Mammography is one of the most commonly applied tools for early breast cancer screening. Automatic segmentation of breast masses in mammograms is essential but challenging due to the low signal-to-noise ratio and the wide variety of mass shapes and sizes. Existing methods deal with these challenges mainly by extracting mass-centered image patches manually or automatically. However, manual patch extraction is time-consuming and automatic patch extraction brings errors that could not be compensated in the following segmentation step. In this study, we propose a novel attention-guided dense-upsampling network (AUNet) for accurate breast mass segmentation in whole mammograms directly. In AUNet, we employ an asymmetrical encoder-decoder structure and propose an effective upsampling block, attention-guided dense-upsampling block (AU block). Especially, the AU block is designed to have three merits. Firstly, it compensates the information loss of bilinear upsampling by dense upsampling. Secondly, it designs a more effective method to fuse high- and low-level features. Thirdly, it includes a channel-attention function to highlight rich-information channels. We evaluated the proposed method on two publicly available datasets, CBIS-DDSM and INbreast. Compared to three state-of-the-art fully convolutional networks, AUNet achieved the best performances with an average Dice similarity coefficient of 81.8% for CBIS-DDSM and 79.1% for INbreast.
Efforts to promote pollution control strategies by the government and the media can lower exposure to ambient pollution. However, few empirical studies have quantified multi-sectoral control measures using big data text mining algorithms to explore the relationship and mechanism between environmental concern and air pollution at the city level. Here, we quantify media and government environmental concerns with the text-mining algorithm. The Dynamic Spatial Durbin model is used to explore the relationship between environmental concerns and air pollution. We find that environmental concerns from government, media, and their synergy are associated with a 3.12%, 3.05% and 3.61% decreased air pollution with spatial spillover effect, respectively. And the government has the problem of incomplete implementation in pollution control, but media environmental concerns can force the government to increase the intensity in pollution control. In addition, industrial restructuring, technological innovation and foreign direct investment mediated the association between environmental concerns and haze pollution are confirmed. This study provides a feasible solution for the mitigation of air pollution in the cooperation of multi-sectoral synergistic governance.
China, the largest developing industrialized country, faces serious air pollution and greenhouse gas emissions. However, studies on the evolution and synergistic drivers of the symbiosis of air pollution and carbon emissions over long time scales from a spatial spillover perspective are rare. Based on the "identification of agglomeration features - description of agglomeration situation - analysis of agglomeration factors" at the level of 280 cities during 2006-2019 in China, we identified the spatial evolution characteristics of carbon emissions and air pollution symbiosis by applying spatial density analysis and geographical concentration and using a dynamic spatial autoregressive model for multiple cooperative test drivers. The result showed: (1) Both carbon emission and air pollution showed a similar spatial aggregation trend, suggesting a significant symbiosis phenomenon, in the order of SO 2 > PM 2.5 > dust (soot) > CO 2. (2) Although the agglomeration of carbon emission and pollution showed spatial imbalance, the agglomeration trend gradually improves over time, and agglomeration centers are all located in Henan Province, with a northwest shift. (3) The symbiosis of carbon emissions and pollution shows a significant spatial spillover effect, and economic growth, the proportion of the secondary industry, population density, and urbanization level play a positive synergistic driving effect on the symbiosis. Thus, the symbiosis between carbon emissions and air pollution is certain, and substantial action against greenhouse gases and air pollutants is imminent in China, with rapid industrialization and urbanization.
This paper begins with network shopping of university students. Then in a comprehensive analysis by knowing the confidence level of site quality, supplier quality, the confidence level of network security, gender ratio of network shopping, the actual experience of network shopping and the current stage impact of factors that influence network shopping of university students. Finally the paper gives the current phase of individual factors affecting network shopping of university students.
Accurately segmenting curvilinear structures, for example, retinal blood vessels or nerve fibers, in the medical image is essential to the clinical diagnosis of many diseases. Recently, deep learning has become a popular technology to deal with the image segmentation task, and it has obtained remarkable achievement. However, the existing methods still have many problems when segmenting the curvilinear structures in medical images, such as losing the details of curvilinear structures, producing many false-positive segmentation results. To mitigate these problems, we propose a novel end-to-end curvilinear structure segmentation network called Curv-Net.Curv-Net is an effective encoder-decoder architecture constructed based on selective kernel (SK) and multibidirectional convolutional LSTM (multi-Bi-ConvLSTM). To be specific, we first employ the SK module in the convolutional layer to adaptively extract the multi-scale features of the input image, and then we design a multi-Bi-ConvLSTM as the skip concatenation to fuse the information learned in the same stage and propagate the feature information from the deep stages to the shallow stages, which can enable the feature captured by Curv-Net to contain more detail information and high-level semantic information simultaneously to improve the segmentation performance.The effectiveness and reliability of our proposed Curv-Net are verified on three public datasets: two color fundus datasets (DRIVE and CHASE_DB1) and one corneal nerve fiber dataset (CCM-2). We calculate the accuracy (ACC), sensitivity (SE), specificity (SP), Dice similarity coefficient (Dice), and area under the receiver (AUC) for the DRIVE and CHASE_DB1 datasets. The ACC, SE, SP, Dice, and AUC of the DRIVE dataset are 0.9629, 0.8175, 0.9858, 0.8352, and 0.9810, respectively. For the CHASE_DB1 dataset, the values are 0.9810, 0.8564, 0.9899, 0.8143, and 0.9832, respectively. To validate the corneal nerve fiber segmentation performance of the proposed Curv-Net, we test it on the CCM-2 dataset and calculate Dice, SE, and false discovery rate (FDR) metrics. The Dice, SE, and FDR achieved by Curv-Net are 0.8114 ± 0.0062, 0.8903 ± 0.0113, and 0.2547 ± 0.0104, respectively.Curv-Net is evaluated on three public datasets. Extensive experimental results demonstrate that Curv-Net outperforms the other superior curvilinear structure segmentation methods.
Deep generative models have gained much attention given their ability to generate data for applications as varied as healthcare to financial technology to surveillance, and many more - the most popular models being generative adversarial networks (GANs) and variational auto-encoders (VAEs). Yet, as with all machine learning models, ever is the concern over security breaches and privacy leaks and deep generative models are no exception. In fact, these models have advanced so rapidly in recent years that work on their security is still in its infancy. In an attempt to audit the current and future threats against these models, and to provide a roadmap for defense preparations in the short term, we prepared this comprehensive and specialized survey on the security and privacy preservation of GANs and VAEs. Our focus is on the inner connection between attacks and model architectures and, more specifically, on five components of deep generative models: the training data, the latent code, the generators/decoders of GANs/VAEs, the discriminators/encoders of GANs/VAEs, and the generated data. For each model, component and attack, we review the current research progress and identify the key challenges. The paper concludes with a discussion of possible future attacks and research directions in the field.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)