COVID-19 severity detection using chest X-ray segmentation and deep learning.

COVID-19 has resulted in a significant global impact on health, the economy, education, and daily life. The disease can range from mild to severe, with individuals over 65 or those with underlying medical conditions being more susceptible to severe illness. Early testing and isolation are vital due to the virus's variable incubation period. Chest radiographs (CXR) have gained importance as a diagnostic tool due to their efficiency and reduced radiation exposure compared to CT scans. However, the sensitivity of CXR in detecting COVID-19 may be lower. This paper introduces a deep learning framework for accurate COVID-19 classification and severity prediction using CXR images. U-Net is used for lung segmentation, achieving a precision of 0.9924. Classification is performed using a Convulation-capsule network, with high true positive rates of 86% for COVID-19, 93% for pneumonia, and 85% for normal cases. Severity assessment employs ResNet50, VGG-16, and DenseNet201, with DenseNet201 showing superior accuracy. Empirical results, validated with 95% confidence intervals, confirm the framework's reliability and robustness. This integration of advanced deep learning techniques with radiological imaging enhances early detection and severity assessment, improving patient management and resource allocation in clinical settings.

Overcoming copper-induced conversion reactions in nickel disulphide anodes for sodium-ion batteries.

Employing copper (Cu) as an anode current collector for metal sulphides is perceived as a general strategy to achieve stable cycle performance in sodium-ion batteries, despite the compatibility of the aluminium current collector with sodium at low voltages. The capacity retention is attributed to the formation of copper sulphide with the slow corrosion of the current collector during cycling which is not ideal. Conventional reports on metal sulphides demonstrate excellent electrochemical performances using excessive carbon coatings/additives, reducing the overall energy density of the cells and making it difficult to understand the underlying side reaction with Cu. In this report, the negative influence of the Cu current collector is demonstrated with in-house synthesised, scalable NiS2 nanoparticles without any carbon coating as opposed to previous works on NiS2 anodes. Ex situ TEM and XPS experiments revealed the formation of Cu2S, further to which various current collectors were employed for NiS2 anode to rule out the parasitic reaction and to understand the true performance of the material. Overall, this study proposes the utilisation of carbon-coated aluminium foil (C/Al) as a suitable current collector for high active material content NiS2 anodes and metal sulphides in general with minimal carbon contents as it remains completely inert during the cycling process. Using a C/Al current collector, the NiS2 anode exhibits stable cycling performance for 5000 cycles at 50 A g-1, maintaining a capacity of 238 mA h g-1 with a capacity decay rate of 8.47 × 10-3% per cycle.

Abnormal Silicon Etching Behaviors in Nanometer-Sized Channels.

Modern semiconductor fabrication is challenged by difficulties in overcoming physical and chemical constraints. A major challenge is the wet etching of dummy gate silicon, which involves the removal of materials inside confined spaces of a few nanometers. These chemical processes are significantly different in the nanoscale and bulk. Previously, electrical double-layer formation, bubble entrapment, poor wettability, and insoluble intermediate precipitation have been proposed. However, the exact suppression mechanisms remain unclear due to the lack of direct observation methods. Herein, we investigate limiting factors for the etching kinetics of silicon with tetramethylammonium hydroxide at the nanoscale by using liquid-phase transmission electron microscopy, three-dimensional electron tomography, and first-principles calculations. We reveal suppressed chemical reactions, unstripping phenomena, and stochastic etching behaviors that have never been observed on a macroscopic scale. We expect that solutions can be suggested from this comprehensive insight into the scale-dependent limiting factors of fabrication.

Development and Application of a Stability Index Estimation Algorithm Based on Machine Learning for Elderly Balance Ability Diagnosis in Daily Life.

