Confidence-Aware Severity Assessment of Lung Disease from Chest X-Rays Using Deep Neural Network on a Multi-Reader Dataset.

In this study, we present a method based on Monte Carlo Dropout (MCD) as Bayesian neural network (BNN) approximation for confidence-aware severity classification of lung diseases in COVID-19 patients using chest X-rays (CXRs). Trained and tested on 1208 CXRs from Hospital 1 in the USA, the model categorizes severity into four levels (i.e., normal, mild, moderate, and severe) based on lung consolidation and opacity. Severity labels, determined by the median consensus of five radiologists, serve as the reference standard. The model's performance is internally validated against evaluations from an additional radiologist and two residents that were excluded from the median. The performance of the model is further evaluated on additional internal and external datasets comprising 2200 CXRs from the same hospital and 1300 CXRs from Hospital 2 in South Korea. The model achieves an average area under the curve (AUC) of 0.94 ± 0.01 across all classes in the primary dataset, surpassing human readers in each severity class and achieves a higher Kendall correlation coefficient (KCC) of 0.80 ± 0.03. The performance of the model is consistent across varied datasets, highlighting its generalization. A key aspect of the model is its predictive uncertainty (PU), which is inversely related to the level of agreement among radiologists, particularly in mild and moderate cases. The study concludes that the model outperforms human readers in severity assessment and maintains consistent accuracy across diverse datasets. Its ability to provide confidence measures in predictions is pivotal for potential clinical use, underscoring the BNN's role in enhancing diagnostic precision in lung disease analysis through CXR.

Epicardial adipose tissue attenuation on computed tomography in women with coronary microvascular dysfunction: A pilot, hypothesis generating study.

BACKGROUND: Patients with myocardial ischemia without obstructive coronary artery disease often have coronary microvascular dysfunction (CMD) and associated increased risk of cardiovascular (CV) events and anginal hospitalizations. Epicardial adipose tissue (EAT) covers much of the myocardium and coronary arteries and when dysfunctional, secretes proinflammatory cytokines and is associated with CV events. While oxidative stress and systemic inflammation are associated with CMD, the relationship between EAT and CMD in women is not well known. METHODS: Women diagnosed with CMD (n = 21) who underwent coronary computed tomography with coronary artery calcium (CAC) scoring were compared to a reference group (RG) of women referred for CAC screening for preventive risk assessment (n = 181). EAT attenuation (Hounsfield units (HU)) was measured adjacent to the proximal right coronary artery, along with subcutaneous adipose tissue (SCAT). Two-sample t-tests with unequal variances were utilized. RESULTS: Mean age of the CMD group was 56 ± 8 years and body mass index (BMI) was 31.6 ± 6.8 kg/m2. CV risk factors in the CMD group were prevalent: 67 % hypertension, 44 % hyperlipidemia, and 33 % diabetes. Both CMD and RG had similar CAC score (25.86 ± 59.54 vs. 24.17 ± 104.6; p = 0.21. In the CMD group, 67 % had a CAC of 0. Minimal atherosclerosis (CAD-RADS 1) was present in 76 % of women with CMD. The CMD group had lower EAT attenuation than RG (-103.3 ± 6.33 HU vs. -97.9 ± 8.3 HU, p = 0.009, respectively). There were no differences in SCAT attenuation. Hypertension, smoking history, age, BMI, and CAC score did not correlate with EAT in either of the groups. CONCLUSIONS: Women with CMD have decreased EAT attenuation compared to RG women. EAT-mediated inflammation and changes in vascular tone may be a mechanistic contributor to abnormal microvascular reactivity. Clinical trials testing therapeutic strategies to decrease EAT may be warranted in the management of CMD.

Differential effect of atorvastatin and pravastatin on thoracic spine attenuation: A sub-analysis of a randomized clinical trial.

