Semi-Supervised Modified-UNet for Lung Infection Image Segmentation

Automatic lung infection segmentation in computed tomography (CT) scans can offer great assistance in radiological diagnosis by improving accuracy and reducing time required for diagnosis. The biggest challenges for deep learning (DL) models in segmenting infection region are the high variances in infection characteristics, fuzzy boundaries between infected and normal tissues, and the troubles in getting large number of annotated data for training. To resolve such issues, we propose a Modified U-Net (Mod-UNet) model with minor architectural changes and significant modifications in the training process of vanilla 2D UNet. As part of these modifications, we updated the loss function, optimization function, and regularization methods, added a learning rate scheduler and applied advanced data augmentation techniques. Segmentation results on two Covid-19 Lung CT segmentation datasets show that the performance of Mod-UNet is considerably better than the baseline U-Net. Furthermore, to mitigate the issue of lack of annotated data, the Mod-UNet is used in a semi-supervised framework (Semi-Mod-UNet) which works on a random sampling approach to progressively enlarge the training dataset from a large pool of unannotated CT slices. Exhaustive experiments on the two Covid-19 CT segmentation datasets and on a real lung CT volume show that the Mod-UNet and Semi-Mod-UNet significantly outperform other state-of-theart approaches in automated lung infection segmentation. IEEE

X-rays imaging analysis for early diagnosis of the thoracic disorders using Capsule Neural Network with Transfer learning

Over the past few years, millions of people around the world have developed thoracic ailments. MRI, CT scan, reverse transcription, and other methods are among those used to detect thoracic disorders. These procedures demand medical knowledge and are exceedingly pricy and delicate. An alternate and more widely used method to diagnose diseases of the chest is X-ray imaging. The goal of this study was to increase detection precision in order to develop a computationally assisted diagnostic tool. Different diseases can be identified by combining radiological imaging with various artificial intelligence application approaches. In this study, transfer learning (TL) and capsule neural network techniques are used to propose a method for the automatic detection of various thoracic illnesses utilizing digitized chest X-ray pictures of suspected patients. Four public databases were combined to build a dataset for this purpose. Three pre trained convolutional neural networks (CNNs) were utilized in TL with augmentation as a preprocessing technique to train and evaluate the model. Pneumonia, COVID19, normal, and TB (Tb) were the four class classifiers used to train the network to categorize. © 2023 IEEE.

Can Chinese banks expand their loan portfolio while maintaining loan quality and profitability post-global financial crisis?

PurposeThis study aims to investigate the relationships between loan growth, loan losses and net income after the 2008 global financial crisis. This study further conducts a comparative analysis by considering the period of COVID-19. Design/methodology/approachThis study uses panel data models such as one-step system GMM, random effects, fixed effects and OLS, with a data set of 131 Chinese commercial banks from 2009 to 2020. FindingsThe study finds no significant relationship between loan growth and future loan losses. However, after adjusting loan loss by net interest income (NII-adjusted loan loss), the study reveals that loan growth in the subsequent year decreases if NII-adjusted loan loss increases. The study also demonstrates the positive effect of loan growth on net income as newly expanded loans are funded at similar costs but offered at a lower rate compared with existing loans. During COVID-19, loan growth and net income were higher than in previous years. Originality/valueThe findings suggest that Chinese banks can increase lending to support the economy without sacrificing loan quality, emphasizing the importance of maintaining and enhancing credit policies and practices. Chinese banks should also continue to refine their pricing strategies for loans and deposits. The findings also imply that China's policy responses to the impact of COVID-19 could serve as lessons for future policy decisions.

Controversial role of neutrophilic granulocytes in the immunopathogenesis of COVID-19: correlation with imbalance of pro-inflammatory neutrophil-associated cytokines and interferon alpha deficiency.