BACKGROUND: The stability index estimation algorithm was derived and applied to develop and implement a balance ability diagnosis system that can be used in daily life. METHODS: The system integrated an approach based on sensory function interaction, called the clinical test of sensory interaction with balance. A capacitance and resistance sensing type force mat was fabricated, and a stability index prediction algorithm was developed and applied using the center of pressure variables. The stability index prediction algorithm derived a center of pressure variable for 103 elderly people by Nintendo Wii Balance Board to predict the stability index of the balance system (Biodex SD), and the accuracy of this approach was confirmed. RESULTS: As a result of testing with the test set, the linear regression model confirmed that the r-value ranged between 0.943 and 0.983. To confirm the similarity between the WBB and the flexible force mat, each measured center of pressure value was inputted and calculated in the developed regression model, and the result of the correlation coefficient validation confirmed an r-value of 0.96. CONCLUSION: The system developed in this study will be applicable to daily life in the home in the form of a floor mat.

Phlebosclerotic Colitis in a Healthy Young Female with Long-term Herbal Medicine Use.

Phlebosclerotic colitis is a rare form of intestinal ischemia. It is caused by calcified peripheral mesenteric veins and a thickened colonic wall. These characteristic findings can be identified on CT and colonoscopy. A 37-year-old female with a history of long-term herbal medicine use presented with acute lower abdominal pain and vomiting of sudden onset. Colonoscopic findings showed dark-blue discolored edematous mucosa and multiple ulcers from the ascending colon to the sigmoid colon. Abdominal CT findings showed diffuse thickening of the colonic wall and calcifications of the peripheral mesenteric veins from the ascending colon to the sigmoid colon. Based on these findings, the patient was diagnosed with phlebosclerotic colitis. We report this rare case of phlebosclerotic colitis in a healthy young female patient with a history of long-term herbal medicine use and include a review of the relevant literature.

Outcomes of surgery for coarctation of the aorta based on a new classification system.

OBJECTIVES: To evaluate early- and long-term outcomes of the surgical treatment for coarctation of the aorta based on a new classification system. METHODS: A retrospective clinical review of 111 patients with coarctation of the aorta who underwent surgery (March 2011 to August 2020) was performed. We categorised coarctation of the aorta into type I, with all three head vessels tightly packed; type II, with the left subclavian artery separated from the two other head vessels; and type III, with all three head vessels separated from one another. Each type included subtype a, with a short isthmic portion, and subtype b, with a long isthmic portion. RESULTS: The median patient age and weight at operation were 8 (range, 1-1490) days and 3.2 (range, 1.9-18.5) kg, respectively. Extended end-to-end anastomosis was performed via sternotomy in 54, via thoracotomy in 12, end-to-side anastomosis in 31, autologous main pulmonary artery patch augmentation in 12, and modified end-to-end anastomosis combined with subclavian artery flap aortoplasty in two patients. There was one (0.9%) case of early mortality and 12 (10.8%) cases of post-operative complications. Two (1.8%) late deaths occurred during follow-up. Five (4.5%) patients underwent balloon dilatation and three (2.7%) underwent reoperation for restenosis of coarctation of the aorta. All patients with type Ia (21 patients, 18.9%) underwent extended end-to-end anastomosis via sternotomy or thoracotomy. CONCLUSIONS: According to the early and late outcomes observed in this study, surgical treatment of coarctation of the aorta using the new classification system could be safe and low risk.

Edge/Fog Computing Technologies for IoT Infrastructure II.

The prevalence of smart devices and cloud computing has led to an explosion in the amount of data generated by IoT devices [...].

Local Scheduling in KubeEdge-Based Edge Computing Environment.

KubeEdge is an open-source platform that orchestrates containerized Internet of Things (IoT) application services in IoT edge computing environments. Based on Kubernetes, it supports heterogeneous IoT device protocols on edge nodes and provides various functions necessary to build edge computing infrastructure, such as network management between cloud and edge nodes. However, the resulting cloud-based systems are subject to several limitations. In this study, we evaluated the performance of KubeEdge in terms of the computational resource distribution and delay between edge nodes. We found that forwarding traffic between edge nodes degrades the throughput of clusters and causes service delay in edge computing environments. Based on these results, we proposed a local scheduling scheme that handles user traffic locally at each edge node. The performance evaluation results revealed that local scheduling outperforms the existing load-balancing algorithm in the edge computing environment.

