method is proposed using convolutional neural networks (CNN).

METHODS

A total of 3289 CT images from ten patients (five men and five women; mean age, 63.0 ± 8.6 years) were obtained in May 2016 (Somatom Sensation 16, Siemens Medical Systems, Forchheim, Germany). These CT images were reconstructed with various kernels, including B10f (very smooth), B30f (medium smooth), B50f (medium sharp), and B70f (very sharp) kernels. Smooth kernel images were converted into sharp kernel images using super-resolution (SR) network with Squeeze-and-Excitation (SE) blocks and auxiliary losses, and vice versa. In this study, the single-conversion model and multi-conversion model were presented. In case of the single-conversion model, for the one corresponding output image (e.g., B10f to B70), SE-Residual blocks were stacked. For the multi-conversion model, to convert an image into several output images (e.g., B10f to B30f, B50f, and B70f, and vice versa), progressive learning (PL) was employed by calculating auxiliary losses in every four SE-Residual blocks. Through auxiliary losses, the model could learn mutual relationships between different kernel types. The conversion quality was evaluated by the root-mean-square-error (RMSE), structural similarity (SSIM) index and mutual information (MI) between original and converted images.

RESULTS

The RMSE (SSIM index , MI) of the multi-conversion model was 4.541 ± 0.688 (0.998 ± 0.001 , 2.587 ± 0.137), 27.555 ± 5.876 (0.944 ± 0.021 , 1.735 ± 0.137), 72.327 ± 17.387 (0.815 ± 0.053 , 1.176 ± 0.096), 8.748 ± 1.798 (0.996 ± 0.002 , 2.464 ± 0.121), 9.470 ± 1.772 (0.994 ± 0.003 , 2.336 ± 0.133), and 9.184 ± 1.605 (0.994 ± 0.002 , 2.342 ± 0.138) in conversion between B10f-B30f, B10f-B50f, B10f-B70f, B70f-B50f, B70f-B30f, and B70f-B10f, respectively, which showed significantly better image quality than the conventional model.

CONCLUSIONS

We proposed deep learning-based CT kernel conversion using SR network. By introducing simplified SE blocks and PL, the model performance was significantly improved.

Emphysema quantification using low-dose computed tomography with deep learning-based kernel conversion comparison

OBJECTIVE

This study determined the effect of dose reduction and kernel selection on quantifying emphysema using low-dose computed tomography (LDCT) and evaluated the efficiency of a deep learning-based kernel conversion technique in normalizing kernels for emphysema quantification.

METHODS

A sample of 131 participants underwent LDCT and standard-dose computed tomography (SDCT) at 1- to 2-year intervals. LDCT images were reconstructed with B31f and B50f kernels, and SDCT images were reconstructed with B30f kernels. A deep learning model was used to convert the LDCT image from a B50f kernel to a B31f kernel. Emphysema indices (EIs), lung attenuation at 15th percentile (perc15), and mean lung density (MLD) were calculated. Comparisons among the different kernel types for both LDCT and SDCT were performed using Friedman's test and Bland-Altman plots.

RESULTS

All values of LDCT B50f were significantly different compared with the values of LDCT B31f and SDCT B30f (p < 0.05). Although there was a statistical difference, the variation of the values of LDCT B50f significantly decreased after kernel normalization. The 95% limits of agreement between the SDCT and LDCT kernels (B31f and converted B50f) ranged from - 2.9 to 4.3% and from - 3.2 to 4.4%, respectively. However, there were no significant differences in EIs and perc15 between SDCT and LDCT converted B50f in the non-chronic obstructive pulmonary disease (COPD) participants (p > 0.05).

CONCLUSION

The deep learning-based CT kernel conversion of sharp kernel in LDCT significantly reduced variation in emphysema quantification, and could be used for emphysema quantification.

KEY POINTS

• Low-dose computed tomography with smooth kernel showed adequate performance in quantifying emphysema compared with standard-dose CT. • Emphysema quantification is affected by kernel selection and the application of a sharp kernel resulted in a significant overestimation of emphysema. • Deep learning-based kernel normalization of sharp kernel significantly reduced variation in emphysema quantification.

