Programmed cell death 4 (PDCD4) is involved in a number of bioprocesses, such as apoptosis and inflammation. However, its regulatory mechanisms in atherosclerosis remain unclear. In this study, we investigated the role and mechanisms of action of PDCD4 in high-fat diet-induced atherosclerosis in mice and in foam cells (characteristic pathological cells in atherosclerotic lesions) derived from ox-LDL-stimulated macrophages. MicroRNA (miR)-16 was predicted to bind PDCD4 by bioinformatics analysis. In the mice with atherosclerosis and in the foam cells, PDCD4 protein expression (but not the mRNA expression) was enhanced, while that of miR-16 was reduced. Transfection with miR-16 mimic decreased the activity of a luciferase reporter containing the 3′ untranslated region (3′UTR) of PDCD4 in the macrophage-derived foam cells. Conversely, treatment with miR-16 inhibitor enhanced the luciferase activity. However, by introducing mutations in the predicted binding site located in the 3′UTR of PDCD4, the miR-16 mimic and inhibitor were unable to alter the level of PDCD4, suggesting that miR-16 is a direct negative regulator of PDCD4 in atherosclerosis. Furthermore, transfection wtih miR-16 mimic and siRNA targeting PDCD4 suppressed the secretion and mRNA expression of pro-inflammatory factors, such as interleukin (IL)-6 and tumor necrosis factor-α (TNF-α), whereas it enhanced the secretion and mRNA expression of the anti-inflammatory factor, IL-10. Treatment with miR-16 inhibitor exerted the opposite effects. In addition, the phosphorylation of p38 and extracellular signal-regulated kinase (ERK), and nuclear factor-κB (NF-κB) expression were altered by miR-16. In conclusion, our data demonstrate that the targeting of PDCD4 by miR-16 may suppress the activation of inflammatory macrophages though mitogen-activated protein kinase (MAPK) and NF-κB signaling in atherosclerosis; thus, PDCD4 may prove to be a potential therapeutic target in the treatment of atherosclerosis.

Owing to the flexible architectures of deep convolutional neural networks (CNNs) are successfully used for image denoising. However, they suffer from the following drawbacks: (i) deep network architecture is very difficult to train. (ii) Deeper networks face the challenge of performance saturation. In this study, the authors propose a novel method called enhanced convolutional neural denoising network (ECNDNet). Specifically, they use residual learning and batch normalisation techniques to address the problem of training difficulties and accelerate the convergence of the network. In addition, dilated convolutions are used in the proposed network to enlarge the context information and reduce the computational cost. Extensive experiments demonstrate that the ECNDNet outperforms the state-of-the-art methods for image denoising.

Age estimation on the basis of the face has been widely used in the field of human-computer interaction and intelligent surveillance. Many existing methods extract deeper global features from the facial image and achieve significant improvement on age estimation. However, local features and their relationship are important for age estimation. In this study, the authors propose a model to use local features for age estimation. The proposed model consists of three stages, preliminary abstraction stage for extracting deeper features, local feature encoding stage to model the relationship between local features and recall stage for the combination of temporary local impressions. Extensive experiments show that their proposed method outperforms previous state-of-the-art methods. 2 Related work People use the words 'baby face' or 'obsolete' to describe the gap between the real and apparent ages. Specifically, in the real world, real and apparent ages of people are inconsistent. It is not easy to judge the true age from a photograph. To address this problem, some scholars utilise neural networks to design lots of methods. These methods can be roughly divided into three kinds: classification, regression and ranking method. 2.1 Classification methods for age estimation In this kind of method, different ages are regarded as different categories. There are many examples of this kind of method.

No abstract

In recent years, deep learning has been widely applied for mammographic image classification. However, most of the existing methods are based on a single mammography view and cannot sufficiently extract discriminative features, thereby resulting in an unsatisfactory classification accuracy. To solve this problem and improve the mammographic image classification performance, we propose a novel multi-view convolutional neural network (CNN) based on multiple mammography views in this paper. Considering that the images acquired from different perspectives contain different and complementary breast mass information, we modify the CNN architecture to exploit the complementary information from the various views of mammography. The new architecture can extract discriminative features from the mediolateral oblique (MLO) and craniocaudal (CC) views of the mammographic images and can effectively incorporate these features for mammographic images. The dilated convolutional layers enable the feature maps extracted from the multiple breast mass views to capture information from a large ''field of vision''. Moreover, multiscale features are obtained by using the convolutional and dilated convolutions. In addition, we incorporate a penalty term into the cross entropy loss function, which enables the model evolution to reduce the misclassification rate by enhancing the contributions of the samples misclassified in the training process. The proposed method was evaluated and compared with several state-of-the-art methods on the open Digital Database for Screening Mammography (DDSM) and Mammographic Image Analysis Society (MIAS) datasets. The experimental results show that the proposed method exhibits a better performance than those of the state-of-the-art methods.INDEX TERMS Medical image processing, mammographic image, deep learning, convolutional neural network.