A review on water-saving agriculture in Europe

This paper aims to analyze the research on the current situation of water-saving agriculture development in Europe. Water-saving agriculture in Europe started early, governments and farmers in various countries have a strong awareness of water-saving in agriculture and have achieved certain results. Due to the global spread of the COVID-19 pandemic, the lack of up-to-date field research, the complexity of various agricultural disciplines and categories, and the lack of information sharing, the current cognition of recent progress in the development of water-saving agriculture in Europe is not comprehensive enough. This paper selects four representative European countries: Spain, Germany, Italy, and Denmark as the research objects. Based on the existing research of Chinese and Western scholars, this paper analyzes and studies the current situation of water-saving agriculture in Europe. It has far-reaching significance for other countries in the world to have further development in water-saving agriculture and to protect water resources.

Mixup-Inf-Net: A data augmentation algorithm for segmentation of new coronary pneumonia infections

In 2020, the global spread of Coronavirus Disease 2019 exposed entire world to a severe health crisis. This has limited fast and accurate screening of suspected cases due to equipment shortages and and harsh testing environments. The current diagnosis of suspected cases has benefited greatly from the use of radiographic brain imaging, also including X-ray and scintigraphy, as a crucial addition to screening tests for new coronary pneumonia disease. However, it is impractical to gather enormous volumes of data quickly, which makes it difficult for depth models to be trained. To solve these problems, we obtained a new dataset by data augmentation Mixup method for the used chest CT slices. It uses lung infection segmentation (Inf-Net [1]) in a deep network and adds a learning framework with semi-supervised to form a Mixup-Inf-Net semi-supervised learning framework model to identify COVID-19 infection area from chest CT slices. The system depends primarily on unlabeled data and merely a minimal amount of annotated data is required;therefore, the unlabeled data generated by Mixup provides good assistance. Our framework can be used to improve improve learning and performance. The SemiSeg dataset and the actual 3D CT images that we produced are used in a variety of tests, and the analysis shows that Mixup-Inf-Net semi-supervised outperforms most SOTA segmentation models learning framework model in this study, which also enhances segmentation performance. © 2023 SPIE.

New Approaches to the Economic Security of Russian Regions in Terms of the COVID-19 Pandemic

The study aims to identify the problems of economic security of the Russian regions under the influence of force majeure caused by the pandemic COVID-19 and their assessment, as well as to determine ways to stabilize the socio-economic situation. The authors conducted a grouping of the economic security indicators of the federal districts and proposed a methodology for its assessment in terms of the coronavirus pandemic. The authors identified the problem areas of socio-economic development of the Russian regions and also proved the decline in their economic security during the pandemic. The authors evaluated the effectiveness of the internal state administration of the federal districts according to the anti-crisis measures adopted in 2020 (maintaining turnover in the main regional segments of the economy, avoiding tax debt on regional fees, increasing the profitability of the real business, raising the level of digital development), as well as measures to preserve employment and solvency of the population of each region. The authors justified the directions of normalization of the socio-economic development of the federal districts of Russia by eliminating the economic security problems. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.

Global Governance in the New Era: Concepts and Approaches

This book mainly introduces the concepts and approaches of global governance from the viewpoints of Chinese and Russian scholars and is divided into four parts. The first one deals with the concept of a new type of global governance, namely "Globalization 2.0". The second one is dedicated to institutions and multilateralism, including the importance and effectiveness of international institutions. The third part focuses on the important countries and regions in the new era, as well as such issues as the current global status quo, processes in Eurasia, the prospects of the U.S.-China-Russia trilateral relationship. The last part analyzes the future development of global governance and possible solutions of how it might be improved. Climate change, digital era, cyber security, financial and economic regimes, COVID-19 are all involved in this part. In short, this book is a profound and cutting-edge research on global governance. © China Social Sciences Press 2023.

