Voxel-Wise Comparison of Co-Registered Quantitative CT and Hyperpolarised Gas Diffusion-Weighted MRI Measurements in IPF.

The patterns of idiopathic pulmonary fibrosis (IPF) lung disease that directly correspond to elevated hyperpolarised gas diffusion-weighted (DW) MRI metrics are currently unknown. This study aims to develop a spatial co-registration framework for a voxel-wise comparison of hyperpolarised gas DW-MRI and CALIPER quantitative CT patterns. Sixteen IPF patients underwent 3He DW-MRI and CT at baseline, and eleven patients had a 1-year follow-up DW-MRI. Six healthy volunteers underwent 129Xe DW-MRI at baseline only. Moreover, 3He DW-MRI was indirectly co-registered to CT via spatially aligned 3He ventilation and structural 1H MRI. A voxel-wise comparison of the overlapping 3He apparent diffusion coefficient (ADC) and mean acinar dimension (LmD) maps with CALIPER CT patterns was performed at baseline and after 1 year. The abnormal lung percentage classified with the LmD value, based on a healthy volunteer 129Xe LmD, and CALIPER was compared with a Bland-Altman analysis. The largest DW-MRI metrics were found in the regions classified as honeycombing, and longitudinal DW-MRI changes were observed in the baseline-classified reticular changes and ground-glass opacities regions. A mean bias of -15.3% (95% interval -56.8% to 26.2%) towards CALIPER was observed for the abnormal lung percentage. This suggests DW-MRI may detect microstructural changes in areas of the lung that are determined visibly and quantitatively normal by CT.

Quantitative CT and machine learning classification of fibrotic interstitial lung diseases.

OBJECTIVES: To evaluate quantitative computed tomography (QCT) features and QCT feature-based machine learning (ML) models in classifying interstitial lung diseases (ILDs). To compare QCT-ML and deep learning (DL) models' performance. METHODS: We retrospectively identified 1085 patients with pathologically proven usual interstitial pneumonitis (UIP), nonspecific interstitial pneumonitis (NSIP), and chronic hypersensitivity pneumonitis (CHP) who underwent peri-biopsy chest CT. Kruskal-Wallis test evaluated QCT feature associations with each ILD. QCT features, patient demographics, and pulmonary function test (PFT) results trained eXtreme Gradient Boosting (training/validation set n = 911) yielding 3 models: M1 = QCT features only; M2 = M1 plus age and sex; M3 = M2 plus PFT results. A DL model was also developed. ML and DL model areas under the receiver operating characteristic curve (AUC) and 95% confidence intervals (CIs) were compared for multiclass (UIP vs. NSIP vs. CHP) and binary (UIP vs. non-UIP) classification performances. RESULTS: The majority (69/78 [88%]) of QCT features successfully differentiated the 3 ILDs (adjusted p ≤ 0.05). All QCT-ML models achieved higher AUC than the DL model (multiclass AUC micro-averages 0.910, 0.910, 0.925, and 0.798 and macro-averages 0.895, 0.893, 0.925, and 0.779 for M1, M2, M3, and DL respectively; binary AUC 0.880, 0.899, 0.898, and 0.869 for M1, M2, M3, and DL respectively). M3 demonstrated statistically significant better performance compared to M2 (∆AUC: 0.015, CI: [0.002, 0.029]) for multiclass prediction. CONCLUSIONS: QCT features successfully differentiated pathologically proven UIP, NSIP, and CHP. While QCT-based ML models outperformed a DL model for classifying ILDs, further investigations are warranted to determine if QCT-ML, DL, or a combination will be superior in ILD classification. KEY POINTS: • Quantitative CT features successfully differentiated pathologically proven UIP, NSIP, and CHP. • Our quantitative CT-based machine learning models demonstrated high performance in classifying UIP, NSIP, and CHP histopathology, outperforming a deep learning model. • While our quantitative CT-based machine learning models performed better than a DL model, additional investigations are needed to determine whether either or a combination of both approaches delivers superior diagnostic performance.

