RESUMEN
High-throughput extraction of radiomic features from low-dose CT scans can characterize the heterogeneity of the lung parenchyma and potentially aid in identifying subpopulations that may have higher risk of lung diseases, such as COPD, and lung cancer due to inflammation or obstruction of the airways. We aim to determine the feasibility of a lung radiomics phenotyping approach in a lung cancer screening cohort, while quantifying the effect of different CT reconstruction algorithms on phenotype robustness. We identified low-dose CT scans (n = 308) acquired with Siemens Healthineers scanners from patients who completed low-dose CT within our lung cancer screening program between 2015 and 2018 and had two different sets of image reconstructions kernel available (i.e., medium (I30f.), sharp (I50f.)) for the same acquisition. Following segmentation of the lung field, a total of 26 radiomic features were extracted from the entire 3D lung-field using a previously validated fully-automated lattice-based software pipeline, adapted for low-dose CT scans. The lattice in-house software was used to extract features including gray-level histogram, co-occurrence, and run-length descriptors. The lattice approach uses non-overlapping windows for traversing along pixels of images and calculates different features. Each feature was averaged for each scan within a range of lattice window sizes (W) of 4, 8 and 20 mm. The extracted imaging features from both datasets were harmonized to correct for differences in image acquisition parameters. Subsequently, unsupervised hierarchical clustering was applied on the extracted features to identify distinct phenotypic patterns of the lung parenchyma, where consensus clustering was used to identify the optimal number of clusters (K = 2). Differences between phenotypes for demographic and clinical covariates including sex, age, BMI, pack-years of smoking, Lung-RADS and cancer diagnosis were assessed for each phenotype cluster, and then compared across clusters for the two different CT reconstruction algorithms using the cluster entanglement metric, where a lower entanglement coefficient corresponds to good cluster alignment. Furthermore, an independent set of low-dose CT scans (n = 88) from patients with available pulmonary function data on lung obstruction were analyzed using the identified optimal clusters to assess associations to lung obstruction and validate the lung phenotyping paradigm. Heatmaps generated by radiomic features identified two distinct lung parenchymal phenotype patterns across different feature extraction window sizes, for both reconstruction algorithms (P < 0.05 with K = 2). Associations of radiomic-based clusters with clinical covariates showed significant differences for BMI and pack-years of smoking (P < 0.05) for both reconstruction kernels. Radiomic phenotype patterns were more similar across the two reconstructed kernels, when smaller window sizes (W = 4 and 8 mm) were used for radiomic feature extraction, as deemed by their entanglement coefficient. Validation of clustering approaches using cluster mapping for the independent sample with lung obstruction also showed two statistically significant phenotypes (P < 0.05) with significant difference for BMI and smoking pack-years. Radiomic analysis can be used to characterize lung parenchymal phenotypes from low-dose CT scans, which appear reproducible for different reconstruction kernels. Further work should seek to evaluate the effect of additional CT acquisition parameters and validate these phenotypes in characterizing lung cancer screening populations, to potentially better stratify disease patterns and cancer risk.
Asunto(s)
Neoplasias Pulmonares , Humanos , Neoplasias Pulmonares/diagnóstico por imagen , Tomografía Computarizada por Rayos X/métodos , Detección Precoz del Cáncer , Pulmón/diagnóstico por imagen , AlgoritmosRESUMEN
Radiomic approaches in precision medicine are promising, but variation associated with image acquisition factors can result in severe biases and low generalizability. Multicenter datasets used in these studies are often heterogeneous in multiple imaging parameters and/or have missing information, resulting in multimodal radiomic feature distributions. ComBat is a promising harmonization tool, but it only harmonizes by single/known variables and assumes standardized input data are normally distributed. We propose a procedure that sequentially harmonizes for multiple batch effects in an optimized order, called OPNested ComBat. Furthermore, we propose to address bimodality by employing a Gaussian Mixture Model (GMM) grouping considered as either a batch variable (OPNested + GMM) or as a protected clinical covariate (OPNested - GMM). Methods were evaluated on features extracted with CapTK and PyRadiomics from two public lung computed tomography (CT) datasets. We found that OPNested ComBat improved harmonization performance over standard ComBat. OPNested + GMM ComBat exhibited the best harmonization performance but the lowest predictive performance, while OPNested - GMM ComBat showed poorer harmonization performance, but the highest predictive performance. Our findings emphasize that improved harmonization performance is no guarantee of improved predictive performance, and that these methods show promise for superior standardization of datasets heterogeneous in multiple or unknown imaging parameters and greater generalizability.
