RESUMEN
In this paper, we propose a fast and accurate deep network-based object tracking method, which combines feature representation, template tracking and foreground detection into a single framework for robust tracking. The proposed framework consists of a backbone network, which feeds into two parallel networks, TmpNet for template tracking and FgNet for foreground detection. The backbone network is a pre-trained modified VGG network, in which a few parameters need to be fine-tuned for adapting to the tracked object. FgNet is a fully convolutional network to distinguish the foreground from background in a pixel-to-pixel manner. The parameter in TmpNet is the learned channel-wise target template, which initializes in the first frame and performs fast template tracking in the test frames. To enable each component to work closely with each other, we use a multi-task loss to end-to-end train the proposed framework. In online tracking, we combine the score maps from TmpNet and FgNet to find the optimal tracking results. Experimental results on object tracking benchmarks demonstrate that our approach achieves favorable tracking accuracy against the state-of-the-art trackers while running at a real-time speed of 38 fps.
RESUMEN
Exercise is an effective measure for preventing and treating cardiovascular diseases, although the exact molecular mechanism remains unknown. Previous studies have shown that both irisin and exosomes can improve the course of cardiovascular disease independently. Therefore, it is speculated that the cardiovascular protective effect of exercise is also related to its ability to regulate the concentrations of irisin and exosomes in the circulatory system. In this review, the potential synergistic interactions between irisin and exosomes are examined, as well as the underlying mechanisms including the AMPK/PI3K/AKT pathway, the TGFß1/Smad2/3 pathway, the PI3K/AKT/VEGF pathway, and the PTEN/PINK1/Parkin pathway are examined. This paper provides evidence to propose that exercise promotes the release of exosomes enriched with irisin, miR-486-5p and miR-342-5p from skeletal muscles, which results in the activation protective networks in the cardiovascular system. Moreover, the potential synergistic effect in exosomal cargo can provide new ideas for clinical research of exercise mimics.
RESUMEN
In the past, several methods based on iterative solution of pressure-Poisson equation have been developed for measurement of pressure from phase-contrast magnetic resonance (PC-MR) data. In this paper, a non-iterative harmonics-based orthogonal projection method is discussed which can keep the pressures measured based on the Navier-Stokes equation independent of the path of integration. The gradient of pressure calculated with Navier-Stokes equation is expanded with a series of orthogonal basis functions, and is subsequently projected onto an integrable subspace. Before the projection step however, a scheme is devised to eliminate the discontinuity at the vessel boundaries. The approach was applied to velocities obtained from computational fluid dynamics (CFD) simulations of stenotic flow and compared with pressures independently obtained by CFD. Additionally, MR velocity data measured in in-vitro phantom models with different degree of stenoses and different flow rates were used to test the algorithm and results were compared with CFD simulations. The pressure results obtained from the new method were also compared with pressures calculated by an iterative solution to the pressure-Poisson equation. Experiments have shown that the proposed approach is faster and is less sensitive to noise.