A densely connected LDCT image denoising network based on dual-edge extraction and multi-scale attention under compound loss.

BACKGROUND: Low dose computed tomography (LDCT) uses lower radiation dose, but the reconstructed images contain higher noise that can have negative impact in disease diagnosis. Although deep learning with the edge extraction operators reserves edge information well, only applying the edge extraction operators to input LDCT images does not yield overall satisfactory results. OBJECTIVE: To improve LDCT images quality, this study proposes and tests a dual edge extraction multi-scale attention mechanism convolution neural network (DEMACNN) based on a compound loss. METHODS: The network uses edge extraction operators to extract edge information from both the input images and the feature maps in the network, improving the utilization of the edge operators and retaining the images edge information. The feature enhancement block is constructed by fusing the attention mechanism and multi-scale module, enhancing effective information, while suppressing useless information. The residual learning method is used to learn the network, improving the performance of the network, and solving the problem of gradient disappearance. Except for the network structure, a compound loss function, which consists of the MSE loss, the proposed joint total variation loss, and the edge loss, is proposed to enhance the denoising ability of the network and reserve the edge of images. RESULTS: Compared with other advanced methods (REDCNN, CT-former and EDCNN), the proposed new network achieves the best PSNR and SSIM values in LDCT images of the abdomen, which are 33.3486 and 0.9104, respectively. In addition, the new network also performs well on head and chest image data. CONCLUSION: The experimental results demonstrate that the proposed new network structure and denoising algorithm not only effectively removes the noise in LDCT images, but also protects the edges and details of the images well.

Working Mode and Case Analysis of the First Pharmaceutical Ward Rounds in Our Hospital / 中国药房

OBJECTIVE：To est ablish the working mode of the first pharmaceutical ward rounds of clinical pharmacists in our hospital，in order to provide a useful reference for establishing a national standardized pharmaceutical ward rounds model. METHODS：By sharing the clinical cases of the first pharmaceutical ward rounds ，the work content and process of the first pharmaceutical ward rounds in our hospital were introduced. RESULTS & CONCLUSIONS ：The clinical pharmacist ’s first pharmaceutical ward round in our hospital mainly includes self introduction of clinical pharmacists ，diagnosis of patients ’condition under the guidance of doctors ，collection and evaluation of patients ’previous medication information （including previous medication varieties ，usage methods ，efficacy and safety evaluation ），assistance for doctors in formulating initial treatment plan ， carrying out initial medication and diet education ，and intensive communication and cooperation with nurses. The development of first pharmaceutical ward rounds promotes the rational use of drugs in clinic ，elevates the hospitalization satisfaction of patients and improves the professional quality of clinical pharmacists.

Preliminary study on the short－term and long－term effects of the inhibition of hypoxia inducible factor－1 alpha decomposition and activation of Wnt signaling pathway in brain injury in neonatal rats / 中国新生儿科杂志

Objective To investigate the protective effect of inhibition of hypoxia inducible factor－1 alpha (HIF－1α) and activation of Wnt signaling pathway on brain injury in neonatal rats.Method A total of 312 newborn SD rats were used to establish cerebral white matter damage model (WMD) on day 3.And they were randomly assigned into the model group (WMD group), post－modeling HIF－1αdecomposition inhibition group (PHI group), and post－modeling HIF－1αdecomposition inhibition with activation of Wnt signaling pathway group (PHI+activated Wnt group ) and post－modeling HIF－1αdecomposition inhibition with inhibition of the Wnt signaling pathway group (PHI+inhibition Wnt group).Brain tissues were taken on day 1, 3, 7 and 14 after modeling, respectively.The changes of oligodendrocyte precursor cell (OPC) and oligodendrocyte ( OL ) in brain tissues at different time points were observed by tissue immunofluorescence.The expression of HIF－1αprotein in the brain tissue of each time point was measured by western blot technique.The mRNA level of HIF－1αand Wnt7a in the brain tissue of each time point was detected by RT－qPCR technique.Behaviors of rats were tested by the suspension experiment , the open field experiment and the dark experiment , at 28 d after modeling.Result The numbers of OPC on 1 d and 3 d after modeling and the number of OL on 7 d and 14 d after modeling in PHI +activated Wnt group were significantly higher than the other three groups.The content of HIF－1αin WMD group was the least on 1, 3, 7 and 14 d, but the content of PHI+activated Wnt group was the highest , and the difference was statistically significant (P＜0.05).On 1, 3, 7 and 14 d after modeling, the expression level of HIF－1αand Wnt7a in PHI+activated Wnt group were higher than those in the other three groups , the difference was statistically significant (P＜0.05), and Wnt7a expression was positively correlated with the change of HIF－1α(P＜0.05).There was no significant difference of suspension experiment at 28 d after modeling between groups. Compared with other groups , WMD group had the lowest score on open field experiment ( P＜0.05).The PHI+activation Wnt group had better memory function , and then the PHI group , WMD group.The latent time of dark experiment were significantly shorter in PHI +acitivation Wnt group.There were more mistaken time of dark experiment in WMD group compared with PHI +activation Wnt group.Conclusion Inhibition of HIF－1αdecomposition and activation of Wnt signaling pathway have partially repair effect on brain injury in neonatal rats.