Fast de novo antibody structure prediction with atomic accuracy

Background: In the field of antibody engineering, an essential task is to design a novel antibody whose paratopes bind to a specific antigen with correct epitopes. Understanding antibody structure and its paratope can facilitate a mechanistic understanding of its function. Therefore, antibody structure prediction from its sequence alone has always been a highly valuable problem for de novo antibody design. AlphaFold2 (AF2), a breakthrough in the field of structural biology, provides a solution to this protein structure prediction problem by learning a deep learning model. However, the computational efficiency and undesirable prediction accuracy on antibody, especially on the complementarity-determining regions limit its applications in de novo antibody design. Method(s): To learn informative representation of antibodies, we trained a deep antibody language model (ALM) on curated sequences from observed antibody space database via a well-designed transformer model. We also developed a novel model named xTrimoABFold++ to predict antibody structure from antibody sequence only based on the pretrained ALM as well as efficient evoformers and structural modules. The model was trained end-to-end on the antibody structures in PDB by minimizing the ensemble loss of domain-specific focal loss on CDR and the frame aligned point loss. Result(s): xTrimoABFold++ outperforms AF2 and OmegaFold, HelixFold-Single with 30+% improvement on RMSD. Also, it is 151 times faster than AF2 and predicts antibody structure in atomic accuracy within 20 seconds. In recently released antibodies, for example, cemiplimab of PD1 (PDB: 7WVM) and cross-neutralizing antibody 6D6 of SARS-CoV-2 (PDB: 7EAN), the RMSD of xTrimoABFold++ are 0.344 and 0.389 respectively. Conclusion(s): To the best of our knowledge, xTrimoABFold++ achieved the state-of-the-art in antibody structure prediction. Its improvement on both accuracy and efficiency makes it a valuable tool for de novo antibody design, and could make further improvement in immuno-theory.

Consumers' fear regarding food security in Slovenia during the first wave of COVID-19 crisis

The various crises are having a significant impact on the entire food sector and are changing the attitudes of Europeans as well as policies on the importance of food security and sustainably produced quality and safe food for consumer health. The paper focuses on the consumer's fear of food security for the time of the first wave of COVID-19 and the associated concern for food security in the future and the changes in consumer behaviour. The online survey in Slovenia was conducted in June 2020 using a "snowball" method. The sample included 490 individuals. The results showed that both measured forms of fear (i) fear over food security during the first wave of COVID-19 crisis, and (ii) fear over food security in the future were statistically significant, moderately strong and positively associated with almost all forms of self-perceived behaviour change caused by the COVID-19 crisis. The respondents focused more on buying locally produced and processed food, food stockpiling and decreasing food waste. Only minor changes were expressed with regards to their food purchasing channels, with the elderly, the highly educated and those who classified themselves in a higher social class buying more often directly from farmers. In the future, the results of this research should be compared with other countries and the impact of an individual's economic situation and the impact of promotional campaigns on agricultural products on changing consumer behaviour should also be analysed in more detail.

Modelling COVID-19 effect on the performance of MENA Health-care sector

PurposeThis study models the effects of the COVID-19 pandemic on the performance of the private health-care sector in the Middle East and North Africa (MENA) countries. This paper aims to address the economic, societal and sustainability of the health-care sector.Design/methodology/approachData were collected from Bloomberg and the sample consists of 534 firm-year observations from 55 firms listed over 2010–2020. The authors apply panel data and control for the country and governance effects.FindingsThe authors found heterogeneous results regarding the three sub-sectors. The pandemic has a negative effect on the accounting and market performances of the "Pharmaceutical companies” and an insignificant impact on "Healthcare Management and Facilities Services.” Moreover, the impact of COVID-19 on health-care firms' performance depends on the country's economic classification and the degree of regulatory and governance frameworks.Research limitations/implicationsFurther studies may consider a larger sample and other regions. It is recommended to address the health-care sector's challenges to invest in new technologies such as "digital twin” and predictive and personalized medicine. It is worth testing model development theory and its effects on speeding up and designing models to ensure the proper functioning and developing mathematics to determine uncertainties in patient data and model predictions.Originality/valueTo the best of the authors' knowledge, this paper is novel as it is unique in modeling the impact of COVID-19 on the health-care public companies in the MENA region. The findings pinpoint firms' and countries' heterogeneous impacts on financial and market performances.