Quantitative texture-based analysis of pulmonary parenchymal features on chest CT: comparison with densitometric indices and short-term effect of changes in smoking habit.

PURPOSE: To investigate the correlations between densitometric and Computer Aided Lung Informatics for Pathology Evaluation and Rating (CALIPER)-derived indices of pulmonary emphysema and their change in the short-term period for groups of patients with different smoking habits. METHOD: This retrospective study included 284 subjects from the ITALUNG trial (198 men and 86 women; mean±sd age 60±4 years) who underwent low-dose chest computed tomography at baseline and 2-year follow-up. Subjects were divided into four groups (persistent smokers, restarters, quitters and former smokers) according to their smoking habit at baseline and follow-up. Densitometric and texture analyses were performed, using CALIPER software. A correlation analysis was conducted between CALIPER-derived low-attenuation areas (LAAs) and densitometric indices, including the 15th percentile of the whole-lung attenuation histogram (Perc15) and the relative areas with density ≤-950 HU (RA950). Densitometric indices and LAAs were evaluated at baseline and variation assessed longitudinally with comparisons between groups with different smoking habit. Further analysis of parenchymal changes per pulmonary zone was performed. RESULTS: LAAs were strongly correlated with Perc15 (rs=0.81; p<0.001) and RA950 (rs=0.905; p<0.001). At baseline, the group of smokers showed higher Perc15, lower RA950, lower LAAs (particularly mild sub-class of LAAs) than the group of ex-smokers (p<0.001). At 2-year follow-up, densitometric indices and LAAs increased in persistent smokers, former smokers and quitters (p<0.05). The progression was larger and statistically more significant in quitters (p<0.001). CONCLUSION: CALIPER texture analysis provides an objective measure comparable to traditional density/histogram features to assess the lung parenchymal changes in relation to different smoking habits.

Lung vessel volume evaluated with CALIPER software is an independent predictor of mortality in COVID-19 patients: a multicentric retrospective analysis.

INTRODUCTION: Computer-Aided Lung Informatics for Pathology Evaluation and Ratings (CALIPER) software has already been widely used in the evaluation of interstitial lung diseases (ILD) but has not yet been tested in patients affected by COVID-19. Our aim was to use it to describe the relationship between Coronavirus Disease 2019 (COVID-19) outcome and the CALIPER-detected pulmonary vascular-related structures (VRS). MATERIALS AND METHODS: We performed a multicentric retrospective study enrolling 570 COVID-19 patients who performed a chest CT in emergency settings in two different institutions. Fifty-three age- and sex-matched healthy controls were also identified. Chest CTs were analyzed with CALIPER identifying the percentage of VRS over the total lung parenchyma. Patients were followed for up to 72 days recording mortality and required intensity of care. RESULTS: There was a statistically significant difference in VRS between COVID-19-positive patients and controls (median (iqr) 4.05 (3.74) and 1.57 (0.40) respectively, p = 0.0001). VRS showed an increasing trend with the severity of care, p < 0.0001. The univariate Cox regression model showed that VRS increase is a risk factor for mortality (HR 1.17, p < 0.0001). The multivariate analysis demonstrated that VRS is an independent explanatory factor of mortality along with age (HR 1.13, p < 0.0001). CONCLUSION: Our study suggests that VRS increases with the required intensity of care, and it is an independent explanatory factor for mortality. KEY POINTS: • The percentage of vascular-related structure volume (VRS) in the lung is significatively increased in COVID-19 patients. • VRS showed an increasing trend with the required intensity of care, test for trend p< 0.0001. • Univariate and multivariate Cox models showed that VRS is a significant and independent explanatory factor of mortality.

Vessel-related structures predict UIP pathology in those with a non-IPF pattern on CT.

