ABSTRACT
Open set recognition (OSR) aims to correctly recognize the known classes and reject the unknown classes for increasing the reliability of the recognition system. The distance-based loss is often employed in deep neural networks-based OSR methods to constrain the latent representation of known classes. However, the optimization is usually conducted using the nondirectional euclidean distance in a single feature space without considering the potential impact of spatial distribution. To address this problem, we propose orientational distribution learning (ODL) with hierarchical spatial attention for OSR. In ODL, the spatial distribution of feature representation is optimized orientationally to increase the discriminability of decision boundaries for open set recognition. Then, a hierarchical spatial attention mechanism is proposed to assist ODL to capture the global distribution dependencies in the feature space based on spatial relationships. Moreover, a composite feature space is constructed to integrate the features from different layers and different mapping approaches, and it can well enrich the representation information. Finally, a decision-level fusion method is developed to combine the composite feature space and the naive feature space for producing a more comprehensive classification result. The effectiveness of ODL has been demonstrated on various benchmark datasets, and ODL achieves state-of-the-art performance.
ABSTRACT
BACKGROUND: Olmesartan is a type of angiotensin II receptor inhibitor that can reduce the incidence of cardiovascular events. However, its role in the function of endothelial progenitor cells in atherosclerosis patients is still unclear. Our study aimed to explore the effects and mechanism of olmesartan on endothelial progenitor cell mobilization and function in carotid atherosclerosis. MATERIAL/METHODS: Forty carotid atherosclerosis patients were enrolled. Patients were administrated olmesartan 20 mg/day for 3 months. Flow cytometry was used for counting circulating endothelial progenitor cells; colorimetric method was used to measure the serum levels of endothelial nitric oxide synthase and nitric oxide. Cell migration, adhesion, and proliferation capacity, and related signaling pathway were also analyzed. Spearman rank correlation analysis was used to investigate the influence of olmesartan on endothelial progenitor cells and clinical characteristics (e.g., sex, age, blood pressure). RESULTS: Compared with the control group, the number of circulating endothelial progenitor cells was significantly decreased. Olmesartan can increase circulating endothelial progenitor cells number and the serum levels of eNOS and NO. Furthermore, it can improve cell migration, adhesion, and proliferation capacities. Spearman rank correlation analysis showed there is no relationship between olmesartan promotion effects on endothelial progenitor cell mobilization and the clinical characteristics (P>0.05). P-eNOS and P-Akt expression can be unregulated by RNH-6270 treatment and blocked by LY294002. CONCLUSIONS: Olmesartan can effectively promote the endothelial progenitor cells mobilization and improve their function in patients with carotid atherosclerosis, independent of basic characteristics. This process relies on the PI3K/Akt/eNOS signaling pathway.