Deep learning-enabled accurate normalization of reconstruction kernel effects on emphysema quantification in low-dose CT

Lung densitometry is being frequently adopted in CT-based emphysema quantification, yet known to be affected by the choice of reconstruction kernel. This study presents a two-step deep learning architecture that enables accurate normalization of reconstruction kernel effects on emphysema quantification in low-dose CT. Deep learning is used to convert a CT image of a sharp kernel to that of a standard kernel with restoration of truncation artifacts and smoothing-free pixel size normalization. We selected 353 scans reconstructed by both standard and sharp kernels from four different CT scanners from the United States National Lung Screening Trial program database. A truncation artifact correction model was constructed with a combination of histogram extrapolation and a deep learning model trained with truncated and non-truncated image sets. Then, we performed frequency domain zero-padding to normalize reconstruction field of view effects while preventing image smoothing effects. The kernel normalization model has a U-Net based architecture trained for each CT scanner dataset. Three lung density measurements including relative lung area under 950 HU (RA950), lower 15th percentile threshold (perc15), and mean lung density were obtained in the datasets from standard, sharp, and normalized kernels. The effect of kernel normalization was evaluated with pair-wise differences in lung density metrics. The mean of pair-wise differences in RA950 between standard and sharp kernel reconstructions was reduced from 10.75% to  -0.07% using kernel normalization. The difference for perc15 decreased from  -31.03 HU to  -0.30 HU after kernel normalization. Our study demonstrated the feasibility of applying deep learning techniques for normalizing CT kernel effects, thereby reducing the kernel-induced variability in lung density measurements. The deep learning model could increase the accuracy of emphysema quantification, thereby allowing reliable surveillance of emphysema in lung cancer screening even when follow-up CT scans are acquired with different reconstruction kernels.

Investigating the Robustness Neighborhood Gray Tone Difference Matrix and Gray Level Co-occurrence Matrix Radiomic Features on Clinical Computed Tomography Systems Using Anthropomorphic Phantoms: Evidence From a Multivendor Study

OBJECTIVE

The aim of this study was to determine if optimized imaging protocols across multiple computed tomography (CT) vendors could result in reproducible radiomic features calculated from an anthropomorphic phantom.

METHODS

Materials with varying degrees of heterogeneity were placed throughout the lungs of the phantom. Twenty scans of the phantom were acquired on 3 CT manufacturers with chest CT protocols that had optimized protocol parameters. Scans were reconstructed using vendor-specific standards and lung kernels. The concordance correlation coefficient (CCC) was used to calculate reproducibility between features. For features with high CCC values, Bland-Altman analysis was also used to quantify agreement.

RESULTS

The mean Hounsfield unit (HU) was 32.93 HU (141.7 to -26.5 HU) for the rubber insert and 347.2 HU (-320.9 to -347.7 HU) for the wood insert. Low CCC values of less than 0.9 were calculated for all features across all scans.

CONCLUSIONS

Radiomic features that are derived from the spatial distribution of voxel intensities should be particularly scrutinized for reproducibility in a multivendor environment.

Ultra-low-dose sequential computed tomography for quantitative lung aeration assessment-a translational study

Background

Quantitative lung computed tomography (CT) provides fundamental information about lung aeration in critically ill patients. We tested a scanning protocol combining reduced number of CT slices and tube current, comparing quantitative analysis and radiation exposure to conventional CT.

Methods

In pigs, CT scans were performed during breath hold in a model of lung injury with three different protocols: standard spiral with 180 mAs tube current-time product (Spiral180), sequential with 20-mm distance between slices and either 180 mAs (Sequential180) or 50 mAs (Sequential50). Spiral scans of critically ill patients were collected retrospectively, and subsets of equally spaced slices were extracted. The agreement between CT protocols was assessed with Bland–Altman analysis.

Results

In 12 pigs, there was good concordance between the sequential protocols and the spiral scan (all biases ≤1.9%, agreements ≤±6.5%). In Spiral180, Sequential180 and Sequential50, estimated dose exposure was 2.3 (2.1–2.8), 0.21 (0.19–0.26), and 0.09 (0.07–0.10) mSv, respectively (p < 0.001 compared to Spiral180); number of acquired slices was 244 (227–252), 12 (11–13) and 12 (11–13); acquisition time was 7 (6–7), 23 (21–25) and 24 (22–26) s. In 32 critically ill patients, quantitative analysis extrapolated from 1-mm slices interleaved by 20 mm had a good concordance with the analysis performed on the entire spiral scan (all biases <1%, agreements ≤2.2%).

Conclusions

In animal CT data, combining sequential scan and low tube current did not affect significantly the quantitative analysis, with a radiation exposure reduction of 97%, reaching a dose comparable to chest X-ray, but with longer acquisition time. In human CT data, lung aeration analysis could be extrapolated from a subset of thin equally spaced slices.