Sensory Interaction and Balancing Ability Evaluation of the Elderly Using a Simplified Force Plate System.

The Wii balance board (WBB) is a simplified force plate system used to evaluate the balancing ability of the elderly via a sensory interaction task to confirm a significant standing balance index. The accuracy of this system has been verified in previous studies. In this study, an instrumented and modified clinical test of sensory interaction on balance (i-mCTSIB) was performed on 84 elderly subjects, and the variables for center of pressure (CoP) were calculated using WBB for each task condition. The results indicate that the visual condition has a significant effect on the sway proprioceptive sensory variables with a foam condition as their complexity increases. In addition, the correlation between the variable and Berg Balance Scale was not confirmed since CTSIB is a sensory interaction on balance ability. Therefore, WBB can be used to evaluate balancing ability based on sensory interactions consisting of the surface condition.

Regional Brain Volume Changes in Catholic Nuns: A Cross-Sectional Study Using Deep Learning-Based Brain MRI Segmentation.

OBJECTIVE: Religious behaviors are considered as complex brain-based phenomena that may be associated with structural brain change. To identify the pattern of regional brain volume change in nuns, we investigated structural alterations in the brains of nuns using a fast processing automated segmentation method based on deep learning algorithms. METHODS: We retrospectively reviewed the medical records of the catholic sisters between the ages of 31 and 80 who are members of the charity of St. Vincent de Paul of Korea. A total of 193 asymptomatic subjects (86 nuns and 107 control subjects) received comprehensive health screening and underwent brain MRI scans. We compared cortical and sub-cortical volume between groups across multiple locations using our in-house U-Net++ deep learning-based automatic segmentation tool. RESULTS: Compared to the control group, the nun group displayed increased gray matter volume in the right lingual cortex, left isthmus-cingulate, posterior-cingulate, rostral-middle-frontal, superior-frontal, supramarginal, temporal-pole cortices, and bilateral pars-triangularis cortices after correction for multiple comparisons. On the other hand, the nun group showed reduced gray matter volume in the temporal and parietal regions relative to healthy controls. CONCLUSION: Our study suggests that spiritual practice may affect brain structure, especially in several frontal regions involved in a higher level of insight function.

A Work-Related Musculoskeletal Disorders (WMSDs) Risk-Assessment System Using a Single-View Pose Estimation Model.

Musculoskeletal disorders are an unavoidable occupational health problem. In particular, workers who perform repetitive tasks onsite in the manufacturing industry suffer from musculoskeletal problems. In this paper, we propose a system that evaluates the posture of workers in the manufacturing industry with single-view 3D human pose-estimation that can estimate the posture in 3D using an RGB camera that can easily acquire the posture of a worker in a complex workplace. The proposed system builds a Duckyang-Auto Worker Health Safety Environment (DyWHSE), a manufacturing-industry-specific dataset, to estimate the wrist pose evaluated by the Rapid Limb Upper Assessment (RULA). Additionally, we evaluate the quality of the built DyWHSE dataset using the Human3.6M dataset, and the applicability of the proposed system is verified by comparing it with the evaluation results of the experts. The proposed system provides quantitative assessment guidance for working posture risk assessment, assisting the continuous posture assessment of workers.

Coronary artery spasm due to acute myocarditis in an adolescent: a case report.

BACKGROUND: Myocarditis refers to the inflammation of the myocardium caused by infection or autoimmune disease that may or may not present with clinical manifestations, such as gastrointestinal symptoms, dyspnea, chest pain, or sudden death. Although myocarditis and coronary artery vasospasm may mimic ST-segment elevation myocardial infarction (STEMI) with normal coronary arteries on angiography, acute myocarditis rarely causes coronary artery spasm. Here, we report a case of coronary artery spasm with reversible electrocardiographic changes mimicking STEMI in an adolescent with acute myocarditis. CASE PRESENTATION: A 15-year-old boy present with sudden-onset repeated chest pain following a 3-day history of flu-like illness. Cardiac biomarkers were significantly elevated. Electrocardiography showed ST-segment elevation in the absence of detectable vasospasm on coronary angiography. These findings were consistent with the diagnosis of coronary artery spasm secondary to acute myocarditis. Treatment with immunoglobulin for 2 days improved his condition. The patient was discharged on the 12th day with complete resolution of symptoms and normalization of electrocardiogram findings. CONCLUSIONS: We reported a case of coronary artery spasm due to acute myocarditis. This study highlights the importance of considering coronary artery spasm due to acute myocarditis as a differential diagnosis in patients presenting with signs of STEMI as these diseases have different medical management strategies.