BACKGROUND: Statins reduce cardiovascular events and may improve bone mineral density. METHODS: We conducted a sub-analysis of a randomized clinical trial that investigated the differential effect of moderate vs intensive low-density lipoprotein cholesterol (LDL-C) lowering therapies on coronary artery calcium (CAC) scores, and used the acquired images to assess the change in radiological attenuation of selected thoracic vertebrae. Baseline and 12-month unenhanced chest CT scans were performed in 420 hyperlipidemic, postmenopausal women randomized to atorvastatin (ATV) 80 mg/day or pravastatin (PRV) 40 mg/day in the Beyond Endorsed Lipid Lowering with Electron Beam Tomography Scanning (BELLES) trial. Bone attenuation was measured in three contiguous thoracic vertebrae at baseline and 12 months. RESULTS: There were no differences in baseline demographic and clinical characteristics between treatment arms. The median percent lowering (interquartile range) in LDL-C was significantly greater with ATV than PRV [-53 (-69 to 20)% vs -28 (-55 to 74)%, p < 0.001], although the CAC score change was similar [12 (-63 to 208)% vs 13 (-75 to 358)%; p = 0.44]. At follow-up, the median bone attenuation loss was significantly greater with PRV than with ATV [-2.6 (-27 to 11)% vs 0 (-11 to 25)%; p < 0.001]. The attenuation loss in the PRV group was comparable to that of a historical untreated general population sample. In the entire cohort, the changes in LDL-C and total cholesterol were inversely correlated with bone attenuation change (p < 0.01). In adjusted multivariable linear regression analyses, race and percent change in LDL-C were independent predictors of bone attenuation change. Age, body mass index, history of smoking, diabetes mellitus, hypertension, peripheral vascular disease, or hormone replacement therapy did not affect percent change in BMD. CONCLUSIONS: These findings support the hypothesis that there is an interaction between bone and cardiometabolic health and that intensive lipid lowering has a beneficial effect on bone health.

Relationships of pericoronary and epicardial fat measurements in male and female patients with and without coronary artery disease.

INTRODUCTION: Although pericoronary adipose tissue (PCAT) is a component of the epicardial adipose tissue (EAT) depot, they may have different associations to coronary artery disease (CAD). We explored relationships between pericoronary adipose tissue mean attenuation (PCATMA) and EAT measurements in coronary CT angiography (CCTA) in patients with and without CAD. MATERIAL AND METHODS: CCTA scans of 185 non-CAD and 81 CAD patients (86.4% >50% stenosis) were included and retrospectively analyzed. PCATMA and EAT density/volume were measured and analyzed by sex, including associations with age, risk factors and tube voltage using linear regression models. RESULTS: In non-CAD and CAD, mean PCATMA and EAT volume were higher in men than in women (non-CAD: -92.5 ± 10.6HU vs -96.2 ± 8.4HU, and 174.4 ± 69.1 cm3 vs 124.1 ± 57.3 cm3; CAD: -92.2 ± 9.0HU vs -97.4 ± 9.7HU, and 193.6 ± 62.5 cm3 vs 148.5 ± 50.5 cm3 (p < 0.05)). EAT density was slightly lower in men than women in non-CAD (-96.4 ± 6.3HU vs -94.4 ± 5.5HU (p < 0.05)), and similar in CAD (-98.2 ± 5.2HU vs 98.2 ± 6.4HU). There was strong correlation between PCATMA and EAT density (non-CAD: r = 0.725, p < 0.001, CAD: r = 0.686, p < 0.001) but no correlation between PCATMA and EAT volume (non-CAD: r = 0.018, p = 0.81, CAD: r = -0.055, p = 0.63). A weak inverse association was found between EAT density and EAT volume (non-CAD: r = -0.244, p < 0.001, CAD: r = -0.263, p = 0.02). In linear regression models, EAT density was significantly associated with PCATMA in both non-CAD and CAD patients independent of risk factors and tube voltage. CONCLUSION: In CAD and non-CAD patients, EAT density, but not EAT volume, showed significant associations with PCATMA. Compared to women, men had higher PCATMA and EAT volume independently of disease status, but similar or slightly lower EAT density. Differences in trends and relations of PCATMA and EAT by sex could indicate that personalized interpretation and thresholding is needed.

Evaluation of pericoronary adipose tissue attenuation on CT.