OBJECTIVES: To determine if a quantitative imaging variable (vessel-related structures [VRS]) could identify subjects with a non-IPF diagnosis CT pattern who were highly likely to have UIP histologically. METHODS: Subjects with a multidisciplinary diagnosis of interstitial lung disease including surgical lung biopsy and chest CT within 1 year of each other were included in the study. Non-contrast CT scans were analyzed using the Computer-Aided Lung Informatics for Pathology Evaluation and Rating (CALIPER) program, which quantifies the amount of various abnormal CT patterns on chest CT. Quantitative data were analyzed relative to pathological diagnosis as well as the qualitative CT pattern. RESULTS: CALIPER-derived volumes of reticulation (p = 0.012), honeycombing (p = 0.017), and VRS (p < 0.001) were associated with a UIP pattern on pathology on univariate analysis but only VRS was associated with a UIP pathology on multivariable analysis (p = 0.013). Using a VRS cut-off of 173 cm3, the sensitivity and specificity for pathological UIP were similar to those for standard qualitative CT assessment (55.9% and 80.4% compared to 60.6% and 80.4%, respectively). VRS differentiated pathological UIP cases in those with a non-IPF diagnosis CT category (p < 0.001) but not in other qualitative CT patterns (typical UIP, probable UIP, and indeterminate for UIP). The rate of pathological UIP in those with VRS greater than 173 cm3 (84.2%) was nearly identical to those who had a qualitative CT pattern of probable UIP (88.9%). CONCLUSIONS: VRS may be an adjunct to CT in predicting pathology in patients with interstitial lung disease. KEY POINTS: • Volume of vessel-related structures (VRS) was associated with usual interstitial pneumonia (UIP) on pathology. • This differentiation arose from those with CT scans with a non-IPF diagnosis imaging pattern. • Higher VRS has similar diagnostic ramifications for UIP as probable UIP, transitively suggesting in patients with high VRS, pathology may be obviated.

Validation of the BRODERS classifier (Benign versus aggRessive nODule Evaluation using Radiomic Stratification), a novel HRCT-based radiomic classifier for indeterminate pulmonary nodules.

INTRODUCTION: Implementation of low-dose chest computed tomography (CT) lung cancer screening and the ever-increasing use of cross-sectional imaging are resulting in the identification of many screen- and incidentally detected indeterminate pulmonary nodules. While the management of nodules with low or high pre-test probability of malignancy is relatively straightforward, those with intermediate pre-test probability commonly require advanced imaging or biopsy. Noninvasive risk stratification tools are highly desirable. METHODS: We previously developed the BRODERS classifier (Benign versus aggRessive nODule Evaluation using Radiomic Stratification), a conventional predictive radiomic model based on eight imaging features capturing nodule location, shape, size, texture and surface characteristics. Herein we report its external validation using a dataset of incidentally identified lung nodules (Vanderbilt University Lung Nodule Registry) in comparison to the Brock model. Area under the curve (AUC), as well as sensitivity, specificity, negative and positive predictive values were calculated. RESULTS: For the entire Vanderbilt validation set (n=170, 54% malignant), the AUC was 0.87 (95% CI 0.81-0.92) for the Brock model and 0.90 (95% CI 0.85-0.94) for the BRODERS model. Using the optimal cut-off determined by Youden's index, the sensitivity was 92.3%, the specificity was 62.0%, the positive (PPV) and negative predictive values (NPV) were 73.7% and 87.5%, respectively. For nodules with intermediate pre-test probability of malignancy, Brock score of 5-65% (n=97), the sensitivity and specificity were 94% and 46%, respectively, the PPV was 78.4% and the NPV was 79.2%. CONCLUSIONS: The BRODERS radiomic predictive model performs well on an independent dataset and may facilitate the management of indeterminate pulmonary nodules.

Automated CT Analysis of Major Forms of Interstitial Lung Disease.