Neutrophilic granulocytes (NG) are the main drivers of pathological inflammation in COVID-19. Objective. To specify the mechanisms of immunopathogenesis of COVID-19 based on a comparative immunological study of the number and phenotype of CD16+SD62L+CD11b+CD63- and CD16+SD62L+CD11b+CD63+ subsets with an assessment of their effector functions against changing profile of NG-associated cytokines IL-8, IL-18, IL-17A, VEGF-A, IFNalpha, and IFNgamma. Patients and methods. In patients with moderate-to-severe and severe COVID-19, we determined IL-1beta, TNFalpha, IL-6, IL-8, IL-18, IL-17A, VEGF-A, IFNalpha, and IFNgamma (ELISA), the phenotype of CD16+SD62L+CD11b+CD63- and CD16+SD62L+CD11b+CD63+ subsets, NF-kappaB-NG (CYTOMICS FC500), phagocytically active NG (%), neutrophil extracellular traps (NETs), NG in apoptosis, and the activity of NADPH oxidase. Results. In COVID-19 against the background of IFNalpha and IFNgamma production blockade and high levels of NG-associated IL-8, IL-18, IL-17A, VEGF-A, a reduction in the number of mature and functionally active CD16brightSD62LbrightCD11bbrightCD63-NG subsets was revealed, as well as an increase in the number of CD16dimSD62LdimSD11bbrightCD63-NG subsets with an immunosuppressive phenotype and CD16brightSD62LbrightSD11bbrightCD63bright-NG subsets with high cytotoxic activity and ability to form NETs, a decrease in the percentage of phagocytically active NG and an increase in the activity of NADPH oxidase, NETs, and NG in apoptosis. Conclusion. IFNalpha deficiency provokes a hyperergic response of NG-associated cytokines, which leads to the formation of uncontrolled immune inflammation involving NG subsets with an immunosuppressive and cytotoxic phenotype, exacerbating the course of COVID-19. The use of recombinant IFNalpha-2b with antioxidants (Viferon) in the early stages of the disease can help to restore immune homeostasis, normalize the level of NG-associated cytokines, reduce NERTs, and achieve good clinical efficacy.Copyright © 2022, Dynasty Publishing House. All rights reserved.

A Review on Solar Energy Policy and Current Status: Top 5 Countries and Kazakhstan

The article describes the world's experience in developing the solar industry. It discusses the mechanisms of state support for developing renewable energy sources in the cases of five countries that are the most successful in this area—China, the United States, Japan, India, and Germany. Furthermore, it contains a brief review of state policy in producing electricity by renewable energy facilities in Kazakhstan. This paper uses statistical information from the International Renewable Energy Agency (IRENA), the International Energy Agency (IEA), British Petroleum (BP), and the Renewable Energy Network (REN21), and peer-reviewed sources. The research methodology includes analytical research and evaluation methods to examine the current state of solar energy policy, its motivators and incentives, as well as the prospects for its development in Kazakhstan and in the world. Research shows that solar energy has a huge development potential worldwide and is sure to take its place in gross electricity production. This paper focuses on the selected economic policies of the top five countries and Kazakhstan, in what may be considered a specific research limitation. Future research suggestions for the expansion of Renewable Energy (RE) in Kazakhstan could include analysing the impact of introducing dedicated policies and incentives for solar systems and exploring the benefits and challenges of implementing large RE zones with government–business collaboration.

Assessing public support for social policy in times of crisis: evidence from the Child Tax Credit during the COVID-19 era in the United States

The 2021 American Rescue Plan included the temporary expansion of the Child Tax Credit (CTC)-the largest individual income tax credit program in the United States-for most families with children. In the context of the COVID-19 pandemic, how did the public perceive this social policy benefit for families, especially in relation to other traditional social programs? By focusing on the CTC, an understudied policy area, and presenting original survey data, this paper first shows that, while the majority of respondents favored the CTC, levels of support for these benefits were lower than support for other social programs. Second, the paper suggests that, compared to older people and people with disabilities, Americans view families as part of the "undeserving" population. Third, by presenting panel data, we show that there is no change in levels of CTC support even among recipients of these benefits. Overall, these findings shed light on important challenges to the development and implementation of family policy in the USA, as well as the possibility of recalibrating the US liberal welfare state.