Electronic supplementary material

The online version of this article (doi: 10.1186/s40635-017-0133-6) contains supplementary material, which is available to authorized users.

Lung Mass in Smokers

RATIONALE AND OBJECTIVE

Emphysema is characterized by airspace dilation, inflammation, and irregular deposition of elastin and collagen in the interstitium. Computed tomographic studies have reported that lung mass (LM) may be increased in smokers, a finding attributed to inflammatory and parenchymal remodeling processes observed on histopathology. We sought to examine the epidemiologic and clinical associations of LM in smokers.

MATERIALS AND METHODS

Baseline epidemiologic, clinical, and computed tomography (CT) data (n = 8156) from smokers enrolled into the COPDGene Study were analyzed. LM was calculated from the CT scan. Changes in lung function at 5 years' follow-up were available from 1623 subjects. Regression analysis was performed to assess for associations of LM with forced expiratory volume in 1 second (FEV₁) and FEV₁ decline.

RESULTS

Subjects with Global Initiative for Chronic Obstructive Lung Disease (GOLD) 1 chronic obstructive pulmonary disease had greater LM than either smokers with normal lung function or those with GOLD 2-4 chronic obstructive pulmonary disease (P < 0.001 for both comparisons). LM was predictive of the rate of the decline in FEV₁ (decline per 100 g, -4.7 ± 1.7 mL/y, P = 0.006).

CONCLUSIONS

Our cross-sectional data suggest the presence of a biphasic radiological remodeling process in smokers: the presence of such nonlinearity must be accounted for in longitudinal computed tomographic studies. Baseline LM predicts the decline in lung function.

Emphysema Quantification on Cardiac CT Scans Using Hidden Markov Measure Field Model: The MESA Lung Study

Cardiac computed tomography (CT) scans include approximately 2/3 of the lung and can be obtained with low radiation exposure. Large cohorts of population-based research studies reported high correlations of emphysema quantification between full-lung (FL) and cardiac CT scans, using thresholding-based measurements. This work extends a hidden Markov measure field (HMMF) model-based segmentation method for automated emphysema quantification on cardiac CT scans. We show that the HMMF-based method, when compared with several types of thresholding, provides more reproducible emphysema segmentation on repeated cardiac scans, and more consistent measurements between longitudinal cardiac and FL scans from a diverse pool of scanner types and thousands of subjects with ten thousands of scans.

Lung hyperaeration assessment by computed tomography: correction of reconstruction-induced bias

Background

Computed tomography (CT) reconstruction parameters, such as slice thickness and convolution kernel, significantly affect the quantification of hyperaerated parenchyma (V_HYPER%). The aim of this study was to investigate the mathematical relation between V_HYPER% calculated at different reconstruction settings, in mechanically ventilated and spontaneously breathing patients with different lung pathology.

Methods

In this retrospective observational study, CT scans of patients of the intensive care unit and emergency department were collected from two CT scanners and analysed with different kernel-thickness combinations (reconstructions): 1.25 mm soft kernel, 5 mm soft kernel, 5 mm sharp kernel in the first scanner; 2.5 mm slice thickness with a smooth (B41s) and a sharp (B70s) kernel on the second scanner. A quantitative analysis was performed with Maluna® to assess lung aeration compartments as percent of total lung volume. CT variables calculated with different reconstructions were compared in pairs, and their mathematical relationship was analysed by using quadratic and power functions.

Results

43 subjects were included in the present analysis. Image reconstruction parameters influenced all the quantitative CT-derived variables. The most relevant changes occurred in the hyperaerated and normally aerated volume compartments. The application of a power correction formula led to a significant reduction in the bias between V_HYPER% estimations (p < 0.001 in all cases). The bias in V_HYPER% assessment did not differ between lung pathology nor ventilation mode groups (p > 0.15 in all cases).

Conclusions

Hyperaerated percent volume at different reconstruction settings can be described by a fixed mathematical relationship, independent of lung pathology, ventilation mode, and type of CT scanner.

DERIVATION OF A TEST STATISTIC FOR EMPHYSEMA QUANTIFICATION

Density masking is the de-facto quantitative imaging phenotype for emphysema that is widely used by the clinical community. Density masking defines the burden of emphysema by a fixed threshold, usually between -910 HU and -950 HU, that has been experimentally validated with histology. In this work, we formalized emphysema quantification by means of statistical inference. We show that a non-central Gamma is a good approximation for the local distribution of image intensities for normal and emphysema tissue. We then propose a test statistic in terms of the sample mean of a truncated non-central Gamma random variable. Our results show that this approach is well-suited for the detection of emphysema and superior to standard density masking. The statistical method was tested in a dataset of 1337 samples obtained from 9 different scanner models in subjects with COPD. Results showed an increase of 17% when compared to the density masking approach, and an overall accuracy of 94.09%.