Increases in expression of carbohydrate sulfotransferases CHST11 and CHST15 and decline in N-acetylgalactosamine-4-sulfatase (Arylsulfatase B, ARSB) require phospho-p38-MAPK following exposure to SARS-CoV-2 spike protein receptor binding domain in human a

Objective: Immunohistochemistry of post-mortem lung tissue from Covid-19 patients with diffuse alveolar damage demonstrated marked increases in chondroitin sulfate and CHST15 and decline in N-acetylgalactosamine-4-sulfatase. Studies were undertaken to identify the mechanisms involved in these effects. Method(s): Human primary small airway epithelial cells (PCS 301-010;ATCC) were cultured and exposed to the SARSCoV- 2 spike protein receptor binding domain (SPRBD;AA: Lys310-Leu560;Amsbio). Expression of the spike protein receptor, angiotensin converting enzyme 2 (ACE2), was enhanced by treatment with Interferon-beta. Promoter activation, DNA-binding, RNA silencing, QPCR, Western blots, ELISAs, and specific enzyme inhibitors were used to elucidate the underlying molecular mechanisms. Result(s): Treatment of the cultured cells by the SPRBD led to increased CHST15 and CHST11 expression and decline in ARSB expression. Sulfotransferase activity, total chondroitin sulfate, and sulfated glycosaminoglycan (GAG) content were increased. Phospho-T180/T182-p38-MAPK and phospho- S423/S425-Smad3 were required for the activation of the CHST15 and CHST11 promoters. Inhibition by SB203580, a phospho-p38 MAPK inhibitor, and by SIS3, a Smad3 inhibitor, blocked the CHST15 and CHST11 promoter activation. SB203580 reversed the SPRBD-induced decline in ARSB expression, but SIS3 had no effect on ARSB expression or promoter activation. Phospho-p38 MAPK was shown to reduce retinoblastoma protein (RB) S807/S811 phosphorylation and increase RB S249/T252 phosphorylation. E2F-DNA binding declined following exposure to SPRBD, and SB203580 reversed this effect. This indicates a mechanism by which SPRBD, phospho-p38 MAPK, E2F, and RB can regulate ARSB expression and thereby impact on chondroitin 4-sulfate and dermatan sulfate and molecules that bind to these sulfated GAGs, including Interleukin-8, bone morphogenetic protein-4, galectin-3 and SHP-2 (Src homology region 2-containing protein tyrosine phosphatase 2). Conclusion(s): The enzyme ARSB is required for the degradation of chondroitin 4-sulfate and dermatan sulfate, and accumulation of these sulfated GAGs can contribute to lung pathophysiology, as evident in Covid-19. Some effects of the SPRBD may be attributable to unopposed Angiotensin II, when Ang1-7 counter effects are diminished due to binding of ACE2 with the SARS-CoV-2 spike protein and reduced production of Ang1-7. Aberrant cell signaling and activation of the phospho-p38 MAPK and Smad3 pathways increase CHST15 and CHST11 production, which can contribute to increased chondroitin sulfate in infected cells. Decline in ARSB may occur as a consequence of effects of phospho-p38 MAPK on RB phosphorylation and E2F1 availability. Decline in ARSB and the resulting impaired degradation of sulfated GAGs have profound consequences on cellular metabolic, signaling, and transcriptional events. Funding is VA Merit Award.Copyright © 2023 The American Society for Biochemistry and Molecular Biology, Inc.