Net neutrality in the USA during COVID-19

The COVID-19 pandemic provides an opportunity to review net neutrality and the notion that bright light rules are necessary to hold broadband providers from exercising market power. The 2015 Federal Communications Commission (FCC) Open Internet Order asserted that broadband providers have the capability and incentive to harm their customers and third-party service providers. It imposed a set of rules to control broadband providers' offers, prices, and traffic management. The 2017 FCC vacated all but the transparency provisions of the OIO, restoring the oversight of broadband to the FTC. This paper offers a review of the evidence regarding the effects of net neutrality regulation, including an investigation of the incidence of violations, or lack thereof, during the 2020 pandemic in the United States. It provides a review of the net neutrality literature and the international research on broadband provider behaviour during COVID-19. The paper presents original research conducted with FCC and FTC reports and a survey of news stories. Brief reviews of federal data on network performance and broadband adoption provide additional context. Given the limited incidence of violations that could be uncovered for the period, the paper suggests why broadband providers behaved opposite to regulatory advocates' predictions. Contrary to many policy assertions, broadband providers did not block or throttle service, nor did they increase prices arbitrarily or decrease quality. Broadband providers appeared to expand availability, lower broadband prices, and make more networks available, frequently without customer charge. The paper suggests how policy could be updated to reflect the actual behaviour of broadband providers. © 2023 the authors.

A Hybrid Model of Deep Learning Features and Clinical Features for Severe Cases Predication of COVID-19

COVID-19 has spread around the world since 2019. Approximately 6.5% of COVID-19 a risk of developing severe disease with high mortality rate. To reduce the mortality rate and provide appropriate treatment, this research established an integrated models with to predict the clinical outcome of COVID-19 patients with clinical, deep learning and radiomics features. To obtain the optimal feature combination for prediction, 9 clinical features combination was selected from all available clinical factors after using LASSO, 18 deep learning features from U-Net architecture, and 9 radiomics features from segmentation result. A total of 213 COVID-19 patients and 335 non-COVID-19 patients from 5 hospitals were enrolled and used as training and test sample in this research. The proposed model obtained an accuracy, precision, recall, specificity, F1-score and ROC curve of 0.971, 0.943, 0.937, 0.974, 0.941 and 0.979, respectively, which exceeds the related work using only clinical, deep learning or radiomics factors. © 2023 SPIE.

Impact of Renewable Energy on the Economy of Saudi Arabia

The objective of the study was to identify the impact of renewable energy on Saudi economy during 2000-2021. Analytical techniques were used to conduct this study. An analysis of the study used a set of variables, in which Renewable energy perceives as independent variable and the dependent variables are GDP per capita, net foreign direct investment, unemployment, fixed capital formation, and net foreign trade. The data of the study were analyzed using the E-views program. According to the study, renewable energy has an impact on certain economic variables and does not have an impact on others. A partial validity is found for the study's central hypothesis. According to our findings, renewable energy contributes significantly to net foreign direct investment, unemployment, and fixed capital formation, but not to GDP per capita, net foreign trade, or fixed capital formation.

Trade-based money laundering and informal remittance services: implications on the sustainability of the balance of payments of a small open economy

PurposeThis study aims to discuss the consequences of trade-based money laundering (TBML) and informal remittance services on the sustainability of the position of balance of payments and net foreign assets of a small open economy.Design/methodology/approachThis paper uses a case study design using facts related to TBML and informal remittance services on the balance of payment and net foreign assets of Sri Lanka.FindingsThe contextual analysis reveals that the growth of the informal economy promotes informal remittance services in Sri Lanka. The policy decision to peg local currency to US dollars as a result of a shortage of foreign exchange had forced people to use informal channels for different purposes. The unclear and vague customer due diligence process of the anti-money laundering and countering the financing of terrorism (AML/CFT) regime also has forced people to use informal remittance services. Criminals especially drug traffickers have grabbed the promoted informal remittance services to transfer proceeds from Sri Lanka to overseas drug suppliers. On the other hand, systematic deficiencies in monitoring and regulation of movement of fund transfers and merchandise across borders provide opportunities for criminals to use different TBML techniques to transfer funds. These limitations force policymakers and regulators to think of developing a comprehensive payment ecosystem to prevent money laundering and terrorist financing. Therefore, the global initiative is required to move towards a payment ecosystem from a recommendation-based AML/CFT regime to reduce global crimes.Research limitations/implicationsThis study was designed to discuss the implications of TBML and informal remittance services on the balance of payments and net foreign assets in a small open economy. The structure and size of the economy, the strength of the overall economy and the AML/CFT regime will play an important role in controlling criminal activities and combating money laundering of an economy;hence, the impact of TBML and informal remittance services will vary accordingly across the countriesOriginality/valueThis paper is an original work done by the authors, which discusses the implications of TBML and informal remittance services on the balance of payments and net foreign assets of an emerging market context.

