Automatic thoracic aorta calcium quantification using deep learning in non-contrast ECG-gated CT images.

Thoracic aorta calcium (TAC) can be assessed from cardiac computed tomography (CT) studies to improve cardiovascular risk prediction. The aim of this study was to develop a fully automatic system to detect TAC and to evaluate its performance for classifying the patients into four TAC risk categories. The method started by segmenting the thoracic aorta, combining three UNets trained with axial, sagittal and coronal CT images. Afterwards, the surrounding lesion candidates were classified using three combined convolutional neural networks (CNNs) trained with orthogonal patches. Image datasets included 1190 non-enhanced ECG-gated cardiac CT studies from a cohort of cardiovascular patients (age 57 ± 9 years, 80% men, 65% TAC > 0). In the test set (N = 119), the combination of UNets was able to successfully segment the thoracic aorta with a mean volume difference of 0.3 ± 11.7 ml (<6%) and a median Dice coefficient of 0.947. The combined CNNs accurately classified the lesion candidates and 87% of the patients (N = 104) were accurately placed in their corresponding risk categories (Kappa = 0.826, ICC = 0.9915). TAC measurement can be estimated automatically from cardiac CT images using UNets to isolate the thoracic aorta and CNNs to classify calcified lesions.

Echocardiographic Measurements of Left Heart Chamber Size in a Large Cohort of Subjects: Comparison of Body Surface Area and Height Indexing to Account for Effects of Obesity.

BACKGROUND: The assessment of cardiac chamber size in the obese population is a challenging subject. Values usually indexed to body surface area (BSA) are smaller in obese subjects and prone to overcorrection. The aims of this study were to find reference thresholds to account for the effects of obesity among a large cohort of patients and to evaluate indexing to height as an alternative to BSA. METHODS: The past 10 years of records from a single echocardiography unit were retrospectively analyzed, and 14,007 subjects without known cardiac disease were included (mean age, 45 ± 15 years; 54% women; 20% obese). Measurements included left atrial diameter, area, and volume, left ventricular (LV) end-diastolic and end-systolic diameters, aortic root diameter, and LV mass. Absolute, BSA-indexed, and height-indexed maximum thresholds (mean + 1.96 SDs) were calculated. Allometric indexing of the form variable/heightß was tested. Correlation coefficients between indexed and absolute values were calculated to evaluate their proportional association (ideally r = 1). Correlations between indexed values and body size represented residual associations to be minimized (ideally r = 0). RESULTS: The strongest association of echocardiographic measurements with body size was observed for BSA (r = 0.36-0.63), whereas the isometric and allometric height models showed lower comparable values (r = 0.28-0.48). Positive correlations with body mass index were mostly observed for left atrial size (r ≈ 0.36) and LV mass (r ≈ 0.36) measurements. Values of the scaling exponent ß for allometric height indexing were 1.72 for left atrial volume and 2.33 for LV mass. Correlations between indexed and absolute values were higher for height than BSA (0.80-0.98 vs 0.44-0.92). Correlations between indexed values and height were closer to 0 than for BSA, particularly using the allometric model. The overcorrection observed with increasing obesity class after BSA indexing was avoided after height indexing. CONCLUSIONS: Unlike BSA, height indexing provided adequate body size scaling of left heart chamber size, avoiding overcorrection using allometric models in particular.

Thoracic Aorta Calcium Detection and Quantification Using Convolutional Neural Networks in a Large Cohort of Intermediate-Risk Patients.

Arterial calcification is an independent predictor of cardiovascular disease (CVD) events whereas thoracic aorta calcium (TAC) detection might anticipate extracoronary outcomes. In this work, we trained six convolutional neural networks (CNNs) to detect aortic calcifications and to automate the TAC score assessment in intermediate CVD risk patients. Cardiac computed tomography images from 1415 patients were analyzed together with their aortic geometry previously assessed. Orthogonal patches centered in each aortic candidate lesion were reconstructed and a dataset with 19,790 images (61% positives) was built. Three single-input 2D CNNs were trained using axial, coronal and sagittal patches together with two multi-input 2.5D CNNs combining the orthogonal patches and identifying their best regional combination (BRC) in terms of lesion location. Aortic calcifications were concentrated in the descending (66%) and aortic arch (26%) portions. The BRC of axial patches to detect ascending or aortic arch lesions and sagittal images for the descending portion had the best performance: 0.954 F1-Score, 98.4% sensitivity, 87% of the subjects correctly classified in their TAC category and an average false positive TAC score per patient of 30. A CNN that combined axial and sagittal patches depending on the candidate aortic location ensured an accurate TAC score prediction.