Load-Balancing of Kubernetes-Based Edge Computing Infrastructure Using Resource Adaptive Proxy.

Kubernetes (K8s) is expected to be a key container orchestration tool for edge computing infrastructures owing to its various features for supporting container deployment and dynamic resource management. For example, its horizontal pod autoscaling feature provides service availability and scalability by increasing the number of replicas. kube-proxy provides traffic load-balancing between replicas by distributing client requests equally to all pods (replicas) of an application in a K8s cluster. However, this approach can result in long delays when requests are forwarded to remote workers, especially in edge computing environments where worker nodes are geographically dispersed. Moreover, if the receiving worker is overloaded, the request-processing delay can increase significantly. To overcome these limitations, this paper proposes an enhanced load balancer called resource adaptive proxy (RAP). RAP periodically monitors the resource status of each pod and the network status among worker nodes to aid in load-balancing decisions. Furthermore, it preferentially handles requests locally to the maximum extent possible. If the local worker node is overloaded, RAP forwards its requests to the best node in the cluster while considering resource availability. Our experimental results demonstrated that RAP could significantly improve throughput and reduce request latency compared with the default load-balancing mechanism of K8s.

Right Pulmonary Artery Originating from Ascending Aorta (Hemitruncus Arteriosus) with VACTERL Association in a Neonate: A Case Report.

Vertebral, anal, cardiac, tracheo-esophageal fistula, renal and limb (VACTERL) association is defined as a condition including at least three of the above-mentioned anomalies in the same infant. Several cardiac defects that have been reported as a part of the VACTERL association are ventricular and atrial septal defects, hypoplastic left heart syndrome, transposition of the great arteries and tetralogy of Fallot. Anomalous origin of pulmonary artery (AOPA) from the ascending aorta is an unusual and critical cardiovascular anomaly, which frequently involves the right pulmonary artery (RPA). A male neonate was delivered by normal spontaneous vaginal delivery at 39 weeks and 3 days gestation, weighting 2660 gm. He was diagnosed with VACTERL association with five abnormalities: vertebral abnormalities, anal atresia, cardiovascular anomaly (right pulmonary artery originating from ascending aorta), tracheo-esophageal fistula and renal anomalies. AOPA origination from ascending aorta as part of the VACTERL association in a neonate is a rare congenital cardiovascular malformation. Here we present a rare case of RPA originating from the ascending aorta seen with VACTERL association in a neonate.

Association of breastfeeding and risk of metabolic syndrome and its components in postmenopausal parous women: Korea national health and nutrition examination survey (2010 ~ 2016).

BACKGROUND: Understanding the relationship between breastfeeding (BF) and metabolic syndrome (Mets) is important for maternal long-term health benefits and disease prevention. This study aimed to examine the association between BF and Mets and its components among postmenopausal parous Korean women. METHODS: This cross-sectional study on 10,356 Korean women used nationally representative data from the KNHANES from 2010 to 2016. Anthropometric, laboratory data and manual BP were measured. A multivariate logistic regression analysis was conducted to examine the association of BF with Mets and its components after adjusting for potential confounding variables. A p-value < 0.05 was to be considered statistically significant. RESULTS: Mets was present in 42% of the study participants. The BF group had low household income and education level. The prevalence of Mets in the BF group was higher than that in the non-BF group (42.69% vs. 34.76%, p <  0.001). BF was associated with increased risk of Mets (odds ratio [OR]: 1.4, 95% confidence interval [CI]: 1.18-1.65, p <  0.001). The BF group was at higher risks for diabetes (OR: 1.5, 95%CI: 1.14-1.98), hypertension (OR: 1.32, 95%CI: 1.03-1.68), hypertriglyceridemia (OR: 1.42, 95%CI: 1.02-1.99) and low high-density lipoprotein cholesterol (OR: 1.32, 95%CI: 1.06-1.65). CONCLUSION: In this study, BF did not affect decreasing the prevalence of Mets and its components.