Meeting the Hospital Oxygen Demand with a Decentralized Autonomous PV System: Effect of PV Tracking Systems

When it comes to supplying oxygen, current standard hospitals in Iran have proven inadequate in the face of the COVID-19 pandemic, particularly during infection peaks. Power disruptions drastically reduce the oxygen pressure in hospitals, putting patients' health at risk. The present study is the first to attempt to power an oxygen concentrator with a solar-energy-based system. The HOMER 2.81 package was used for technical–economic–environmental–energy analysis. The most notable aspects of this work include evaluating different available solar trackers, using up-to-date equipment price data and up-to-date inflation rate, considering the temperature effects on solar cell performance, sensitivity analysis for the best scenario, considering pollution penalties, and using a three-time tariff system with price incentives for renewable power. The study has been carried out at Hajar Hospital, Shahrekord, Chaharmahal and Bakhtiari Province, Iran. The study showed that, by supplying 60% of the power demand, the dual-axis solar tracking system offered the highest annual power output (47,478 kWh). Furthermore, generating power at—$0.008/kWh due to selling power to the grid, the vertical-axis tracker was found to be the most economical design. Comparing the configuration with a vertical-axis tracker with the conventional scenario (relying on the power distribution grid), the investment is estimated to be recovered in three years with $234,300 in savings by the end of the 25th year. In the best economic scenario, 6137 kg CO2 is produced, and the analysis revealed the negative impact of a temperature rise on the performance and solar power output.

Multi-Attentional U-Net for Medical Image Segmentation

Deep learning (DL) approaches for image segmentation have been gaining state-of-the-art performance in recent years. Particularly, in deep learning, U-Net model has been successfully used in the field of image segmentation. However, traditional U-Net methods extract features, aggregate remote information, and reconstruct images by stacking convolution, pooling, and up sampling blocks. The traditional approach is very inefficient due of the stacked local operators. In this paper, we propose the multi-attentional U-Net that is equipped with non-local blocks based self-attention, channel-attention, and spatial-attention for image segmentation. These blocks can be inserted into U-Net to flexibly aggregate information on the plane and spatial scales. We perform and evaluate the multi-attentional U-Net model on three benchmark data sets, which are COVID-19 segmentation, skin cancer segmentation, thyroid nodules segmentation. Results show that our proposed models achieve better performances with faster computation and fewer parameters. The multi-attention U-Net can improve the medical image segmentation results. © 2022 IEEE.

A Systematic Literature Review of Deep Learning Algorithms for Segmentation of the COVID-19 Infection

Coronavirus has infected more than 753 million people, ranging in severity from one person to another, where more than six million infected people died worldwide. Computer-aided diagnostic (CAD) with artificial intelligence (AI) showed outstanding performance in effectively diagnosing this virus in real-time. Computed tomography is a complementary diagnostic tool to clarify the damage of COVID-19 in the lungs even before symptoms appear in patients. This paper conducts a systematic literature review of deep learning methods for classifying the segmentation of COVID-19 infection in the lungs. We used the methodology of systematic reviews and meta-analyses (PRISMA) flow method. This research aims to systematically analyze the supervised deep learning methods, open resource datasets, data augmentation methods, and loss functions used for various segment shapes of COVID-19 infection from computerized tomography (CT) chest images. We have selected 56 primary studies relevant to the topic of the paper. We have compared different aspects of the algorithms used to segment infected areas in the CT images. Limitations to deep learning in the segmentation of infected areas still need to be developed to predict smaller regions of infection at the beginning of their appearance.

Remora Namib Beetle Optimization Enabled Deep Learning for Severity of COVID-19 Lung Infection Identification and Classification Using CT Images.