Masked Face Recognition Model with Explainable AI

Due to the recent COVID-19 pandemic, people tend to wear masks indoors and outdoors. Therefore, systems with face recognition, such as FaceID, showed a tendency of decline in accuracy. Consequently, many studies and research were held to improve the accuracy of the recognition system between masked faces. Most of them targeted to enhance dataset and restrained the models to get reasonable accuracies. However, not much research was held to explain the reasons for the enhancement of the accuracy. Therefore, we focused on finding an explainable reason for the improvement of the model's accuracy. First, we could see that the accuracy has actually increased after training with a masked dataset by 12.86%. Then we applied Explainable AI (XAI) to see whether the model has really focused on the regions of interest. Our approach showed through the generated heatmaps that difference in the data of the training models make difference in range of focus. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

An Empirical Study of the Effect of Emotional Intelligence on Job Performance the Case Study of Educational Non-Governmental Organizations During the Covid-19 Outbreak

The Third-sector organizations, known as Non-Governmental Organizations (NGOs) working on had an essential role in improving education, building human capital, sustainable development, humanitarian aid, and raising entrepreneurs, especially in the areas of political conflict and increased poverty. This research aims to analyze the effect of Emotional Intelligence on Job Performance in three selected Educational and human aid NGOs in the Kurdistan Region/Iraq during the Covid-19 pandemic. This research is claimed to be novel to study the concepts in businesses on NGOs. The author used a self-administered questionnaire with included two validated measures and demographic items. The data has been collected from 83 respondents working as employees in the NGOs selected. The author used Pearson correlation, ANOVA, and linear regression to justify the hypothesis developed. The results show a strong positive relationship between EI and job performance. The EI positively and significantly affects Job Performance and there is no difference between the genders of the study in terms of Emotional Intelligence and Job performance. The study recommends educational and human aid NGOs consider EI as an important factor in increasing the performance of their employees, and this research is to be a foundation for further research to understand the application of management concepts of Businesses in the context of NGOs.

THE RELATIONSHIP BETWEEN THE FUNCTIONALITY OF CHILDREN WITH DISABILITIES AND ITS EFFECTS ON PARENTS DURING THE COVID-19 PANDEMIC PROCESS.

Purpose: The aim of this study was to investigate the relationship between the functionality of disabled children and its effects on parents during the Covid-19 pandemic. Method(s): A total of 168 people, including 84 disabled children and 84 mothers, were included in the study. The Pediatric Disability Assessment Inventory (PEDI) and Gross Motor Function Classification System (GMFCS) were used for children with disabilities. The Zarit Burden Scale (ZBS), Fatigue Severity Scale (FSS) and The Nordic Musculoskeletal Questionnaire (NMQ) were applied to the mothers to question musculoskeletal disorders. Result(s): There was no correlation between care burden score and PEDI, total score, self-care and mobility scores (p>0.05). A moderately negative (r=-0.306;p<0.01) significant linear relationship was found between care burden score and social function score. There was no significant linear relationship between the fatigue severity score and PEDI total score, self-care, mobility and social function scores (p>0.05). No correlation was found between care burden score and fatigue severity score (p>0.05). For the last 12 months, only the pain in the lumbar region of the parents prevented them from doing their usual work. It was determined that the most aching body parts of the parents who complained of musculoskeletal pain during the last 12 months were in the waist, neck, shoulder, back, and knee regions. Conclusion(s): As a result, no relationship was found between the functionality of disabled children and their parents' influences during the Covid-19 pandemic.Copyright © 2022 Turkish Physiotherapy Association. All rights reserved.