This study aimed to determine diagnostic and prognostic differences in major forms of interstitial lung disease using quantitative CT imaging. A retrospective study of 225 subjects with a multidisciplinary diagnosis of idiopathic pulmonary fibrosis (IPF), interstitial pneumonia with autoimmune features (IPAF), connective tissue disease (CTD), or chronic hypersensitivity pneumonitis (cHP) was conducted. Non-contrast CT scans were analyzed using the Computer Aided Lung Informatics for Pathology Evaluation and Rating (CALIPER) program. Resulting data were analyzed statistically using ANOVA and Student's t-test. Univariate, multivariable, and receiver operating characteristic analyses were conducted on patient mortality data. CALIPER analysis of axial distribution on CT scans in those with IPF demonstrated greater peripheral volumes of reticulation than either CTD (p = 0.033) or cHP (p = 0.007). CTD showed lower peripheral ground-glass opacity than IPF (p = 0.005) and IPAF (p = 0.004). Statistical analysis of zonal distributions revealed reduced lower zone ground-glass opacity in cHP than IPF (p = 0.044) or IPAF (p = 0.018). Analysis of pulmonary vascular-related structure (VRS) volume by diagnosis indicated greater VRS volume in IPF compared to CTD (p = 0.003) and cHP (p = 0.003) as well as in IPAF compared to CTD (p = 0.007) and cHP (p = 0.007). Increased reticulation (p = 0.043) and ground glass opacity (p = 0.032) were predictive of mortality on univariate analysis. Increased pulmonary VRS volume was predictive of mortality (p < 0.001) even after multivariate analysis (p = 0.041). Quantitative CT imaging revealed significant differences between ILD diagnoses in specific CT findings in axial and, to a lesser degree, zonal distributions. Increased pulmonary VRS volume seems to be associated with both diagnosis and survival.

Do we need to see to believe?-radiomics for lung nodule classification and lung cancer risk stratification.

Despite multiple recent advances, the diagnosis and management of lung cancer remain challenging and it continues to be the deadliest malignancy. In 2011, the National Lung Screening Trial (NLST) reported 20% reduction in lung cancer related mortality using annual low dose chest computed tomography (CT). These results led to the approval and nationwide establishment of lung cancer CT-based lung cancer screening programs. These findings have been further validated by the recently published Nederlands-Leuvens Longkanker Screenings Onderzoek (NELSON) and Multicentric Italian Lung Detection (MILD) trials, the latter showing benefit of screening even beyond the 5 years. However, the implementation of lung cancer screening has been impeded by several challenges, including the differentiation between benign and malignant nodules, the large number of false positive studies and the detection of indolent, potentially clinically insignificant lung cancers (overdiagnosis). Hence, the development of non-invasive strategies to accurately classify and risk stratify screen-detected pulmonary nodules in order to individualize clinical management remains a high priority area of research. Radiomics is a recently coined term which refers to the process of imaging feature extraction and quantitative analysis of clinical diagnostic images to characterize the nodule phenotype beyond what is possible with conventional radiologist assessment. Even though it is still in early phase, several studies have already demonstrated that radiomics approaches are potentially useful for lung nodule classification, risk stratification, individualized management and prediction of overall prognosis. The goal of this review is to summarize the current literature regarding the radiomics of screen-detected lung nodules, highlight potential challenges and discuss its clinical application along with future goals and challenges.

Quantitative CT Analysis of Diffuse Lung Disease.