Coronavirus disease 2019 (COVID-19) has seen a crucial outburst for both females and males worldwide. Automatic lung infection detection from medical imaging modalities provides high potential for increasing the treatment for patients to tackle COVID-19 disease. COVID-19 detection from lung CT images is a rapid way of diagnosing patients. However, identifying the occurrence of infectious tissues and segmenting this from CT images implies several challenges. Therefore, efficient techniques termed as Remora Namib Beetle Optimization_ Deep Quantum Neural Network (RNBO_DQNN) and RNBO_Deep Neuro Fuzzy Network (RNBO_DNFN) are introduced for the identification as well as classification of COVID-19 lung infection. Here, the pre-processing of lung CT images is performed utilizing an adaptive Wiener filter, whereas lung lobe segmentation is performed employing the Pyramid Scene Parsing Network (PSP-Net). Afterwards, feature extraction is carried out wherein features are extracted for the classification phase. In the first level of classification, DQNN is utilized, tuned by RNBO. Furthermore, RNBO is designed by merging the Remora Optimization Algorithm (ROA) and Namib Beetle Optimization (NBO). If a classified output is COVID-19, then the second-level classification is executed using DNFN for further classification. Additionally, DNFN is also trained by employing the newly proposed RNBO. Furthermore, the devised RNBO_DNFN achieved maximum testing accuracy, with TNR and TPR obtaining values of 89.4%, 89.5% and 87.5%.

Clinical and Sociodemographic Factors Associated with Telemedicine Engagement in an Urban Community Health Center Cohort During the COVID-19 Pandemic.

Objective: To examine chronic diseases, clinical factors, and sociodemographic characteristics associated with telemedicine utilization among a safety-net population. Materials and Methods: We conducted a retrospective cohort study of adults seeking care in an urban, multisite community health center in the Northeast United States. We included adults with ≥1 outpatient in-person visit during the pre-COVID-19 period (March 1, 2019-February 29, 2020) and ≥1 outpatient visit (in-person or telemedicine) during the COVID-19 period (March 1, 2020-February 29, 2021). Multivariable logistic regression models estimated associations between clinical and sociodemographic factors and telemedicine use, classified as "any" (≥1 visit) and "high" (≥3 visits). Results: Among 5,793 patients who met inclusion criteria, 4,687 (80.9%) had any (≥1) telemedicine visit and 1,053 (18.2%) had high (≥3) telemedicine visits during the COVID-19 period. Older age and Medicare coverage were associated with having any telemedicine use. Older and White patients were more likely to have high telemedicine use. Uninsured patients were less likely to have high telemedicine use. Patients with increased health care utilization in the pre-COVID-19 period and those with hypertension, diabetes, substance use disorders, and depression were more likely to have high telemedicine engagement. Discussion: Chronic conditions, older patients, and White patients compared with Latinx patients, were associated with high telemedicine engagement after adjusting for prior health care utilization. Conclusion: Equity-focused approaches to telemedicine clinical strategies are needed for safety-net populations. Community health centers can adopt disease-specific telemedicine strategies with high patient engagement.

Changes in Acute ED Visits by Race/Ethnicity During the Early COVID-19 Pandemic.

Emergency department (ED) visits for conditions unrelated to the Coronavirus Disease 2019 (COVID-19) pandemic decreased during the early pandemic, raising concerns about critically ill patients forgoing care and increasing their risk of adverse outcomes. It is unclear if Hispanic and Black adults, who have a high prevalence of chronic conditions, sought medical assistance for acute emergencies during this time. This study used 2018-2020 ED visit data from the largest safety net hospital in Los Angeles County to estimate ED visit differences for cardiac emergencies, diabetic complications, and strokes, during the first societal lockdown among Black and Hispanic patients using time series analyses. Emergency department visits were lower than the expected levels during the first societal lockdown. However, after the lockdown ended, Black patients experienced a rebound in ED visits while visits for Hispanics remained depressed. Future research could identify barriers Hispanics experienced that contributed to prolonged ED avoidance.

Experiences of distress and gaps in government safety net supports among parents of young children during the COVID-19 pandemic: a qualitative study.

