Structural finite-element analysis (FEA) has been widely used to study the biomechanics of human tissues and organs, as well as tissue–medical device interactions, and treatment strategies. However, patient-specific FEA models usually require complex procedures to set up and long computing times to obtain final simulation results, preventing prompt feedback to clinicians in time-sensitive clinical applications. In this study, by using machine learning techniques, we developed a deep learning (DL) model to directly estimate the stress distributions of the aorta. The DL model was designed and trained to take the input of FEA and directly output the aortic wall stress distributions, bypassing the FEA calculation process. The trained DL model is capable of predicting the stress distributions with average errors of 0.492% and 0.891% in the Von Mises stress distribution and peak Von Mises stress, respectively. This study marks, to our knowledge, the first study that demonstrates the feasibility and great potential of using the DL technique as a fast and accurate surrogate of FEA for stress analysis.

Geometric features of the aorta are linked to patient risk of rupture in the clinical decision to electively repair an ascending aortic aneurysm (AsAA). Previous approaches have focused on relationship between intuitive geometric features (e.g. diameter and curvature) and wall stress. This work investigates the feasibility of a machine learning approach to establish the linkages between shape features and FEA predicted AsAA rupture risk, and it may serve as a faster surrogate for FEA associated with long simulation time and numerical convergence issues. This method consists of four main steps: (1) constructing a statistical shape model (SSM) from clinical 3D CT images of AsAA patients; (2) generating a dataset of representative aneurysm shapes and obtaining FEA predicted risk scores defined as systolic pressure divided by rupture pressure (rupture is determined by a threshold criterion); (3) establishing relationship between shape features and risk by using classifiers and regressors; and (4) evaluating such relationship in cross validation. The results show that SSM parameters can be used as strong shape features to make predictions of risk scores consistent with FEA, which lead to an average risk classification accuracy of 95.58% by using support vector machine and an average regression error of 0.0332 by using support vector regression, while intuitive geometric features have relatively weak performance. Compared to FEA, this machine learning approach is magnitudes faster. In our future studies, material properties and inhomogeneous thickness will be incorporated into the models and learning algorithms, which may lead to a practical system for clinical applications.

Objectives Studies have shown that patients harboring bicuspid aortic valve (BAV) or bovine aortic arch (BAA) are more likely to develop ascending aortic aneurysm (AsAA) than the general population. A thorough quantification of the AsAA tissue properties for these patient groups may offer insight into the underlying mechanisms of AsAA development in these patients. Thus, the objective of this study was to investigate and compare the mechanical and microstructural properties of aortic tissues from AsAA patients with and without concomitant BAV or BAA. Materials and methods AsAA (n = 20), BAV (n = 20) and BAA (n = 15) human tissues were obtained from patients who underwent elective AsAA surgery. Planar biaxial and uniaxial failure tests were used to characterize the mechanical and failure properties of the tissues, respectively. Histological analysis was performed to detect the medial degenerative characteristics of aortic aneurysm. Individual layer thickness and composition were quantified for each patient group. Results The circumferential (CIRC) response of the BAV samples was stiffer than both AsAA (p = 0.473) and BAA (p = 0.152) tissues at low load. The BAV tissues were nearly isotropic while AsAA and BAA tissues were anisotropic. The areal strain of BAV samples were significantly less than AsAA (p = 0.041) and BAA (p = 0.004) tissues at a low load. The BAA samples were similar to the AsAA samples in both mechanical and failure properties. On the microstructural level, all samples displayed moderate medial degeneration characterized by elastin fragmentation, cell loss, mucoid accumulation and fibrosis. The ultimate tensile strength of BAV and BAA tissues were also found to decrease with age. Conclusions The BAV tissues were stiffer than both AsAA and BAA tissues, and the BAA tissues were similar to the AsAA tissues. The BAV samples were thinnest with less elastin than AsAA and BAA samples, which may attribute to the loss of extensibility at low load of these tissues. No apparent difference in failure mechanics among the tissue groups suggests that each of the patient groups may have a similar risk of rupture.

Objective Bovine pericardium (BP) has been identified as a choice biomaterial for the development of surgical bioprosthetic heart valves (BHV) and transcatheter aortic valves (TAV). Porcine pericardium (PP) and younger BP have been suggested as candidates TAV leaflet biomaterials for smaller-profile devices due to their reduced thickness; however, their mechanical and structural properties remain to be fully characterized. This study characterized the material properties of chemically treated thick (PPK) and thin (PPN) PP, as well as fetal (FBP), calf (CBP) and adult (ABP) BP tissues in order to better understand their mechanical behavior. Methods Planar biaxial testing and uniaxial failure testing methods were employed to quantify tissue mechanical responses and failure properties. Fiber characteristics were examined using histological analysis. Results ABP and CBP tissues were significantly stiffer and stronger than the younger FBP tissues. Histological analysis revealed a significantly larger concentration of thin immature collagen fibers in the FBP tissues than in the ABP and CBP tissues. While PP tissues were thinnest, they were stiffer and less extensible than the BP tissues. Conclusions Due to comparable mechanical properties but significantly reduced thickness, CBP tissue may be a more suitable material for TAV manufacturing than ABP tissue. FBP tissue, despite its reduced thickness and higher flexibility, was weaker and should be studied in more detail. Although PP tissues are the thinnest, they were least extensible and failed at earlier strain than BP tissues. The differences between PP and BP tissues should be further investigated and suggest that they should not be used interchangeably in the manufacturing of TAV.