The Impact of Sources of Variability on Parametric Response Mapping of Lung CT Scans

Parametric response mapping (PRM) of inspiration and expiration computed tomography (CT) images improves the radiological phenotyping of chronic obstructive pulmonary disease (COPD). PRM classifies individual voxels of lung parenchyma as normal, emphysematous, or nonemphysematous air trapping. In this study, bias and noise characteristics of the PRM methodology to CT and clinical procedures were evaluated to determine best practices for this quantitative technique. Twenty patients of varying COPD status with paired volumetric inspiration and expiration CT scans of the lungs were identified from the baseline COPDGene cohort. The impact of CT scanner manufacturer and reconstruction kernels were evaluated as potential sources of variability in PRM measurements along with simulations to quantify the impact of inspiration/expiration lung volume levels, misregistration, and image spacing on PRM measurements. Negligible variation in PRM metrics was observed when CT scanner type and reconstruction were consistent and inspiration/expiration lung volume levels were near target volumes. CT scanner Hounsfield unit drift occurred but remained difficult to ameliorate. Increasing levels of image misregistration and CT slice spacing were found to have a minor effect on PRM measurements. PRM-derived values were found to be most sensitive to lung volume levels and mismatched reconstruction kernels. As with other quantitative imaging techniques, reliable PRM measurements are attainable when consistent clinical and CT protocols are implemented.

Normalizing computed tomography data reconstructed with different filter kernels: effect on emphysema quantification

Objectives

To propose and evaluate a method to reduce variability in emphysema quantification among different computed tomography (CT) reconstructions by normalizing CT data reconstructed with varying kernels.

Methods

We included 369 subjects from the COPDGene study. For each subject, spirometry and a chest CT reconstructed with two kernels were obtained using two different scanners. Normalization was performed by frequency band decomposition with hierarchical unsharp masking to standardize the energy in each band to a reference value. Emphysema scores (ES), the percentage of lung voxels below -950 HU, were computed before and after normalization. Bland-Altman analysis and correlation between ES and spirometry before and after normalization were compared. Two mixed cohorts, containing data from all scanners and kernels, were created to simulate heterogeneous acquisition parameters.

Results

The average difference in ES between kernels decreased for the scans obtained with both scanners after normalization (7.7 ± 2.7 to 0.3 ± 0.7; 7.2 ± 3.8 to -0.1 ± 0.5). Correlation coefficients between ES and FEV₁, and FEV₁/FVC increased significantly for the mixed cohorts.

Conclusions

Normalization of chest CT data reduces variation in emphysema quantification due to reconstruction filters and improves correlation between ES and spirometry.

Key Points

• Emphysema quantification is sensitive to the reconstruction kernel used.

• Normalization allows comparison of emphysema quantification from images reconstructed with varying kernels.

• Normalization allows comparison of emphysema quantification obtained with scanners from different manufacturers.

• Normalization improves correlation of emphysema quantification with spirometry.

• Normalization can be used to compare data from different studies and centers.

Adaptive quantification and longitudinal analysis of pulmonary emphysema with a hidden Markov measure field model

The extent of pulmonary emphysema is commonly estimated from CT scans by computing the proportional area of voxels below a predefined attenuation threshold. However, the reliability of this approach is limited by several factors that affect the CT intensity distributions in the lung. This work presents a novel method for emphysema quantification, based on parametric modeling of intensity distributions and a hidden Markov measure field model to segment emphysematous regions. The framework adapts to the characteristics of an image to ensure a robust quantification of emphysema under varying CT imaging protocols, and differences in parenchymal intensity distributions due to factors such as inspiration level. Compared to standard approaches, the presented model involves a larger number of parameters, most of which can be estimated from data, to handle the variability encountered in lung CT scans. The method was applied on a longitudinal data set with 87 subjects and a total of 365 scans acquired with varying imaging protocols. The resulting emphysema estimates had very high intra-subject correlation values. By reducing sensitivity to changes in imaging protocol, the method provides a more robust estimate than standard approaches. The generated emphysema delineations promise advantages for regional analysis of emphysema extent and progression.