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.

This work aimed to automatically segment and classify the coronary arteries with either normal or anomalous origin from the aorta (AAOCA) using convolutional neural networks (CNNs), seeking to enhance and fasten clinician diagnosis. We implemented three single-view 2D Attention U-Nets with 3D view integration and trained them to automatically segment the aortic root and coronary arteries of 124 computed tomography angiographies (CTAs), with normal coronaries or AAOCA. Furthermore, we automatically classified the segmented geometries as normal or AAOCA using a decision tree model. For CTAs in the test set (n = 13), we obtained median Dice score coefficients of 0.95 and 0.84 for the aortic root and the coronary arteries, respectively. Moreover, the classification between normal and AAOCA showed excellent performance with accuracy, precision, and recall all equal to 1 in the test set. We developed a deep learning-based method to automatically segment and classify normal coronary and AAOCA. Our results represent a step towards an automatic screening and risk profiling of patients with AAOCA, based on CTA.

Artificial Neural Networks (ANNs) are a tool in approximation theory widely used to solve interpolation problems. In fact, ANNs can be assimilated to functions since they take an input and return an output. The structure of the specifically adopted network determines the underlying approximation space, while the form of the function is selected by fixing the parameters of the network. In the present paper, we consider one-hidden layer ANNs with a feedforward architecture, also referred to as shallow or two-layer networks, so that the structure is determined by the number and types of neurons. The determination of the parameters that define the function, called training, is done via the resolution of the approximation problem, so by imposing the interpolation through a set of specific nodes. We present the case where the parameters are trained using a procedure that is referred to as Extreme Learning Machine (ELM) that leads to a linear interpolation problem. In such hypotheses, the existence of an ANN interpolating function is guaranteed. Given that the ANN is interpolating, the error incurred occurs outside the sampling interpolation nodes provided by the user. In this study, various choices of nodes are analyzed: equispaced, Chebychev, and randomly selected ones. Then, the focus is on regular target functions, for which it is known that interpolation can lead to spurious oscillations, a phenomenon that in the ANN literature is referred to as overfitting. We obtain good accuracy of the ANN interpolating function in all tested cases using these different types of interpolating nodes and different types of neurons. The following study is conducted starting from the well-known bell-shaped Runge example, which makes it clear that the construction of a global interpolating polynomial is accurate only if trained on suitably chosen nodes, ad example the Chebychev ones. In order to evaluate the behavior when the number of interpolation nodes increases, we increase the number of neurons in our network and compare it with the interpolating polynomial. We test using Runge’s function and other well-known examples with different regularities. As expected, the accuracy of the approximation with a global polynomial increases only if the Chebychev nodes are considered. Instead, the error for the ANN interpolating function always decays, and in most cases we observe that the convergence follows what is observed in the polynomial case on Chebychev nodes, despite the set of nodes used for training. Then we can conclude that the use of such an ANN defeats the Runge phenomenon. Our results show the power of ANNs to achieve excellent approximations when interpolating regular functions also starting from uniform and random nodes, particularly for Runge’s function.

Background: Anomalous Aortic Origin of a Coronary Artery (AAOCA) is a congenital condition that can lead to ischemia and sudden cardiac death. Current diagnostic tools are unable to fully quantify the pathological behavior that occurs mainly with physical effort. Methods: Patients’ computed tomography scans and centerline-based geometric quantities were used to develop three-dimensional computer-aided design models of the main anatomical variants of AAOCA. Blood pressure ranging from rest to extreme effort was simulated through structural finite element analyses, and the pressurized geometries were analyzed to evaluate coronary lumen cross-sectional areas and variations at the different loading conditions. Results: We simulated 39 subjects, demonstrating the ability to reproduce accurately the patient-specific anatomy of different AAOCA variants and capture pathological behaviors. AAOCAs with intramural courses showed compression along the proximal segment with a caliber reduction ranging from 0.14% to 18.87% at different pressure levels. The percentage of proximal narrowing relative to the distal segment was greater than any other type of anomalous course and exceeded 50% with simulated exertion. Conclusions: The present study proposes a computational pipeline to investigate conditions not reproducible in clinical practice, providing information to support decision-making in the management of AAOCA patients.

Background: The relationship between the increases in pulse pressure (PP) and arterial stiffness determined by aging or systemic hypertension has been widely reported. These findings are supported by large-cohort analysis conducted in well-known populations, such as the Framingham Study. However, there is evidence that an age-PP curvilinear relationship may exist in hypertensive subjects. This study aimed to evaluate the age-related change in pulse pressure and arterial stiffness in a population-based study. Methods: Carotid femoral Pulse Wave Velocity (cfPWV) were obtained in 2075 subjects. Results: Age-related changes of PP showed a curvilinear relationship (R=0.39, p<0.0001) in normotensive subjects, with a nadir at around 50 years of age. On the other hand, the age-cfPWV relationship showed a linear and positive correlation (R=0.72, p<0.0001). PP also showed a curvilinear relationship with age (R=0.36, p<0.0001) in hypertensive subjects, with a nadir around 50 years of age. The age-cfPWV relationship showed a linear and positive correlation (R=0.55, p<0.0001). Similar results were observed in the adult population (age≥16 years). Multivariate analysis showed that age, sex, cfPWV, and mean arterial pressure are determinants of PP values in the entire population; however, this result is not uniform when the different subgroups are analyse. Conclusion: In conclusion, age-related changes in PP showed a curvilinear relationship and no parallelism with the age-cfPWV relationship for both normotensive and hypertensive subjects. The determinants of PP impact it differently depending on age and the pathological condition of the subject.

Cardiovascular risk is normally assessed using clinical risk factors but it can be refined using non-invasive infra-clinical markers. Intima-Media Thickness (IMT) is recognized as an early indicator of cardiovascular disease. Carotid Wall Stress (CWS) can be calculated using arterial pressure and carotid size (diameter and IMT). Generally, IMT is measured during diastole when it reaches its maximum value. However, it changes during the cardiac cycle and a time-dependant waveform can be obtained using B-mode ultrasound images. In this work we calculated CWS considering three different approaches for IMT assessment: (i) constant IMT (standard diastolic value), (ii) estimated IMT from diameter waveform (assuming a constant cross-sectional wall area) and (iii) continuously measured IMT. Our results showed that maximum wall stress depends on the IMT estimation method. Systolic CWS progressively increased using the three approaches (p<0.024). We conclude that maximum CWS is highly dependent on wall thickness and accurate IMT measures during systole should be encouraged.