Role of the Digital for the Third Sector in the Campania Region (Italy): From the Side of Research to the Side of the Objects in the Aftermath of the COVID-19 Pandemic

This paper aims to investigate the role of the digital in facing the social and practical impact of COVID-19 pandemic on particularly fragile and affected realities, Third Sector Organizations (TSO), in a context pervaded by structural and socio-economic weaknesses, the Campania Region in the South of Italy. It analyzes the digital object as: 1. a process - digitization/digitalization and digital transformation;2. a scenario - in which identities, activities and alternative spaces of use or data collection transit and are constructed;3. skills and capabilities - as social capital and value. This re-framing work is intended to be a useful tool for reflecting on the role of digital in research processes, while also offering a contribution in the debate on the Third Sector in contexts of crisis, such as the one generated by the COVID-19 pandemic, that impacts its existence, activity, shape, and perspectives. © This is an open access, peer reviewed article published under the Creative Commons License (CC BY 3.0).

Guidelines for the Region's Socio-economic Policies During the Pandemic

The study focuses on identifying the benefits of implementing the region's socio-economic policies according to the principles of lean production to overcome the negative effects of the COVID-19 pandemic. The author investigates the problems of socio-economic development of the regions of Russia during the COVID-19 pandemic, identifies the most significant threats to the regions (rising unemployment, falling average per capita incomes of the population, reduction of regional budgets and growth of regional public debt). The author proved that the principles of lean production can be successfully implemented as fundamental in the implementation of the socio-economic policy of the region. The focus of regional socio-economic policies during the pandemic should be the optimization of the cost of maintaining the region's public administration and increasing the quality of regional governance;improving regional policies to support people in the aftermath of a pandemic;developing the infrastructure and businesses implementing lean technologies. The author developed an algorithm for the formation and realization of regional socio-economic policy according to the principles of lean production during the pandemic, as well as describes the features of its implementation in the Belgorod Region. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.

Assessment of adjustment disorder in people with COVID-19 infection

Objective: This study aimed to evaluate the development of adjustment disorder according to the ADNM-20 (Adjustment Disorder New Module-20) scale in participants who were followed up for Covid-19 infection. Methods: A cross-sectional survey was conducted from September to November 2020. After sample size calculation, we aimed to reach minimum 170 people out of 1290 people who applied to the hospital for Covid-19 disease treatment. Participants were selected from the patients admitted to the hospital using a simple stratified random sampling method. We reached 182 people after treating the patients who were followed up with Covid-19 infection in a University Hospital in Istanbul, Turkey. A questionnaire and the Adjustment Disorder New Module-20 scale were applied via phone / mail at the end of the 6th month after Covid-19 related hospital admission by researchers. Results: Adjustment disorder was found in 28.8% (n=42) of the participants disorder according to the ADNM-20 scale. While the rate of development of adjustment disorder due to Covid-19-related stress was 26.7% (n=39);the rate of development of adjustment disorder due to non-Covid-19 stress was found to be 2.1% (n=3). With the increase in stress load, the development of adjustment disorder increased significantly. The frequency of developing Covid-19-related stress-related adjustment disorder was statistically significantly increased with the duration of exposure to stress. Conclusion: We have found out that one out of every four people who apply to the hospital for healthcare services due to Covid-19 infection may develop an adjustment disorder. Assessment of the adjustment disorder more frequently and making early interventions may contribute to the prevention of progressive mental disorders.

Economic policy uncertainty and international tourist arrivals: a disaggregated analysis of the Croatian Adriatic coast

This is the first study to examine the differential impact of Croatian and European economic policy uncertainty indices while controlling for the real effective exchange rate and industrial production on international tourist arrivals for the seven coastal counties of Croatia and the country as a whole. The Toda-Yamamoto long-run causality modeling approach with a Fourier approximation is employed to capture structural shifts. This approach is particularly useful in light of the disruption from the COVID-19 pandemic on the tourism sector. The results show unidirectional causality from both Croatian and European economic policy uncertainty indices to international tourist arrivals with the impact of the economic policy uncertainty indices negative and statistically significant across the respective coastal counties. Moreover, the findings show that European economic policy uncertainty exhibits a greater adverse impact on international tourist arrivals relative to Croatian economic policy uncertainty.