Asunto(s)
Tomografía Computarizada por Rayos X , Distribución NormalRESUMEN
Radiomic features have a wide range of clinical applications, but variability due to image acquisition factors can affect their performance. The harmonization tool ComBat is a promising solution but is limited by inability to harmonize multimodal distributions, unknown imaging parameters, and multiple imaging parameters. In this study, we propose two methods for addressing these limitations. We propose a sequential method that allows for harmonization of radiomic features by multiple imaging parameters (Nested ComBat). We also employ a Gaussian Mixture Model (GMM)-based method (GMM ComBat) where scans are split into groupings based on the shape of the distribution used for harmonization as a batch effect and subsequent harmonization by a known imaging parameter. These two methods were evaluated on features extracted with CapTK and PyRadiomics from two public lung computed tomography datasets. We found that Nested ComBat exhibited similar performance to standard ComBat in reducing the percentage of features with statistically significant differences in distribution attributable to imaging parameters. GMM ComBat improved harmonization performance over standard ComBat (- 11%, - 10% for Lung3/CAPTK, Lung3/PyRadiomics harmonizing by kernel resolution). Features harmonized with a variant of the Nested method and the GMM split method demonstrated similar c-statistics and Kaplan-Meier curves when used in survival analyses.
Asunto(s)
Tomografía Computarizada por Rayos XRESUMEN
PURPOSE: Quantitative computed tomography (qCT) imaging-based cluster analysis identified clinically meaningful COPD former-smoker subgroups (clusters) based on cross-sectional data. We aimed to identify progression clusters for former smokers using longitudinal data. PATIENTS AND METHODS: We selected 472 former smokers from SPIROMICS with a baseline visit and a one-year follow-up visit. A total of 150 qCT imaging-based variables, comprising 75 variables at baseline and their corresponding progression rates, were derived from the respective inspiration and expiration scans of the two visits. The COPD progression clusters identified were then associated with subject demography, clinical variables and biomarkers. RESULTS: COPD severities at baseline increased with increasing cluster number. Cluster 1 patients were an obese subgroup with rapid progression of functional small airway disease percentage (fSAD%) and emphysema percentage (Emph%). Cluster 2 exhibited a decrease of fSAD% and Emph%, an increase of tissue fraction at total lung capacity and airway narrowing over one year. Cluster 3 showed rapid expansion of Emph% and an attenuation of fSAD%. Cluster 4 demonstrated severe emphysema and fSAD and significant structural alterations at baseline with rapid progression of fSAD% over one year. Subjects with different progression patterns in the same cross-sectional cluster were identified by longitudinal clustering. CONCLUSION: qCT imaging-based metrics at two visits for former smokers allow for the derivation of four statistically stable clusters associated with unique progression patterns and clinical characteristics. Use of baseline variables and their progression rates enables identification of longitudinal clusters, resulting in a refinement of cross-sectional clusters.