BACKGROUND: The COVID-19 pandemic prompted rapid federal, state, and local government policymaking to buffer families from the health and economic harms of the pandemic. However, there has been little attention to families' perceptions of whether the pandemic safety net policy response was adequate, and what is needed to alleviate lasting effects on family well-being. This study examines the experiences and challenges of families with low incomes caring for young children during the pandemic. METHODS: Semi-structured qualitative interviews conducted from August 2020 to January 2021 with 34 parents of young children in California were analyzed using thematic analysis. RESULTS: We identified three key themes related to parents' experiences during the pandemic: (1) positive experiences with government support programs, (2) challenging experiences with government support programs, and (3) distress resulting from insufficient support for childcare disruptions. Participants reported that program expansions helped alleviate food insecurity, and those attending community colleges reported accessing a range of supports through supportive counselors. However, many reported gaps in support for childcare and distance learning, pre-existing housing instability, and parenting stressors. With insufficient supports, additional childcare and education workloads resulted in stress and exhaustion, guilt about competing demands, and stagnation of longer-term goals for economic and educational advancement. CONCLUSIONS: Families of young children, already facing housing and economic insecurity prior to the pandemic, experienced parental burnout. To support family well-being, participants endorsed policies to remove housing barriers, and expand childcare options to mitigate job loss and competing demands on parents. Policy responses that either alleviate stressors or bolster supports have the potential to prevent distress catalyzed by future disasters or the more common destabilizing experiences of economic insecurity.

CRV-NET: Robust Intensity Recognition of Coronavirus in Lung Computerized Tomography Scan Images.

The early diagnosis of infectious diseases is demanded by digital healthcare systems. Currently, the detection of the new coronavirus disease (COVID-19) is a major clinical requirement. For COVID-19 detection, deep learning models are used in various studies, but the robustness is still compromised. In recent years, deep learning models have increased in popularity in almost every area, particularly in medical image processing and analysis. The visualization of the human body's internal structure is critical in medical analysis; many imaging techniques are in use to perform this job. A computerized tomography (CT) scan is one of them, and it has been generally used for the non-invasive observation of the human body. The development of an automatic segmentation method for lung CT scans showing COVID-19 can save experts time and can reduce human error. In this article, the CRV-NET is proposed for the robust detection of COVID-19 in lung CT scan images. A public dataset (SARS-CoV-2 CT Scan dataset), is used for the experimental work and customized according to the scenario of the proposed model. The proposed modified deep-learning-based U-Net model is trained on a custom dataset with 221 training images and their ground truth, which was labeled by an expert. The proposed model is tested on 100 test images, and the results show that the model segments COVID-19 with a satisfactory level of accuracy. Moreover, the comparison of the proposed CRV-NET with different state-of-the-art convolutional neural network models (CNNs), including the U-Net Model, shows better results in terms of accuracy (96.67%) and robustness (low epoch value in detection and the smallest training data size).

Platelet-neutrophil interaction in COVID-19 and vaccine-induced thrombotic thrombocytopenia.

Coronavirus disease 2019 (COVID-19) is known to commonly induce a thrombotic diathesis, particularly in severely affected individuals. So far, this COVID-19-associated coagulopathy (CAC) has been partially explained by hyperactivated platelets as well as by the prothrombotic effects of neutrophil extracellular traps (NETs) released from neutrophils. However, precise insight into the bidirectional relationship between platelets and neutrophils in the pathophysiology of CAC still lags behind. Vaccine-induced thrombotic thrombocytopenia (VITT) is a rare autoimmune disorder caused by auto-antibody formation in response to immunization with adenoviral vector vaccines. VITT is associated with life-threatening thromboembolic events and thus, high fatality rates. Our concept of the thrombophilia observed in VITT is relatively new, hence a better understanding could help in the management of such patients with the potential to also prevent VITT. In this review we aim to summarize the current knowledge on platelet-neutrophil interplay in COVID-19 and VITT.

Ecosystem degradation and the spread of Covid-19.

The linkages between the emergence of zoonotic diseases and ecosystem degradation have been widely acknowledged by the scientific community and policy makers. In this paper we investigate the relationship between human overexploitation of natural resources, represented by the Human Appropriation of Net Primary Production Index (HANPP) and the spread of Covid-19 cases during the first pandemic wave in 730 regions of 63 countries worldwide. Using a Bayesian estimation technique, we highlight the significant role of HANPP as a driver of Covid-19 diffusion, besides confirming the well-known impact of population size and the effects of other socio-economic variables. We believe that these findings could be relevant for policy makers in their effort towards a more sustainable intensive agriculture and responsible urbanisation.