Going beyond Cardiomegaly: Evaluation of Cardiac Chamber Enlargement at Non-Electrocardiographically Gated Multidetector CT: Current Techniques, Limitations, and Clinical Implications

Opportunistic Screening for Atrial Fibrillation on Routine Chest Computed Tomography

PURPOSE

Quantitative biomarkers from chest computed tomography (CT) can facilitate the incidental detection of important diseases. Atrial fibrillation (AFib) substantially increases the risk for comorbid conditions including stroke. This study investigated the relationship between AFib status and left atrial enlargement (LAE) on CT.

MATERIALS AND METHODS

A total of 500 consecutive patients who had undergone nongated chest CTs were included, and left atrium maximal axial cross-sectional area (LA-MACSA), left atrium anterior-posterior dimension (LA-AP), and vertebral body cross-sectional area (VB-Area) were measured. Height, weight, age, sex, and diagnosis of AFib were obtained from the medical record. Parametric statistical analyses and receiver operating characteristic curves were performed. Machine learning classifiers were run with clinical risk factors and LA measurements to predict patients with AFib.

RESULTS

Eighty-five patients with a diagnosis of AFib were identified. Mean LA-MACSA and LA-AP were significantly larger in patients with AFib than in patients without AFib (28.63 vs. 20.53 cm 2 , P <0.000001; 4.34 vs. 3.5 cm, P <0.000001, respectively), both with area under the curves (AUCs) of 0.73. Multivariable logistic regression analysis including age, sex, and VB-Area with LA-MACSA improved the AUC for predicting AFib (AUC=0.77). An LA-MACSA threshold of 30 cm 2 demonstrated high specificity for AFib diagnosis at 92% and sensitivity of 48%, and LA-AP threshold at 4.5 cm demonstrated 90% specificity and 42% sensitivity. A Bayesian machine learning model using age, sex, height, body surface area, and LA-MACSA predicted AFib with an AUC of 0.743.

CONCLUSIONS

LA-MACSA or LA-AP can be rapidly measured from routine chest CT, and when >30 cm 2 and >4.5 cm, respectively, are specific indicators to predict patients at increased risk for AFib.

Opportunistic screening at chest computed tomography: literature review of cardiovascular significance of incidental findings

Background and Objective

Several incidental cardiovascular findings are present in a routine chest computed tomography (CT) scan, many of which do not make it to the final radiology report. However, these findings have important clinical implications, particularly providing prognosis and risk-stratification for future cardiovascular events. The purpose of this article is to review the literature on these incidental cardiovascular findings in a routine chest CT and inform the radiologist on their clinical relevance.

Methods

A time unlimited review of PubMed and Web of Science was performed by using relevant keywords. Articles in English that involved adults were included.

Key Content and Findings

Coronary artery calcification (CAC) is the most common incidental cardiac finding detected in a routine chest CT and is a significant predictor of cardiovascular events. Noncoronary vascular calcifications in chest CT include aortic valve, mitral annulus, and thoracic aortic calcifications (TAC). Among these, aortic valve calcification (AVC) has the strongest association with coronary artery disease and cardiovascular events. Additional cardiac findings such as myocardial scar and left ventricular size and noncardiac findings such as thoracic fat, bone density, hepatic steatosis, and breast artery calcifications can also help in risk stratification and patient management.

Conclusions

The radiologist interpreting a routine chest CT should be cognizant of the incidental cardiovascular findings, which helps in the diagnosis and risk-stratification of cardiovascular disease. This will guide appropriate referral and management.

Posteroanterior Chest X-ray Image Classification with a Multilayer 1D Convolutional Neural Network-Based Classifier for Cardiomegaly Level Screening

Palpitations, chest tightness, and shortness of breath are early indications of cardiomegaly, which is an asymptomatic disease. Their causes and treatment strategies are different due to differing indications. Hence, early screening of cardiomegaly levels can be used to make a strategy for administering drugs and surgical treatments. In this study, we will establish a multilayer one-dimensional (1D) convolutional neural network (CNN)-based classifier for automatic cardiomegaly level screening based on chest X-ray (CXR) image classification in frontal posteroanterior view. Using two-round 1D convolutional processes in the convolutional pooling layer, two-dimensional (2D) feature maps can be converted into feature signals, which can enhance their characteristics for identifying normal condition and cardiomegaly levels. In the classification layer, a classifier based on gray relational analysis, which has a straightforward mathematical operation, is used to screen the cardiomegaly levels. Based on the collected datasets from the National Institutes of Health CXR image database, the proposed multilayer 1D CNN-based classifier with K-fold cross-validation has promising results for the intended medical purpose, with precision of 97.80%, recall of 98.20%, accuracy of 98.00%, and F1 score of 0.9799.

Delayed bolus-tracking trigger at CT correlates with cardiac dysfunction and suboptimal portovenous contrast phase

OBJECTIVE

To assess whether delayed trigger during bolus-tracking for CT correlates with reduced heart function and suboptimal portovenous contrast phase.

METHODS AND MATERIALS

Patients who underwent portovenous abdominal CT using bolus-tracking and echocardiography within 2 weeks were included and excluded if there was a non-standard contrast injection. The bolus trigger time (BTT) at 100 Hounsfield units in the abdominal aorta, patient age, congestive heart failure (CHF) history, and ejection fraction were recorded. Two radiologists scored the liver contrast phase (1-5, 5 being an optimal portovenous phase). When applicable, the BTT and contrast score of the most recent comparison examination with equivalent technical parameters were also recorded. Simple linear regression (univariate) was used to test for associations with trigger time.

RESULTS

114 patients with a mean age of 61 ± 15 years fulfilled criteria. The mean trigger time was 18 ± 6 s (range: 6-38 s) and the mean ejection fraction was 52 ± 12% (range: 19-69%). A longer bolus trigger had a significant correlation with reduced ejection fraction (P = 0.0018), lower hepatic contrast score (P < 0.0001), history of CHF (P = 0.0212), and older age (P = 0.0223). Contrast score differences between the study exam and available prior exams revealed score differences of 0 (n = 73), 1 (n = 15) and 2 (n = 5); these were associated, respectively, with a mean bolus trigger time difference between exams of 2 s (range, 0-6 s), 6 s (range, 1-15 s), and 11 s (range, 5-13). The P-value comparing bolus trigger time and contrast score differences was less than 0.0001. A lower ejection fraction also significantly correlated with suboptimal PV contrast phase (P < 0.0001).

CONCLUSION

Delayed time to trigger during bolus-tracking for CT can indicate cardiac dysfunction and may not adequately adjust to provide an optimal portovenous contrast phase.