Quantitative analysis of thin-section CT of the chest has a growing role in the clinical evaluation and management of diffuse lung diseases. This heterogeneous group includes diseases with markedly different prognoses and treatment options. Quantitative tools can assist in both accurate diagnosis and longitudinal management by improving characterization and quantification of disease and increasing the reproducibility of disease severity assessment. Furthermore, a quantitative index of disease severity may serve as a useful tool or surrogate endpoint in evaluating treatment efficacy. The authors explore the role of quantitative imaging tools in the evaluation and management of diffuse lung diseases. Lung parenchymal features can be classified with threshold, histogram, morphologic, and texture-analysis-based methods. Quantitative CT analysis has been applied in obstructive, infiltrative, and restrictive pulmonary diseases including emphysema, cystic fibrosis, asthma, idiopathic pulmonary fibrosis, hypersensitivity pneumonitis, connective tissue-related interstitial lung disease, and combined pulmonary fibrosis and emphysema. Some challenges limiting the development and practical application of current quantitative analysis tools include the quality of training data, lack of standard criteria to validate the accuracy of the results, and lack of real-world assessments of the impact on outcomes. Artifacts such as patient motion or metallic beam hardening, variation in inspiratory effort, differences in image acquisition and reconstruction techniques, or inaccurate preprocessing steps such as segmentation of anatomic structures may lead to inaccurate classification. Despite these challenges, as new techniques emerge, quantitative analysis is developing into a viable tool to supplement the traditional visual assessment of diffuse lung diseases and to provide decision support regarding diagnosis, prognosis, and longitudinal evaluation of disease. ©RSNA, 2019.

Computed Tomography-Based Score Indicative of Lung Cancer Aggression (SILA) Predicts the Degree of Histologic Tissue Invasion and Patient Survival in Lung Adenocarcinoma Spectrum.

OBJECTIVE: Most computed tomography (CT)-detected lung cancers are adenocarcinomas (ACs), representing lesions with variable tissue invasion, aggressiveness, and clinical outcome. Visual radiologic characterization of AC pulmonary nodules is both inconsistent and inadequate to confidently predict histopathologic classification or prognosis. Comprehensive pathologic interpretation requires full nodule resection. We have described a computerized scoring system for AC detected on CT scans that can noninvasively estimate the degree of histologic invasion and simultaneously predict patient survival. METHODS: The Computer-Aided Nodule Assessment and Risk Yield has been validated to characterize CT-detected nodules across the spectrum of AC. With the use of unsupervised clustering, nine natural exemplars were identified as basic radiographic features of AC nodules. We now introduce the Score Indicative of Lung Cancer Aggression (SILA), which is a cumulative aggregate of normalized distributions of ordered Computer-Aided Nodule Assessment and Risk Yield exemplars. The SILA values for each of 237 unique nodules in AC were compared with the histopathologically defined maximum linear extent of tumor invasion. With use of the SILA, Kaplan-Meier survival and Cox proportionality analysis were performed on patients with stage I AC, who comprised a subset of our cohort. RESULTS: The SILA discriminated between indolent and invasive AC (p < 0.0001). In addition, prediction of linear extent of histopathologic tumor invasion was possible. In stage I AC, three separate SILA prognosis groups were identified: indolent, intermediate, and poor, with 5-year survival rates of 100%, 79%, 58%, respectively. Cox proportionality hazard modeling predicted a 50% increase in mortality, for a 0.1 unit increase in the SILA over a median follow-up time of 3.6 years (p < 0.0002). CONCLUSIONS: The SILA is a computer-based analytic measure allowing noninvasive approximation of histologic invasion and prediction of patient survival in CT-detected AC nodules.

Spirometric assessment of emphysema presence and severity as measured by quantitative CT and CT-based radiomics in COPD.