Pericoronary adipose tissue (PCAT) is the fat deposit surrounding coronary arteries. Although PCAT is part of the larger epicardial adipose tissue (EAT) depot, it has different pathophysiological features and roles in the atherosclerosis process. While EAT evaluation has been studied for years, PCAT evaluation is a relatively new concept. PCAT, especially the mean attenuation derived from CT images may be used to evaluate the inflammatory status of coronary arteries non-invasively. The most commonly used measure, PCATMA, is the mean attenuation of adipose tissue of 3 mm thickness around the proximal right coronary artery with a length of 40 mm. PCATMA can be analyzed on a per-lesion, per-vessel or per-patient basis. Apart from PCATMA, other measures for PCAT have been studied, such as thickness, and volume. Studies have shown associations between PCATMA and anatomical and functional severity of coronary artery disease. PCATMA is associated with plaque components and high-risk plaque features, and can discriminate patients with flow obstructing stenosis and myocardial infarction. Whether PCATMA has value on an individual patient basis remains to be determined. Furthermore, CT imaging settings, such as kV levels and clinical factors such as age and sex affect PCATMA measurements, which complicate implementation in clinical practice. For PCATMA to be widely implemented, a standardized methodology is needed. This review gives an overview of reported PCAT methodologies used in current literature and the potential use cases in clinical practice.

Inter-observer variability of expert-derived morphologic risk predictors in aortic dissection.

OBJECTIVES: Establishing the reproducibility of expert-derived measurements on CTA exams of aortic dissection is clinically important and paramount for ground-truth determination for machine learning. METHODS: Four independent observers retrospectively evaluated CTA exams of 72 patients with uncomplicated Stanford type B aortic dissection and assessed the reproducibility of a recently proposed combination of four morphologic risk predictors (maximum aortic diameter, false lumen circumferential angle, false lumen outflow, and intercostal arteries). For the first inter-observer variability assessment, 47 CTA scans from one aortic center were evaluated by expert-observer 1 in an unconstrained clinical assessment without a standardized workflow and compared to a composite of three expert-observers (observers 2-4) using a standardized workflow. A second inter-observer variability assessment on 30 out of the 47 CTA scans compared observers 3 and 4 with a constrained, standardized workflow. A third inter-observer variability assessment was done after specialized training and tested between observers 3 and 4 in an external population of 25 CTA scans. Inter-observer agreement was assessed with intraclass correlation coefficients (ICCs) and Bland-Altman plots. RESULTS: Pre-training ICCs of the four morphologic features ranged from 0.04 (-0.05 to 0.13) to 0.68 (0.49-0.81) between observer 1 and observers 2-4 and from 0.50 (0.32-0.69) to 0.89 (0.78-0.95) between observers 3 and 4. ICCs improved after training ranging from 0.69 (0.52-0.87) to 0.97 (0.94-0.99), and Bland-Altman analysis showed decreased bias and limits of agreement. CONCLUSIONS: Manual morphologic feature measurements on CTA images can be optimized resulting in improved inter-observer reliability. This is essential for robust ground-truth determination for machine learning models. KEY POINTS: • Clinical fashion manual measurements of aortic CTA imaging features showed poor inter-observer reproducibility. • A standardized workflow with standardized training resulted in substantial improvements with excellent inter-observer reproducibility. • Robust ground truth labels obtained manually with excellent inter-observer reproducibility are key to develop reliable machine learning models.

Evaluating the Performance of a Convolutional Neural Network Algorithm for Measuring Thoracic Aortic Diameters in a Heterogeneous Population.

The purpose of this work was to assess the performance of a convolutional neural network (CNN) for automatic thoracic aortic measurements in a heterogeneous population. From June 2018 to May 2019, this study retrospectively analyzed 250 chest CT scans with or without contrast enhancement and electrocardiographic gating from a heterogeneous population with or without aortic pathologic findings. Aortic diameters at nine locations and maximum aortic diameter were measured manually and with an algorithm (Artificial Intelligence Rad Companion Chest CT prototype, Siemens Healthineers) by using a CNN. A total of 233 examinations performed with 15 scanners from three vendors in 233 patients (median age, 65 years [IQR, 54-72 years]; 144 men) were analyzed: 68 (29%) without pathologic findings, 72 (31%) with aneurysm, 51 (22%) with dissection, and 42 (18%) with repair. No evidence of a difference was observed in maximum aortic diameter between manual and automatic measurements (P = .48). Overall measurements displayed a bias of -1.5 mm and a coefficient of repeatability of 8.0 mm at Bland-Altman analyses. Contrast enhancement, location, pathologic finding, and positioning inaccuracy negatively influenced reproducibility (P < .003). Sites with dissection or repair showed lower agreement than did sites without. The CNN performed well in measuring thoracic aortic diameters in a heterogeneous multivendor CT dataset. Keywords: CT, Vascular, Aorta © RSNA, 2022.

