In recent years, deep learning has dominated medical image segmentation. Encoder-decoder architectures, such as U-Net, can be used in state-of-the-art models with powerful designs that are achieved by implementing skip connections that propagate local information from an encoder path to a decoder path to retrieve detailed spatial information lost by pooling operations. Despite their effectiveness for segmentation, these naïve skip connections still have some disadvantages. First, multi-scale skip connections tend to use unnecessary information and computational sources, where likable low-level encoder features are repeatedly used at multiple scales. Second, the contextual information of the low-level encoder feature is insufficient, leading to poor performance for pixel-wise recognition when concatenating with the corresponding high-level decoder feature. In this study, we propose a novel spatial-channel attention gate that addresses the limitations of plain skip connections. This can be easily integrated into an encoder-decoder network to effectively improve the performance of the image segmentation task. Comprehensive results reveal that our spatial-channel attention gate remarkably enhances the segmentation capability of the U-Net architecture with a minimal computational overhead added. The experimental results show that our proposed method outperforms the conventional deep networks in term of Dice score, which achieves 71.72%.
Camellia japonica is a popular garden plant in Asia and widely used as cosmetic sources and traditional medicine. However, the possibility that C. japonica affects cardiovascular system remains unclear. The aim of the present study was to evaluate vascular effects of an extract of C. japonica. Vascular reactivity was assessed in organ baths using porcine coronary arteries and inhibition of proliferation and migration were assessed using human vascular smooth muscle cells (VSMCs). All four different parts, leaf, stem, flower, and fruits, caused concentration-dependent relaxations and C. japonica fruit (CJF) extract showed the strongest vasorelaxation and its effect was endothelium dependent. Relaxations to CJF were markedly reduced by inhibitor of endothelial nitric oxide synthase (eNOS) and inhibitor of PI3-kinase, but not affected by inhibitor of cyclooxygenase and endothelium-derived hyperpolarizing factor-mediated response. CJF induced activated a time- and concentration-dependent phosphorylation of eNOS in endothelial cells. Altogether, these studies have demonstrated that CJF is a potent endothelium-dependent vasodilator and this effect was involved in, at least in part, PI3K-eNOS-NO pathway. Moreover, CJF attenuated TNF-α induced proliferation and PDGF-BB induced migration of VSMCs. The present findings indicate that CJF could be a valuable candidate of herbal medicine for cardiovascular diseases associated with endothelial dysfunction and atherosclerosis.
Learning-based image super-resolution is considered as a promising solution to reconstruct a high-resolution image from a low-resolution image. To improve the super-resolution performance dramatically, this Letter focuses on the effect of training dataset on the performance and proposes an image super-resolution scheme based on patch orientation-specified network. In particular, a deep neural network is trained using patches with a specific orientation and angular transformation is combined with the neural network to cope with various orientations in input patches. Experimental results show the suggested network model is superior to existing state-of-the-art super-resolution alternatives.
In real image coding systems, block-based coding is often applied on images contaminated by camera sensor noises such as Poisson noises, which cause complicated types of noises called compressed Poisson noises. Although many restoration methods have recently been proposed for compressed images, they do not provide satisfactory performance on the challenging compressed Poisson noises. This is mainly due to (i) inaccurate modeling regarding the image degradation, (ii) the signal-dependent noise property, and (iii) the lack of analysis on intercorrelation distortion. In this paper, we focused on the challenging issues in practical image coding systems and propose a compressed Poisson noise reduction scheme based on a secondary domain intercorrelation enhanced network. Specifically, we introduced a compressed Poisson noise corruption model and combined the secondary domain intercorrelation prior with a deep neural network especially designed for signal-dependent compression noise reduction. Experimental results showed that the proposed network is superior to the existing state-of-the-art restoration alternatives on classical images, the LIVE1 dataset, and the SIDD dataset.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.