BACKGROUND: The mechanisms underlying airflow obstruction in COPD cannot be distinguished by standard spirometry. We ascertain whether mathematical modeling of airway biomechanical properties, as assessed from spirometry, could provide estimates of emphysema presence and severity, as quantified by computed tomography (CT) metrics and CT-based radiomics. METHODS: We quantified presence and severity of emphysema by standard CT metrics (VIDA) and co-registration analysis (ImbioLDA) of inspiratory-expiratory CT in 194 COPD patients who underwent pulmonary function testing. According to percentages of low attenuation area below - 950 Hounsfield Units (%LAA-950insp) patients were classified as having no emphysema (NE) with %LAA-950insp < 6, moderate emphysema (ME) with %LAA-950insp ≥ 6 and < 14, and severe emphysema (SE) with %LAA-950insp ≥ 14. We also obtained stratified clusters of emphysema CT features by an automated unsupervised radiomics approach (CALIPER). An emphysema severity index (ESI), derived from mathematical modeling of the maximum expiratory flow-volume curve descending limb, was compared with pulmonary function data and the three CT classifications of emphysema presence and severity as derived from CT metrics and radiomics. RESULTS: ESI mean values and pulmonary function data differed significantly in the subgroups with different emphysema degree classified by VIDA, ImbioLDA and CALIPER (p < 0.001 by ANOVA). ESI differentiated NE from ME/SE CT-classified patients (sensitivity 0.80, specificity 0.85, AUC 0.86) and SE from ME CT-classified patients (sensitivity 0.82, specificity 0.87, AUC 0.88). CONCLUSIONS: Presence and severity of emphysema in patients with COPD, as quantified by CT metrics and radiomics can be estimated by mathematical modeling of airway function as derived from standard spirometry.

Comparison of changes in rectal area and volume during MR evacuation proctography in healthy and constipated adults.

BACKGROUND: During proctography, rectal emptying is visually estimated by the reduction in rectal area. The correlation between changes in rectal area, which is a surrogate measure of volume, is unclear. Our aims were to compare the change in rectal area and volume during magnetic resonance (MR) proctography and to compare these parameters with rectal balloon expulsion time (BET). METHODS: In 49 healthy and 46 constipated participants, we measured BET and rectal area and volume with a software program before and after participants expelled rectal gel during proctography. KEY RESULTS: All participants completed both tests; six healthy and 17 constipated patients had a prolonged (>60 seconds) BET. During evacuation, the reduction in rectal area and volume was lower in participants with an abnormal than a normal BET (P < 0.01). The reduction in rectal area and volume were strongly correlated (r = 0.93, P < 0.001) and equivalent for identifying participants with abnormal BET. Among participants with less evacuation, the reduction in rectal area underestimated the reduction in rectal volume. A rectocele larger than 2 cm was observed in eight of 18 (44%) participants in whom the difference between change in volume and area was ˃10% but only 14 of 77 (18%) participants in whom the difference was ≤10% (P = 0.03). CONCLUSIONS: Measured with MR proctography, the rectal area is reasonably accurate for quantifying rectal emptying and equivalent to rectal volume for distinguishing between normal and abnormal BET. When evacuation is reduced, the change in rectal area may underestimate the change in rectal volume.

Correction: Novel high-resolution computed tomography-based radiomic classifier for screen-identified pulmonary nodules in the National Lung Screening Trial.

[This corrects the article DOI: 10.1371/journal.pone.0196910.].

Assessing the inter-observer variability of Computer-Aided Nodule Assessment and Risk Yield (CANARY) to characterize lung adenocarcinomas.

Lung adenocarcinoma (ADC), the most common lung cancer type, is recognized increasingly as a disease spectrum. To guide individualized patient care, a non-invasive means of distinguishing indolent from aggressive ADC subtypes is needed urgently. Computer-Aided Nodule Assessment and Risk Yield (CANARY) is a novel computed tomography (CT) tool that characterizes early ADCs by detecting nine distinct CT voxel classes, representing a spectrum of lepidic to invasive growth, within an ADC. CANARY characterization has been shown to correlate with ADC histology and patient outcomes. This study evaluated the inter-observer variability of CANARY analysis. Three novice observers segmented and analyzed independently 95 biopsy-confirmed lung ADCs from Vanderbilt University Medical Center/Nashville Veterans Administration Tennessee Valley Healthcare system (VUMC/TVHS) and the Mayo Clinic (Mayo). Inter-observer variability was measured using intra-class correlation coefficient (ICC). The average ICC for all CANARY classes was 0.828 (95% CI 0.76, 0.895) for the VUMC/TVHS cohort, and 0.852 (95% CI 0.804, 0.901) for the Mayo cohort. The most invasive voxel classes had the highest ICC values. To determine whether nodule size influenced inter-observer variability, an additional cohort of 49 sub-centimeter nodules from Mayo were also segmented by three observers, with similar ICC results. Our study demonstrates that CANARY ADC classification between novice CANARY users has an acceptably low degree of variability, and supports the further development of CANARY for clinical application.