COVID-19 pneumonia chest radiographic severity score: variability assessment among experienced and in-training radiologists and creation of a multireader composite score database for artificial intelligence algorithm development.

OBJECTIVE: The purpose was to evaluate reader variability between experienced and in-training radiologists of COVID-19 pneumonia severity on chest radiograph (CXR), and to create a multireader database suitable for AI development. METHODS: In this study, CXRs from polymerase chain reaction positive COVID-19 patients were reviewed. Six experienced cardiothoracic radiologists and two residents classified each CXR according to severity. One radiologist performed the classification twice to assess intraobserver variability. Severity classification was assessed using a 4-class system: normal (0), mild (1), moderate (2), and severe (3). A median severity score (Rad Med) for each CXR was determined for the six radiologists for development of a multireader database (XCOMS). Kendal Tau correlation and percentage of disagreement were calculated to assess variability. RESULTS: A total of 397 patients (1208 CXRs) were included (mean age, 60 years SD ± 1), 189 men). Interobserver variability between the radiologists ranges between 0.67 and 0.78. Compared to the Rad Med score, the radiologists show good correlation between 0.79-0.88. Residents show slightly lower interobserver agreement of 0.66 with each other and between 0.69 and 0.71 with experienced radiologists. Intraobserver agreement was high with a correlation coefficient of 0.77. In 220 (18%), 707 (59%), 259 (21%) and 22 (2%) CXRs there was a 0, 1, 2 or 3 class-difference. In 594 (50%) CXRs the median scores of the residents and the radiologists were similar, in 578 (48%) and 36 (3%) CXRs there was a 1 and 2 class-difference. CONCLUSION: Experienced and in-training radiologists demonstrate good inter- and intraobserver agreement in COVID-19 pneumonia severity classification. A higher percentage of disagreement was observed in moderate cases, which may affect training of AI algorithms. ADVANCES IN KNOWLEDGE: Most AI algorithms are trained on data labeled by a single expert. This study shows that for COVID-19 X-ray severity classification there is significant variability and disagreement between radiologist and between residents.

Registry of Aortic Diseases to Model Adverse Events and Progression (ROADMAP) in Uncomplicated Type B Aortic Dissection: Study Design and Rationale.

Purpose: To describe the design and methodological approach of a multicenter, retrospective study to externally validate a clinical and imaging-based model for predicting the risk of late adverse events in patients with initially uncomplicated type B aortic dissection (uTBAD). Materials and Methods: The Registry of Aortic Diseases to Model Adverse Events and Progression (ROADMAP) is a collaboration between 10 academic aortic centers in North America and Europe. Two centers have previously developed and internally validated a recently developed risk prediction model. Clinical and imaging data from eight ROADMAP centers will be used for external validation. Patients with uTBAD who survived the initial hospitalization between January 1, 2001, and December 31, 2013, with follow-up until 2020, will be retrospectively identified. Clinical and imaging data from the index hospitalization and all follow-up encounters will be collected at each center and transferred to the coordinating center for analysis. Baseline and follow-up CT scans will be evaluated by cardiovascular imaging experts using a standardized technique. Results: The primary end point is the occurrence of late adverse events, defined as aneurysm formation (≥6 cm), rapid expansion of the aorta (≥1 cm/y), fatal or nonfatal aortic rupture, new refractory pain, uncontrollable hypertension, and organ or limb malperfusion. The previously derived multivariable model will be externally validated by using Cox proportional hazards regression modeling. Conclusion: This study will show whether a recent clinical and imaging-based risk prediction model for patients with uTBAD can be generalized to a larger population, which is an important step toward individualized risk stratification and therapy.Keywords: CT Angiography, Vascular, Aorta, Dissection, Outcomes Analysis, Aortic Dissection, MRI, TEVAR© RSNA, 2022See also the commentary by Rajiah in this issue.

