Purpose: Coronavirus disease 2019 (COVID-19) has caused a serious global health crisis. It has been proven that the deep learning method has great potential to assist doctors in diagnosing COVID-19 by automatically segmenting the lesions in computed tomography (CT) slices. However, there are still several challenges restricting the application of these methods, including high variation in lesion characteristics and low contrast between lesion areas and healthy tissues. Moreover, the lack of high-quality labeled samples and large number of patients lead to the urgency to develop a high accuracy model, which performs well not only under supervision but also with semi-supervised methods. Methods: We propose a content-aware lung infection segmentation deep residual network (content-aware residual UNet (CARes-UNet)) to segment the lesion areas of COVID-19 from the chest CT slices. In our CARes-UNet, the residual connection was used in the convolutional block,which alleviated the degradation problem during the training. Then, the content-aware upsampling modules were introduced to improve the performance of the model while reducing the computation cost. Moreover, to achieve faster convergence, an advanced optimizer named Ranger was utilized to update the model's parameters during training. Finally, we employed a semi-supervised segmentation framework to deal with the problem of lacking pixel-level labeled data. Results: We evaluated our approach using three public datasets with multiple metrics and compared its performance to several models. Our method outperforms other models in multiple indicators, for instance in terms of Dice coefficient on COVID-SemiSeg Dataset, CARes-UNet got the score 0.731, and semi-CARes-UNet further boosted it to 0.776. More ablation studies were done and validated the effectiveness of each key component of our proposed model. Conclusions: Compared with the existing neural network methods applied to the COVID-19 lesion segmentation tasks, our CARes-UNet can gain more accurate segmentation results, and semi-CARes-UNet can further improve it using semi-supervised learning methods while presenting a possible way to solve the problem of lack of high-quality annotated samples. Our CARes-UNet and semi-CARes-UNet can be used in artificial intelligence-empowered computer-aided diagnosis system to improve diagnostic accuracy in this ongoing COVID-19 pandemic. K E Y W O R D S computed tomography (CT) image, content-aware residual UNet, coronavirus disease 2019 (COVID-19), deep learning, segmentation
<abstract> <sec><title>Background</title><p>Atherosclerosis is one of the major reasons for cardiovascular disease including coronary heart disease, cerebral infarction and peripheral vascular disease. Atherosclerosis has no obvious symptoms in its early stages, so the key to the treatment of atherosclerosis is early intervention of risk factors. Machine learning methods have been used to predict atherosclerosis, but the presence of strong causal relationships between features can lead to extremely high levels of information redundancy, which can affect the effectiveness of prediction systems.</p> </sec> <sec><title>Objective</title><p>We aim to combine statistical analysis and machine learning methods to reduce information redundancy and further improve the accuracy of disease diagnosis.</p> </sec> <sec><title>Methods</title><p>We cleaned and collated the relevant data obtained from the retrospective study at Affiliated Hospital of Nanjing University of Chinese Medicine through data analysis. First, some features that with too many missing values are filtered out of the 34 features, leaving 25 features. 49% of the samples were categorized as the atherosclerosis risk group while the rest 51% as the control group without atherosclerosis risk under the guidance of relevant experts. We compared the prediction results of a single indicator that had been medically proven to be highly correlated with atherosclerosis with the prediction results of multiple features to fully demonstrate the effect of feature information redundancy on the prediction results. Then the features that could distinguish whether have atherosclerosis risk or not were retained by statistical tests, leaving 20 features. To reduce the information redundancy between features, after drawing inspiration from graph theory, machine learning combined with optimal correlation distances was then used to screen out 15 significant features, and the prediction models were evaluated under the 15 features. Finally, the information of the 5 screened-out non-significant features was fully utilized by ensemble learning to improve the prediction superiority for atherosclerosis.</p> </sec> <sec><title>Results</title><p>Area Under the Receiver Operating Characteristic (ROC) Curve (AUC), which is used to measure the predictive performance of the model, was 0.84035 and Kolmogorov-Smirnov (KS) value was 0.646. After feature selection model based on optimal correlation distance, the AUC value was 0.88268 and the KS value was 0.688, both of which were improved by about 0.04. Finally, after ensemble learning, the AUC value of the model was further improved by 0.01369 to 0.89637.</p> </sec> <sec><title>Conclusions</title><p>The optimal distance feature screening model proposed in this paper improves the performance of atherosclerosis prediction models in terms of both prediction accuracy and AUC metrics. Code and models are available at <a href="https://github.com/Cesartwothousands/Prediction-of-Atherosclerosis" target="_blank">https://github.com/Cesartwothousands/Prediction-of-Atherosclerosis</a>.</p> </sec> </abstract>
IntroductionAs a representation of the gut microbiota, fecal and cecal samples are most often used in human and animal studies, including in non-alcoholic fatty liver disease (NAFLD) research. However, due to the regional structure and function of intestinal microbiota, whether it is representative to use cecal or fecal contents to study intestinal microbiota in the study of NAFLD remains to be shown.MethodsThe NAFLD mouse model was established by high-fat diet induction, and the contents of the jejunum, ileum, cecum, and colon (formed fecal balls) were collected for 16S rRNA gene analysis.ResultsCompared with normal mice, the diversity and the relative abundance of major bacteria and functional genes of the ileum, cecum and colon were significantly changed, but not in the jejunum. In NAFLD mice, the variation characteristics of microbiota in the cecum and colon (feces) were similar. However, the variation characteristics of intestinal microbiota in the ileum and large intestine segments (cecum and colon) were quite different.DiscussionTherefore, the study results of cecal and colonic (fecal) microbiota cannot completely represent the results of jejunal and ileal microbiota.
Background Pregnancy and childbirth are described as transitional phases or existential thresholds that childbearing women have to cross. Aim To gather insights into the personal experiences of women in pregnancy, labour and the days immediately after birth. Methods We conducted a qualitative study in the postpartum ward at Westmead Hospital. We invited 16 primiparous women who had given birth to a single baby to participate in our study. After the participants signed the consent form, we conducted individual, in-depth interviews. We analysed the data using thematic analysis. Findings Confidence was an overarching theme that contributed to the women's experiences of pregnancy, labour and the immediate days after birth. The experiences encompassed two main categories: positive experiences that aided in building confidence, and negative experiences that adversely affected women's confidence. The themes relating to positive experiences, including effective interpersonal relationships, knowledge promotion and positive self-concept, made the women feel more confident. The themes relating to negative experiences, including lack of control and feeling unprepared, made the women feel less confident in their mothering capabilities. Conclusion Confidence was the overarching theme in this study and knowledge was shown to be the fundamental feature of confidence.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.