Comparison of two ellipsoidal models for the estimation of left ventricular end-systolic stress in patients with significant coronary artery disease

Background

The shape of the left ventricle (LV) is an important index to explore cardiac pathophysiology. A comparison was provided to estimate circumferential, longitudinal, and radial wall stress in LV based on the thick-walled ellipsoidal models of Mirsky and Ghista-Sandler for discriminating significant coronary artery disease (CAD) patients from no CAD patients.

Materials and Methods

According to the angiography findings, 82 patients with CAD were divided into two groups: 25 patients without significant CAD and 57 patients with significant CAD of single vessel and multivessel. An ellipsoidal LV geometry was used to calculate end-systolic passive stress as the mechanical behavior of LV. Echocardiographic views-based measurements of LV diameters used to estimate the end-systolic wall stress.

Results

Circumferential wall stress between the control group and significant CAD groups was significantly elevated for the Ghista model (P = 0.008); also, radial and longitudinal stress of the multi-vessel CAD group was significantly higher than the control group (P = 0.01 and P = 0.005, respectively). All stress parameters of the multi-vessel CAD group were statistically significant compared to the control group for the Mirsky model. Receiver operating characteristics curve analysis was shown the circumferential stress of multi-vessel CAD with an area under the curve (AUC) of 0.736 for the Ghista model and an AUC of 0.742 for the Mirsky model.

Conclusion

These results indicated that Ghista and Mirsky model estimates of circumferential passive stress were the potential biomechanical markers to predict patients with multi-vessel CAD. It could be a noninvasive and helpful tool to quantify the contractility of LV.

Robust facial expression recognition system in higher poses

Facial expression recognition (FER) has numerous applications in computer security, neuroscience, psychology, and engineering. Owing to its non-intrusiveness, it is considered a useful technology for combating crime. However, FER is plagued with several challenges, the most serious of which is its poor prediction accuracy in severe head poses. The aim of this study, therefore, is to improve the recognition accuracy in severe head poses by proposing a robust 3D head-tracking algorithm based on an ellipsoidal model, advanced ensemble of AdaBoost, and saturated vector machine (SVM). The FER features are tracked from one frame to the next using the ellipsoidal tracking model, and the visible expressive facial key points are extracted using Gabor filters. The ensemble algorithm (Ada-AdaSVM) is then used for feature selection and classification. The proposed technique is evaluated using the Bosphorus, BU-3DFE, MMI, CK + , and BP4D-Spontaneous facial expression databases. The overall performance is outstanding.