Asunto(s)
Enfermedad Pulmonar Obstructiva Crónica , Enfisema Pulmonar , Estudios Transversales , Humanos , Evaluación de Resultado en la Atención de Salud , Enfermedad Pulmonar Obstructiva Crónica/diagnóstico por imagen , Enfisema Pulmonar/diagnóstico por imagen , FumadoresRESUMEN
BACKGROUND: Quantitative computed tomographic (QCT) imaging-based metrics enable to quantify smoking induced disease alterations and to identify imaging-based clusters for current smokers. We aimed to derive clinically meaningful sub-groups of former smokers using dimensional reduction and clustering methods to develop a new way of COPD phenotyping. METHODS: An imaging-based cluster analysis was performed for 406 former smokers with a comprehensive set of imaging metrics including 75 imaging-based metrics. They consisted of structural and functional variables at 10 segmental and 5 lobar locations. The structural variables included lung shape, branching angle, airway-circularity, airway-wall-thickness, airway diameter; the functional variables included regional ventilation, emphysema percentage, functional small airway disease percentage, Jacobian (volume change), anisotropic deformation index (directional preference in volume change), and tissue fractions at inspiration and expiration. RESULTS: We derived four distinct imaging-based clusters as possible phenotypes with the sizes of 100, 80, 141, and 85, respectively. Cluster 1 subjects were asymptomatic and showed relatively normal airway structure and lung function except airway wall thickening and moderate emphysema. Cluster 2 subjects populated with obese females showed an increase of tissue fraction at inspiration, minimal emphysema, and the lowest progression rate of emphysema. Cluster 3 subjects populated with older males showed small airway narrowing and a decreased tissue fraction at expiration, both indicating air-trapping. Cluster 4 subjects populated with lean males were likely to be severe COPD subjects showing the highest progression rate of emphysema. CONCLUSIONS: QCT imaging-based metrics for former smokers allow for the derivation of statistically stable clusters associated with unique clinical characteristics. This approach helps better categorization of COPD sub-populations; suggesting possible quantitative structural and functional phenotypes.
Asunto(s)
Imagenología Tridimensional/métodos , Enfermedad Pulmonar Obstructiva Crónica/diagnóstico por imagen , Enfermedad Pulmonar Obstructiva Crónica/fisiopatología , Fumar/fisiopatología , Tomografía Computarizada por Rayos X/métodos , Anciano , Estudios de Cohortes , Estudios Transversales , Femenino , Volumen Espiratorio Forzado , Humanos , Masculino , Persona de Mediana Edad , Evaluación de Resultado en la Atención de Salud , Enfermedad Pulmonar Obstructiva Crónica/epidemiología , Fumar/epidemiologíaRESUMEN
Background: Four computed tomography (CT) imaging-based clusters have been identified in a study of the Severe Asthma Research Program (SARP) cohort and have been significantly correlated with clinical and demographic metrics (J Allergy Clin Immunol 2017; 140:690-700.e8). We used a computational fluid dynamics (CFD) model to investigate air flow and aerosol deposition within imaging archetypes representative of the four clusters. Methods: CFD simulations for air flow and 1-8 µm particle transport were performed using CT-based airway models from two healthy subjects and eight asthma subjects. The subject selection criterion was based on the discriminant imaging-based flow-related variables of J(Total) (average local volume expansion in the total lung) and Dh*(sLLL) (normalized airway hydraulic diameter in the left lower lobe), where reduced J(Total) and Dh*(sLLL) indicate reduced regional ventilation and airway constriction, respectively. The analysis focused on the comparisons between all clusters with respect to healthy subjects, between cluster 2 and cluster 4 (nonsevere and severe asthma clusters with airway constriction) and between cluster 3 and cluster 4 (two severe asthma clusters characterized by normal and constricted airways, respectively). Results: Nonsevere asthma cluster 2 and severe asthma cluster 4 subjects characterized by airway constriction had an increase in the deposition fraction (DF) in the left lower lobe. Constricted flows impinged on distal bifurcations resulting in large depositions. Although both cluster 3 (without constriction) and cluster 4 (with constriction) were severe asthma, they exhibited different particle deposition patterns with increasing particle size. The statistical analysis showed that Dh*(sLLL) plays a more important role in particle deposition than J(Total), and regional flow fraction is correlated with DF among lobes for smaller particles. Conclusions: We demonstrated particle deposition characteristics associated with cluster-specific imaging-based metrics such as airway constriction, which could pertain to the design of future drug delivery improvements.
