In order to solve the problem of low accuracy of the U-Net in cardiac ventricular segmentation, we propose an improved U-net named LU-Net by the following three methods. First, in order to improve the efficiency and effectiveness of extracting the features of the original image, we combine U-net with SE-Net model. This model reweights the channels of the feature map, which can give higher weight to the useful information and lower weight to the invalid information. Second, in order to alleviate the extent of losing the pixel-location information when using the encoder to dawn sample, we combine multi-scale input with U-net's encoder. Third, in order to solve the problem of low accuracy in traditional U-net, we replace the transposed convolution layer, used by the traditional U-Net's encoder during upsampling, with an unsampling layer. During the process of unsampling, it can put pixels to their original location using the pixel-location information reserved by the encoder during the sampling process, which can reduce errors caused by losing pixel-location information. Besides, using the unsampling layer during unsampling can also avoid producing checkerboard artifacts during transposed convolution and improve the segmentation accuracy. To verify the effectiveness of LU-Net, we apply it to the ACDC Stacom 2017 dataset. The experimental results show that the evaluation criteria of prediction results are 92.4%, 86.4%, and 92.5% on Dice coefficient, Jaccard similarity coefficient, and F1-ccore respectively, which are better than U-Net, SegNet, and IU-Net and remarkably better than the traditional neural convolution network model, FCN8s.
Introduction: This multicenter, retrospective study assessed the prevalence of post-stroke cognitive impairment (PSCI) 6 months after acute ischemic stroke (AIS) and its risk factors to build a bedside early predictive model for PSCI using the Montreal Cognitive Assessment (MoCA).
Methods: Records of consecutive patients with AIS treated at 4 stroke centers in Shanghai had MoCA assessments within 2 weeks after AIS onset and 6 months later were reviewed. Prevalence of PSCI (MoCA<22) was calculated and risk factors were identified by multivariate logistic regression analysis. The modeling and validation and identified risk factors were included in a predictive model using multivariate regression.
Results: There were 383 patients included and prevalence of PSCI 6 months after AIS was 34.2%, significantly lower than prevalence of patients with acute cognitive impairment (49.6%). Aging, less education, higher glucose level and severe stroke were PSCI risk factors, while level of low-density lipoprotein cholesterol (LDL-C) had a paradox effect on the risk of PSCI. 40.0% of the patients with cognitive impairment at acute phase reverted to normal, and patients with LDL-C 1.8-2.5 mmol/L were more likely to revert. The predictive model we built, DREAM-LDL (Diabetes [fasting blood glucose level], Rating [NIHSS], level of Education, Age, baseline MoCA and LDL-C level), had an AUROC of 0.93 for predicting PSCI at 6 months.
Conclusion: PSCI was common among AIS patients 6 months after AIS. We provided a practical tool to predict PSCI based on MoCA and risk factors present during acute phase of AIS.
Epithelial-mesenchymal transition (EMT) is defined as a process in which differentiated epithelial cells undergo phenotypic transformation into myofibroblasts capable of producing extracellular matrix, and is generally regarded as an integral part of fibrogenesis after tissue injury. Although there is evidence that the complete EMT of tubular epithelial cells (TECs) is not a major contributor to interstitial myofibroblasts in kidney fibrosis, the partial EMT, a status that damaged TECs remain inside tubules, and co-express both epithelial and mesenchymal markers, has been demonstrated to be a crucial stage for intensifying fibrogenesis in the interstitium. The process of tubular EMT is governed by multiple intracellular pathways, among which Wnt/β-catenin signaling is considered to be essential mainly because it controls the transcriptome associated with EMT, making it a potential therapeutic target against kidney fibrosis. A growing body of data suggest that reducing the hyperactivity of Wnt/β-catenin by natural compounds, specific inhibitors, or manipulation of genes expression attenuates tubular EMT, and interstitial fibrogenesis in the TECs cultured under profibrotic environments and in animal models of kidney fibrosis. These emerging therapeutic strategies in basic researches may provide beneficial ideas for clinical prevention and treatment of chronic kidney disease.
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.