Feasibility of Hepatic T1-Mapping and Extracellular Volume Quantification on Routine Cardiac Magnetic Resonance Imaging in Patients with Infiltrative and Systemic Disorders.

RATIONALE AND OBJECTIVES: Cardiac magnetic resonance imaging (CMR) is commonly obtained to evaluate for myocardial infiltrative disorders and fibrosis. Pre- and post-Gadolinium contrast T1-mapping sequences are employed to estimate interstitial expansion using extracellular volume fraction (ECV). Given the proximity of the liver to the heart, T1 and ECV quantification of the liver is feasible on CMR. The purpose of this study was to evaluate for hepatic measures of fibrosis and interstitial expansion in patients with amyloidosis or systemic disease on CMR. MATERIALS AND METHODS: Myocardial and hepatic native T1 values were measured retrospectively using a cardiac short axis modified Look-Locker inversion recovery sequence. Myocardial and hepatic ECV were calculated using pre- and post-contrast T1 and blood pool values according to the following formula: ECV = (Δ(1/T1) myocardium or liver and/or Δ(1/T1) blood)x(1 - hematocrit). Patients were divided into three cohorts by final diagnosis: amyloidosis, systemic disease (e.g. sarcoid, scleroderma), and controls (EF > 50, no ischemia). RESULTS: Of the 135 patients who underwent CMR, 22 had cardiac amyloidosis (age 59.9 ± 12.6 yrs, 41% female), 20 had systemic disease (age 50.9 ± 13.4 yrs, 35% female), and 93 were controls (age 49.5 ± 17.3 yrs, 50% female). Myocardial T1 and ECV values were highest for patients with amyloid, second highest for systemic disease, and least for controls (T1: 1169 ± 92 vs 1101 ± 53 vs 1027 ± 73 ms, p < 0.0001; ECV: 0.47 ± 0.11 vs 0.31 ± 0.05 vs 0.27 ± 0.04, p < 0.0001). Hepatic T1 and ECV were similarly higher in patients with amyloid and systemic disease compared to controls (T1: 646 ± 101 vs 660 ± 93 vs 595 ± 58 ms, p < 0.0001; ECV: 0.38 ± 0.08 vs 0.37 ± 0.05 vs 0.31 ± 0.03, p < 0.0001). There was a positive correlation between hepatic T1 and ECV (R2 = 0.282, p < 0.0001). No patients had abnormal liver function tests or clinical liver disease. CONCLUSION: Hepatic ECV quantification on CMR in patients with amyloidosis and systemic disorders is feasible. Further longitudinal investigation regarding detection of early or subclinical liver disease is warranted.

Season and clinical factors influence epicardial adipose tissue attenuation measurement on computed tomography and may hamper its utilization as a risk marker.

BACKGROUND AND AIMS: A small difference in epicardial adipose tissue (EAT) attenuation measured on computed tomography (CT) imaging has been reported between patients who suffered coronary events and event-free patients. EAT consists of beige adipose tissue functionally similar to brown adipose tissue and its attenuation may be affected by seasonal temperature variations and clinical factors. METHODS: We retrospectively measured EAT attenuation on cardiac CT in 597 patients submitted to cardiac CT imaging for coronary artery calcium scoring. All scans were performed on the same CT scanner during the summer (June, July, August) or winter (December, January, February) months. EAT attenuation in Hounsfield units (HU) was assessed near the proximal right coronary artery in an area free of artifacts. For comparison, subcutaneous adipose tissue (SCAT) attenuation was measure along the midaxillary line. RESULTS: The clinical and demographic characteristics of patients scanned during the summer (N = 253) and the winter (N = 344) months were similar. One third of patients were women, one quarter used statins and anti-hypertensive drugs and 30% were obese. The EAT attenuation was significantly lower during the summer than the winter months (-98.17 ± 6.94 HUs vs -95.64 ± 7.99 HUs; p<0.001). Sex, white race, body mass index, diabetes status, treatment with statins and anti-hypertensive agents significantly modulated the seasonal variation in EAT attenuation. SCAT attenuation was not affected by season or other factors. CONCLUSIONS: The measurement of EAT attenuation is complex and is affected by season, demographic and clinical factors. These factors may hinder the utilization of EAT attenuation as a biomarker of cardiovascular risk.