Asunto(s)
Aerosoles/administración & dosificación , Asma/tratamiento farmacológico , Hidrodinámica , Modelos Biológicos , Adulto , Asma/diagnóstico por imagen , Asma/fisiopatología , Simulación por Computador , Femenino , Humanos , Masculino , Persona de Mediana Edad , Tamaño de la Partícula , Índice de Severidad de la Enfermedad , Tomografía Computarizada por Rayos X/métodos , Adulto JovenRESUMEN
BACKGROUND: Classification of COPD is usually based on the severity of airflow, which may not sensitively differentiate subpopulations. Using a multiscale imaging-based cluster analysis (MICA), we aim to identify subpopulations for current smokers with COPD. METHODS: Among the SPIROMICS subjects, we analyzed computed tomography images at total lung capacity (TLC) and residual volume (RV) of 284 current smokers. Functional variables were derived from registration of TLC and RV images, e.g. functional small airways disease (fSAD%). Structural variables were assessed at TLC images, e.g. emphysema and airway wall thickness and diameter. We employed an unsupervised method for clustering. RESULTS: Four clusters were identified. Cluster 1 had relatively normal airway structures; Cluster 2 had an increase of fSAD% and wall thickness; Cluster 3 exhibited a further increase of fSAD% but a decrease of wall thickness and airway diameter; Cluster 4 had a significant increase of fSAD% and emphysema. Clinically, Cluster 1 showed normal FEV1/FVC and low exacerbations. Cluster 4 showed relatively low FEV1/FVC and high exacerbations. While Cluster 2 and Cluster 3 showed similar exacerbations, Cluster 2 had the highest BMI among all clusters. CONCLUSIONS: Association of imaging-based clusters with existing clinical metrics suggests the sensitivity of MICA in differentiating subpopulations.
Asunto(s)
Evaluación de Resultado en la Atención de Salud/métodos , Enfermedad Pulmonar Obstructiva Crónica/diagnóstico por imagen , Enfermedad Pulmonar Obstructiva Crónica/fisiopatología , Fumadores , Tomografía Computarizada por Rayos X/métodos , Adulto , Anciano , Análisis por Conglomerados , Estudios de Cohortes , Estudios Transversales , Femenino , Volumen Espiratorio Forzado/fisiología , Humanos , Masculino , Persona de Mediana EdadRESUMEN
Quantitative computed tomography (QCT) of the lungs plays an increasing role in identifying sub-phenotypes of pathologies previously lumped into broad categories such as chronic obstructive pulmonary disease and asthma. Methods for image matching and linking multiple lung volumes have proven useful in linking structure to function and in the identification of regional longitudinal changes. Here, we seek to improve the accuracy of image matching via the use of a symmetric multi-level non-rigid registration employing an inverse consistent (IC) transformation whereby images are registered both in the forward and reverse directions. To develop the symmetric method, two similarity measures, the sum of squared intensity difference (SSD) and the sum of squared tissue volume difference (SSTVD), were used. The method is based on a novel generic mathematical framework to include forward and backward transformations, simultaneously, eliminating the need to compute the inverse transformation. Two implementations were used to assess the proposed method: a two-dimensional (2-D) implementation using synthetic examples with SSD, and a multi-core CPU and graphics processing unit (GPU) implementation with SSTVD for three-dimensional (3-D) human lung datasets (six normal adults studied at total lung capacity (TLC) and functional residual capacity (FRC)). Success was evaluated in terms of the IC transformation consistency serving to link TLC to FRC. 2-D registration on synthetic images, using both symmetric and non-symmetric SSD methods, and comparison of displacement fields showed that the symmetric method gave a symmetrical grid shape and reduced IC errors, with the mean values of IC errors decreased by 37%. Results for both symmetric and non-symmetric transformations of human datasets showed that the symmetric method gave better results for IC errors in all cases, with mean values of IC errors for the symmetric method lower than the non-symmetric methods using both SSD and SSTVD. The GPU version demonstrated an average of 43 times speedup and ~5.2 times speedup over the single-threaded and 12-threaded CPU versions, respectively. Run times with the GPU were as fast as 2 min. The symmetric method improved the inverse consistency, aiding the use of image registration in the QCT-based evaluation of the lung.