Novel high-resolution computed tomography-based radiomic classifier for screen-identified pulmonary nodules in the National Lung Screening Trial.

PURPOSE: Optimization of the clinical management of screen-detected lung nodules is needed to avoid unnecessary diagnostic interventions. Herein we demonstrate the potential value of a novel radiomics-based approach for the classification of screen-detected indeterminate nodules. MATERIAL AND METHODS: Independent quantitative variables assessing various radiologic nodule features such as sphericity, flatness, elongation, spiculation, lobulation and curvature were developed from the NLST dataset using 726 indeterminate nodules (all ≥ 7 mm, benign, n = 318 and malignant, n = 408). Multivariate analysis was performed using least absolute shrinkage and selection operator (LASSO) method for variable selection and regularization in order to enhance the prediction accuracy and interpretability of the multivariate model. The bootstrapping method was then applied for the internal validation and the optimism-corrected AUC was reported for the final model. RESULTS: Eight of the originally considered 57 quantitative radiologic features were selected by LASSO multivariate modeling. These 8 features include variables capturing Location: vertical location (Offset carina centroid z), Size: volume estimate (Minimum enclosing brick), Shape: flatness, Density: texture analysis (Score Indicative of Lesion/Lung Aggression/Abnormality (SILA) texture), and surface characteristics: surface complexity (Maximum shape index and Average shape index), and estimates of surface curvature (Average positive mean curvature and Minimum mean curvature), all with P<0.01. The optimism-corrected AUC for these 8 features is 0.939. CONCLUSIONS: Our novel radiomic LDCT-based approach for indeterminate screen-detected nodule characterization appears extremely promising however independent external validation is needed.

Computer-Aided Nodule Assessment and Risk Yield Risk Management of Adenocarcinoma: The Future of Imaging?

Increased clinical use of chest high-resolution computed tomography results in increased identification of lung adenocarcinomas and persistent subsolid opacities. However, these lesions range from very indolent to extremely aggressive tumors. Clinically relevant diagnostic tools to noninvasively risk stratify and guide individualized management of these lesions are lacking. Research efforts investigating semiquantitative measures to decrease interrater and intrarater variability are emerging, and in some cases steps have been taken to automate this process. However, many such methods currently are still suboptimal, require validation and are not yet clinically applicable. The computer-aided nodule assessment and risk yield software application represents a validated tool for the automated, quantitative, and noninvasive tool for risk stratification of adenocarcinoma lung nodules. Computer-aided nodule assessment and risk yield correlates well with consensus histology and postsurgical patient outcomes, and therefore may help to guide individualized patient management, for example, in identification of nodules amenable to radiological surveillance, or in need of adjunctive therapy.

Noninvasive Computed Tomography-based Risk Stratification of Lung Adenocarcinomas in the National Lung Screening Trial.

RATIONALE: Screening for lung cancer using low-dose computed tomography (CT) reduces lung cancer mortality. However, in addition to a high rate of benign nodules, lung cancer screening detects a large number of indolent cancers that generally belong to the adenocarcinoma spectrum. Individualized management of screen-detected adenocarcinomas would be facilitated by noninvasive risk stratification. OBJECTIVES: To validate that Computer-Aided Nodule Assessment and Risk Yield (CANARY), a novel image analysis software, successfully risk stratifies screen-detected lung adenocarcinomas based on clinical disease outcomes. METHODS: We identified retrospective 294 eligible patients diagnosed with lung adenocarcinoma spectrum lesions in the low-dose CT arm of the National Lung Screening Trial. The last low-dose CT scan before the diagnosis of lung adenocarcinoma was analyzed using CANARY blinded to clinical data. Based on their parametric CANARY signatures, all the lung adenocarcinoma nodules were risk stratified into three groups. CANARY risk groups were compared using survival analysis for progression-free survival. MEASUREMENTS AND MAIN RESULTS: A total of 294 patients were included in the analysis. Kaplan-Meier analysis of all the 294 adenocarcinoma nodules stratified into the Good, Intermediate, and Poor CANARY risk groups yielded distinct progression-free survival curves (P < 0.0001). This observation was confirmed in the unadjusted and adjusted (age, sex, race, and smoking status) progression-free survival analysis of all stage I cases. CONCLUSIONS: CANARY allows the noninvasive risk stratification of lung adenocarcinomas into three groups with distinct post-treatment progression-free survival. Our results suggest that CANARY could ultimately facilitate individualized management of incidentally or screen-detected lung adenocarcinomas.