Edge/Fog Computing Technologies for IoT Infrastructure.

The prevalence of smart devices and cloud computing has led to an explosion in the amount of data generated by IoT devices [...].

A Case of Prenatally Diagnosed Uhl's Anomaly with Absent Pulmonary Valve Leaflets and Dysplastic Tricuspid Valve.

Uhl's anomaly is a very rare malformation of unknown cause, characterized by complete or partial absence of the right ventricular myocardium. The cardiac malformation causes progressive right heart failure, increased right-sided cardiac pressure, massive peripheral edema, and ascites. Patients usually present in infancy and rarely survive to adulthood. Previously, diagnosis was made at post-mortem evaluation, but advances in cardiac imaging now permit diagnosis during fetal life. We report a case of Uhl's anomaly in a newborn baby imaged at 23 + 3 weeks of gestation by fetal echocardiography. There was an aneurysmally dilated thin-walled right ventricle with hypertrophy of the right ventricular apical muscles, the tricuspid valve was dysplastic, and the pulmonary valve leaflets were absent.

Balanced Leader Distribution Algorithm in Kubernetes Clusters.

Container-based virtualization is becoming a de facto way to build and deploy applications because of its simplicity and convenience. Kubernetes is a well-known open-source project that provides an orchestration platform for containerized applications. An application in Kubernetes can contain multiple replicas to achieve high scalability and availability. Stateless applications have no requirement for persistent storage; however, stateful applications require persistent storage for each replica. Therefore, stateful applications usually require a strong consistency of data among replicas. To achieve this, the application often relies on a leader, which is responsible for maintaining consistency and coordinating tasks among replicas. This leads to a problem that the leader often has heavy loads due to its inherent design. In a Kubernetes cluster, having the leaders of multiple applications concentrated in a specific node may become a bottleneck within the system. In this paper, we propose a leader election algorithm that overcomes the bottleneck problem by evenly distributing the leaders throughout nodes in the cluster. We also conduct experiments to prove the correctness and effectiveness of our leader election algorithm compared with a default algorithm in Kubernetes.

Fast and Robust Time Synchronization with Median Kalman Filtering for Mobile Ad-Hoc Networks.

Time synchronization is an important issue in ad-hoc networks for reliable information exchange. The algorithms for time synchronization in ad-hoc networks are largely categorized into two types. One is based on a selection of a reference node, and the other is based on a consensus among neighbor nodes. These two types of methods are targeting static environments. However, synchronization errors among nodes increase sharply when nodes move or when incorrect synchronization information is exchanged due to the failure of some nodes. In this paper, we propose a synchronization technique for mobile ad-hoc networks, which considers both the mobility of nodes and the abnormal behaviors of malicious or failed nodes. Specifically, synchronization information extracted from a median of the time information of the neighbor nodes is quickly disseminated. This information effectively excludes the outliers, which adversely affect the synchronization of the networks. In addition, Kalman filtering is applied to reduce the synchronization error occurring in the transmission and reception of time information. The simulation results confirm that the proposed scheme has a fast synchronization convergence speed and low synchronization error compared to conventional algorithms.

Industrial Wireless Sensor Networks: Protocols and Applications.

Wireless sensor networks are penetrating our daily lives, and they are starting to be deployed even in an industrial environment. The research on such industrial wireless sensor networks (IWSNs) considers more stringent requirements of robustness, reliability, and timeliness in each network layer. This Special Issue presents the recent research result on industrial wireless sensor networks. Each paper in the special issue has unique contributions in the advancements of industrial wireless sensor network research and we expect each paper to promote the relevant research and the deployment of IWSNs.