Asunto(s)
Gráficos por Computador , Interpretación de Imagen Asistida por Computador/métodos , Pulmón/anatomía & histología , Humanos , Imagenología Tridimensional , Reproducibilidad de los ResultadosRESUMEN
The purpose of this study was to explore new insights in non-linearity, hysteresis and ventilation heterogeneity of asthmatic human lungs using four-dimensional computed tomography (4D-CT) image data acquired during tidal breathing. Volumetric image data were acquired for 5 non-severe and one severe asthmatic volunteers. Besides 4D-CT image data, function residual capacity and total lung capacity image data during breath-hold were acquired for comparison with dynamic scans. Quantitative results were compared with the previously reported analysis of five healthy human lungs. Using an image registration technique, local variables such as regional ventilation and anisotropic deformation index (ADI) were estimated. Regional ventilation characteristics of non-severe asthmatic subjects were similar to those of healthy subjects, but different from the severe asthmatic subject. Lobar airflow fractions were also well correlated between static and dynamic scans (R2>0.84). However, local ventilation heterogeneity significantly increased during tidal breathing in both healthy and asthmatic subjects relative to that of breath-hold perhaps because of airway resistance present only in dynamic breathing. ADI was used to quantify non-linearity and hysteresis of lung motion during tidal breathing. Non-linearity was greater on inhalation than exhalation among all subjects. However, exhalation non-linearity among asthmatic subjects was greater than healthy subjects and the difference diminished during inhalation. An increase of non-linearity during exhalation in asthmatic subjects accounted for lower hysteresis relative to that of healthy ones. Thus, assessment of non-linearity differences between healthy and asthmatic lungs during exhalation may provide quantitative metrics for subject identification and outcome assessment of new interventions.
Asunto(s)
Asma , Pulmón , Adulto , Asma/diagnóstico por imagen , Asma/fisiopatología , Femenino , Tomografía Computarizada Cuatridimensional , Humanos , Pulmón/diagnóstico por imagen , Pulmón/fisiología , Pulmón/fisiopatología , Masculino , Persona de Mediana Edad , RespiraciónRESUMEN
Introduction: Quantitative CT (QCT) imaging-based metrics have quantified disease alterations in asthma and chronic obstructive pulmonary disease (COPD), respectively. We seek to characterise the similarity and disparity between these groups using QCT-derived airway and parenchymal metrics. Methods: Asthma and COPD subjects (former-smoker status) were selected with a criterion of post-bronchodilator FEV1 <80%. Healthy non-smokers were included as a control group. Inspiratory and expiratory QCT images of 75 asthmatic, 215 COPD and 94 healthy subjects were evaluated. We compared three segmental variables: airway circularity, normalised wall thickness and normalised hydraulic diameter, indicating heterogeneous airway shape, wall thickening and luminal narrowing, respectively. Using an image registration, we also computed six lobar variables including per cent functional small-airway disease, per cent emphysema, tissue fraction at inspiration, fractional-air-volume change, Jacobian and functional metric characterising anisotropic deformation. Results: Compared with healthy subjects, both asthma and COPD subjects demonstrated a decreased airway circularity especially in large and upper lobar airways, and a decreased normalised hydraulic diameter in segmental airways. Besides, COPD subjects had more severe emphysema and small-airway disease, as well as smaller regional tissue fraction and lung deformation, compared with asthmatic subjects. The difference of emphysema, small-airway disease and tissue fraction between asthma and COPD was more prominent in upper and middle lobes. Conclusions: Patients with asthma and COPD, with a persistent FEV1 <80%, demonstrated similar alterations in airway geometry compared with controls, but different degrees of alterations in parenchymal regions. Density-based metrics measured at upper and middle lobes were found to be discriminant variables between patients with asthma and COPD.