Measurements of the left atrium and pulmonary veins for analysis of reverse structural remodeling following cardiac ablation therapy.

RATIONALE AND OBJECTIVES: Geometric analysis of the left atrium and pulmonary veins is important for assessing reverse structural remodeling following cardiac ablation therapy. Most volumetric analysis techniques, however, require laborious manual tracing of image cross-sections. Pulmonary vein diameters are typically measured at the junction between the left atrium and pulmonary veins, called the pulmonary vein ostia, with manually drawn lines on volume renderings or in image slices. In this work, we describe a technique for making semi-automatic measurements of left atrial volume and pulmonary vein diameters from high resolution CT scans and demonstrate its use for analyzing reverse structural remodeling following cardiac ablation therapy. METHODS: The left atrium and pulmonary veins are segmented from high-resolution computed tomography (CT) volumes using a 3D volumetric approach and cut planes are interactively positioned to separate the pulmonary veins from the body of the left atrium. Left atrial volume and pulmonary vein ostial diameters are then automatically computed from the segmented structures. Validation experiments are conducted to evaluate accuracy and repeatability of the measurements. Accuracy is assessed by comparing left atrial volumes computed with the proposed methodology to a manual slice-by-slice tracing approach. Repeatability is assessed by making repeated volume and diameter measurements on duplicated and randomized datasets. The proposed techniques were then utilized in a study of 21 patients from the Catheter Ablation versus Antiarrhythmic Drug Therapy for Atrial Fibrillation Trial (CABANA) pilot study who were scanned both before and approximately 3 months following ablation therapy. RESULTS: In the high resolution CT scans the left atrial volume measurements show high accuracy with a mean absolute difference of 2.3±1.9 cm(3) between volumes computed with the proposed methodology and a manual slice-by-slice tracing approach. In the intra-rater repeatability study, the mean absolute difference in left atrial volume was 4.7±2.5 cm(3) and 4.4±3.4 cm(3) for the two raters. Intra-rater repeatability for pulmonary vein diameters ranged from 0.9 to 2.3 mm. The inter-rater repeatability for left atrial volume was 5.8±5.1 cm(3) and inter-rater repeatability for pulmonary vein diameter measurements ranged from 1.4 to 2.3 mm. In the patient study, significant (p<.05) decreases in left atrial volume and all four pulmonary vein diameters were observed. The absolute change in LA volume was 20.0 cm(3), 95%CI [12.6, 27.5]. The left inferior pulmonary vein diameter decreased 2.1 mm, 95%CI [0.4, 3.7], the left superior pulmonary vein diameter decreased 3.2 mm, 95%CI [1.0, 5.4], the right inferior pulmonary vein diameter decreased 1.5 mm, 95%CI [0.3, 2.7], and the right superior pulmonary vein diameter decreased 2.8 mm, 95%CI [1.4, 4.3]. CONCLUSIONS: Using the proposed techniques, we demonstrate high accuracy of left atrial volume measurements as well as high repeatability for left atrial volume and pulmonary vein diameter measurements. Following cardiac ablation therapy, a significant decrease was observed for left atrial volume as well as all four pulmonary vein diameters.