Assessment of positive airway pressure treatment adherence and sleep quality in sleep apnea patients during COVID-19 pandemic: multi-center cross-sectional study results

Background: Patients with obstructive sleep apnea (OSA), related to their disease consequences and treatment modalities, are physically and mentally vulnerable during the outbreak. Objectives: To investigate the association between pandemic-related changes and positive airway pressure (PAP) adherence and sleep quality in OSA patients. Methods: This was a multi-center cross-sectional study, and the necessary data were collected prospectively. A total of 221 patients were included in the study, who were invited from four different centers from June 1 - December 1, 2020. Pittsburgh Sleep Quality Index (PSQI) was administered to evaluate sleep quality. Information on demographics positive airway pressure (PAP) device use, Coronavirus disease (COVID-19) a questionnaire collected related changes. Patients >18 years with a diagnosis of OSA and prescribed PAP treatment before the pandemic period were included in the study. Lack of cooperation with the questionnaires and incompliant with PAP treatment for longer than one year were the exclusion criteria. Results: Of the 221 participants, 79.2% were men. The mean apnea-hypopnea index was obtained at 40.8+or-24.3. A positive COVID-19 test was reported in nine cases, and three patients had hospitalization. During the pandemic, 102 (46.2%) subjects were retired, 26 (11.8%) lost their jobs, and 34 (15.3%) reported home office work or on-call or on leave. Poor sleep quality was found in 54 (24.4%) individuals. It was also reported that poor sleep quality was more common in those who reported mask use difficulty (38.7% vs. 18.9%;P=0.004) and increased or decreased PAP use (increased, decreased, no change in PAP use: 45.5%, 36.0%, 19.4%, respectively;P=0.01). The good sleep quality group had higher PAP use than the poor sleep quality group (6.2+or-1.5 vs. 5.3+or-2.4 night/week;P=0.002;6.2+or-1.5 vs. 5.5+or-2.2 hour/night;P=0.01). Conclusions: Pandemic period had several negative effects on sleep apnea patients regarding sleep quality and social lives which also influenced PAP adherence in OSA patients. Most patients did not change their regular PAP use attitudes during this period. Similar to the pre-COVID-19 disease period, PAP adherence and compliance positively influenced sleep quality;people who were "good sleepers" were the ones who were the "good PAP device users".

The Influence of Intellectual and Innovative Determinants on the Development of Regions in the Conditions of COVID-19 and Global Digitalization

The social challenges of modern globalization caused by the COVID-19 pandemic have led to significant changes in the development of economic systems at various levels. Social development in the direction of a post-industrial society activates the introduction of digital technologies in all areas of life, which requires paying attention not only to the innovative component of its development, but also to the intellectual one, since the digital transformation requires a constant updating of knowledge;this determines the purpose of this scientific study. The article aims to highlight the influence of intellectual and innovative determinants in the development of regions under current conditions, which are outlined by the manifestations of the COVID-19 pandemic and global digitalization in the development of economic systems. The foundation of the system approach methodology made it possible to distinguish the development trends of the regions in the conditions of the COVID-19 pandemic and global digitalization. It is proposed to create guidelines for the intellectual and innovative promotion, determinants of the development of the regions in the conditions of the COVID-19 pandemic and global digitalization, according to the socioeconomic, scientific-technological, organizational and legal components. The main guidelines of efforts to increase the role of intellectual and innovative determinants in the development of regional systems in the conditions of the COVID-19 pandemic and global digitalization have been tested, taking into account the principles of complexity, integrity, flexibility, efficiency and long term.