Can the degree of coronary collateralization be used in clinical routine as a valid angiographic parameter of viability?

The success rate of percutaneous coronary artery intervention (PCI) of chronic total occlusion (CTO) lesions have increased in the recent years. However, improvement of function is only possible when significant myocardial viability is present. One of the most important factors of maintaining myocardial viability is the opening and development of collaterals. Our hypothesis was that with a higher degree of collaterals more viable myocardium is present. In 38 patients we compared the degree of collaterals, evaluated with a conventional coronary angiogram (CCA) and graded by the Rentrop classification to transmural extent of the scar obtained in a viability study with magnetic resonance (MRI). We found a statistically significant association of the degree of collaterals determined with Rentrop method and transmural extent of the scar as measured by CMR (p = 0.001; Tau = -0.144). Additionally, associations showed an increase in the ratio between viable vs. non-viable myocardium with the degree of collaterals. Our study suggests that it may be beneficial to routinely grade the collaterals at angiography in patients with CTO as an assessment of myocardial viability.

Coronary Computed Tomography Angiography Compared With Single Photon Emission Computed Tomography Myocardial Perfusion Imaging as a Guide to Optimal Medical Therapy in Patients Presenting With Stable Angina: The RESCUE Trial.

Background The RESCUE (Randomized Evaluation of Patients with Stable Angina Comparing Utilization of Noninvasive Examinations) trial was a randomized, controlled, multicenter, comparative efficacy outcomes trial designed to assess whether initial testing with coronary computed tomographic angiography (CCTA) is noninferior to single photon emission computed tomography (SPECT) myocardial perfusion imaging in directing patients with stable angina to optimal medical therapy alone or optimal medical therapy with revascularization. Methods and Results The end point was first major adverse cardiovascular event (MACE) (cardiac death or myocardial infarction), or revascularization. Noninferiority margin for CCTA was set a priori as a hazard ratio (HR) of 1.3 (95% CI=0, 1.605). One thousand fifty participants from 44 sites were randomized to CCTA (n=518) or SPECT (n=532). Mean follow-up time was 16.2 (SD 7.9) months. There were no cardiac-related deaths. In patients with a negative CCTA there was 1 acute myocardial infarction; in patients with a negative SPECT examination there were 2 acute myocardial infarctions; and for positive CCTA and SPECT, 1 acute myocardial infarction each. Participants in the CCTA arm had a similar rate of MACE or revascularization compared with those in the SPECT myocardial perfusion imaging arm, (HR, 1.03; 95% CI=0.61-1.75) (P=0.19). CCTA segment involvement by a stenosis of ≥50% diameter was a better predictor of MACE and revascularization at 1 year (P=0.02) than the percent reversible defect size by SPECT myocardial perfusion imaging. Four (1.2%) patients with negative CCTA compared with 14 (3.2%) with negative SPECT had MACE or revascularization (P=0.03). Conclusions There was no difference in outcomes of patients who had stable angina and who underwent CCTA in comparison to SPECT as the first imaging test directing them to optimal medical therapy alone or with revascularization. CCTA was a better predictor of MACE and revascularization. Registration Information URL: https://www.clinicaltrials.gov/. Identifier: NCT01262625.

Cost-effectiveness for imaging stable ischemic disease.

Stable ischemic heart disease remains a major cause of morbidity and mortality. Although there are multiple imaging modalities to diagnose and/or assist in the clinical management, the most cost-effective approach remains unclear. We reviewed the relevant and recent evidence-based clinical studies and trials to suggest the most cost-effective approach to stable ischemic heart disease. The limitations of these studies are discussed. Incorporating the results of recent multicenter trials, we suggest that for appropriate patients with coronary artery disease with any degree of stenosis or presence of coronary calcium, optimal medical therapy may be most cost-effective. Invasive coronary angiography and/or coronary revascularization would be primarily for non-responders or >/=50% left main stenosis. Stress cardiac magnetic imaging would be performed for those patients with non-diagnostic coronary CT angiography from motion and non-responders from optimal medical therapy in non-diagnostic coronary CT angiography group from high coronary calcium. These paths seem to be safe and cost-effective but requires modeling for confirmation.