COVID-19: our experience and quality of management analysis: (Topolsica Hospital case report)

Various Slovenian hospitals were recruited to treat COVID-19 patients in Slovenia during the COVID-19 epidemic. Centrally coordinated hospital utilisation - depending on the needs, available hospital bed capacity, and considering the professional orientation of individual hospitals - left these facilities with different experiences. We present our experience and COVID-19 treatment management during the fourth epidemic wave in our peripheral, pulmonary-oriented hospital, representing the first treatment quality analysis of these patients in Slovenia. The basic hospitalization characteristics were analysed using integrated Birpis information system solutions and the electronic temperature-therapeutic charts (eTTL) review. The quality of management was assessed through adherence to professional recommendations. The analysis was carried out with the in-built statistical functions of Microsoft Excel software. 99 patients (58 women, 41 men) aged 67.9 years were hospitalised for an average of 8.1 days. The majority were residents of our region (61%), unvaccinated (61.6%), and experienced a severe form of the disease with the need for oxygen supplementation (88.9%). The majority received steroids (73.7%), antibiotics (68.7%) and vitamin D (71.7%), to a lesser extent specific therapy (remdesivir 25.3%, combination casirivimab/imdevimab 2%, tocilizumab 1%). No adverse reactions were noted. 17 people died (total mortality rate 17.2%). There was no infection transmission among the COVID department staff. Results show successful treatment of patients with COVID-19 in Topolsica Hospital. They also suggest the possibility of further improvements, particularly in prescribing antibiotic therapy.

Unmuting the patient voice: Coproducing a virtual, structured education group for patients newly diagnosed with type 2 diabetes

Aim: A structured education group for adults newly diagnosed with type 2 diabetes has been offered in a face-to- face (F2F) format in the health board since 2009. The suspension of in-person groups due to Covid-19 catalysed redevelopment of the group in a virtual, interactive format. Method(s): The aims and objectives of the virtual group were extended from the original F2F format, and the teaching resources were diversified to include film, animations and a workbook. Patients newly diagnosed with type 2 diabetes, were contacted using a standardised engagement protocol and offered the opportunity to join the virtual group. A series of pilot groups were delivered. The Plan-Do- Study- Act (PDSA) model was used. Each pilot group was studied using mixed method data collection and critiqued by patients, the educator and the team, to improve the delivery methods and patient experience. Result(s): Over six months, eight groups were conducted. Forty-six patients were invited and 30 attended. Engagement was higher in the virtual option compared to usual care prior to the pandemic (65% compared to 55%). Results from feedback forms showed that the majority of respondents either agreed (13%) or strongly agreed (80%) that the group had improved their understanding of type 2 diabetes. The group was given a Net Promoter Score (NPS) of 100. Conclusion(s): The digital option provides a feasible model to deliver an alternative interactive, structured group education programme at diagnosis of type 2 diabetes. The next step involves developing an engagement programme with primary care and application for QISMET accreditation.

Medical image mis-segmentation region refinement framework based on dynamic graph convolution

In medical image segmentation tasks, it is hard for traditional Convolutional Neural Network (CNN) to capture essential information such as spatial structure and global contextual semantic features since it suffers from a limited receptive field. The deficiency weakens the CNN segmentation performance in the lesion boundary regions. To handle the aforementioned problems, a medical image mis-segmentation region refinement framework based on dynamic graph convolution is proposed to refine the boundary and under-segmentation regions. The proposed framework first employs a lightweight dual-path network to detect the boundaries and nearby regions, which can further obtain potentially misclassified pixels from the coarse segmentation results of the CNN. Then, we construct the pixels into the appropriate graphs by CNN-extracted features. Finally, we design a dynamic residual graph convolutional network to reclassify the graph nodes and generate the final refinement results. We chose UNet and its eight representative improved networks as the basic networks and tested them on the COVID, DSB, and BUSI datasets. Experiments demonstrated that the average Dice of our framework is improved by 1.79%, 2.29%, and 2.24%, the average IoU is improved by 2.30%, 3.53%, and 2.39%, and the Se is improved by 5.08%, 4.78%, and 5.31% respectively. The experimental results prove that the proposed framework has the refinement capability to remarkably strengthen the segmentation result of the basic network. Furthermore, the framework has the advantage of high portability and usability, which can be inserted into the end of mainstream medical image segmentation networks as a plug-and-play enhancement block.