Detection of COVID-19 Infection Using Convolutional Neural Network

Coronavirus disease (COVID-19) is a newly discovered viral sickness that can be fatal. The majority of patients will experience mild to severe respiratory problems and will improve without need for special treatment. Persons over 65, and for those who are underlying medical disorders such cardiovascular disease, asthma, respiratory illness, and cancer, are more prone for developing severe symptoms. In these conditions, 3D volumetric imaging has proven to be a useful technique for COVID-19 patient diagnosis and prognosis. We present a new approach for detecting and classifying COVID-19 infection using 3D volumetric lung imaging in this work. For the detection and classification process, we have used 3D volumetric image processing and deep learning techniques, respectively. Early recognition and finding are basic elements to stop COVID-19 spreading. Various profound learning-based approaches had been proposed for COVID-19 separating CT examines as an instrument to computerize and assist with finding. These methods suffer with at least one of the faults listed below: (i) They treat each CT scan individually (ii) These methods are trained and tested on the same dataset. To address these two challenges, we present an accurate deep learning technique for COVID-19 screening using a democratic framework in this paper. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-COV-2) Vertical Transmission Covid-Positive Mothers in Neonates

An outbreak of Covid-19 occurred in Wuhan, China initially in December 2019. Over the next few months, the wide spread of SARS-CoV-2 had been reported in all continents and the transmission in utero from an infected mother to fetus debating yet was observed.1,9Objectives: To determine risk of vertical transmission of corona virus in neonates of SARS COVID-2 positive mothers. Study Design: A Cross-Sectional study. Place and Duration of Study: Pediatric department of Pakistan Air Force (PAF) Hospital, Islamabad, Pakistan. The study conducted during 01-03-2020 to 31-08-2020. Methodology: After taking informed consent, Nasopharyngeal swab for PCR for SARS-CoV-2 was taken one week before delivery. Confirmed COVID positive pregnant ladies were included irrespective of symptoms of COVID-19 infection and any other medical illness. Neonates born to COVID-19 positive mothers were admitted in NICU, and Performa was filled for neonates after PCR done 24 and 48 hours respectively. Result(s): Total 14(87.5%) out of 16 COVID positive mothers were asymptomatic. 16(100%) neonates were negative for Sars- COV-2 at 24 hours and 48 hours. Conclusion(s): This study concluded with no evidence of transmission of COVID-19 from infected mothers. Copyright © 2022 Lahore Medical And Dental College. All rights reserved.

Investigating levels of inflammatory biomarkers between SARS-CoV- 2 vaccinated and unvaccinated subjects

Background: To curb the threat of COVID-19, vaccines of different forms and shape have been developed and assessed for their efficacy in the last one and a half year. Amongst those Inactivated viral vaccines developed in China, Sinopharm and Sinovac are the most frequently employed vaccines in Pakistan. It has been established that natural infection and certain forms of SARS-CoV- 2 vaccine alters the clinical picture of blood. Aim(s): In this study we have compared the levels of three inflammatory biomarkers namely PAI-1, D-Dimer and HAI-IgG in the sera collected from SARS-CoV- 2 Vaccinated and unvaccinated Subjects. Method(s): Briefly, 80 individuals, each as a cohort of SARS-CoV- 2 vaccinated and unvaccinated were recruited with written consent after ethical approval for the study. From each subject 2 ml blood was drawn and plasma was separated to assess inflammatory biomarkers like PAI-1, D-Dimer and HIA IgG by ELISA. Additionally, platelets count were also monitored using automated counter. Result(s): Our data show difference in the level of PAI-1, D-Dimer and HIA-IgG between SARS-CoV- 2 Vaccinated and unvaccinated subjects. However, the difference was found statistically in significant. Nevertheless, segregating the data based on the nature of vaccination, age and gender of the subjects shows interesting pattern that could be insightful in relation to the clinical outcome of the vaccine efficacy. Conclusion(s): The findings in this regard could well be of clinical value, especially when the data is stratified with reference to different variables. Therefore, large scale studies are warranted with same, and few additional biomarkers would be of more resolving in relation to the host response against SARS-CoV- 2 vaccination.

Abridging molecular system network of COVID-19 and thrombosis

Background: The advance pathology of SARS-CoV- 2 infection entails engagement of blood related ailment including thrombosis as secondary clinical manifestation. SARS-CoV- 2- Human protein-protein interactome has been explored. Dysregulation of the several proteins and mutations in the genes have been linked with the incidence and progression of thrombosis. Aim(s): Aim of the investigation is to develop and functionally analyze a combine molecular network of SARS-CoV- 2- Human and Thrombosis to delineate candidate molecule that could later be used for the prognosis and therapeutic intervention. Method(s): Briefly, two separate system networks were developed, one for over 500 humans protein that have shown to interact with the viral genome and 26 different proteins encoded by SARS-CoV- 2 genome. The second network is based on the genes tagged for being aberrated genetically and/or in terms of expression in thrombosis. Both networks were combined as a singular entity after removing the redundant repetition and orphans' nodes and edges by selective enrichment. The network then be dissected in different modules primarily based on the promiscuity of the nodes. Complete network and each module were assessed for in betweenness and shortest path length of edges. Result(s): The data shown over 700 genes could be coalesced as a single network providing a molecular interplay that may underpin SARS-CoV- 2 associated thrombosis. Over 16 modules were observed in the network with important candidate genes of thrombosis have been identified as hub due to the inter modular abridging potential. Identification of hub genes was further substantiated with the pathlength distance, lack of orphan edges and partner protein promiscuity. Biological functions and KEGG analysis of the holistic network and modular compartment further strengthen the predicted candidate gene status as central to the disease biology. Conclusion(s): Candidate genes identified in the study could later be used as markers for prognosis of the pathology of COVID-19 for thrombosis and/or developing therapeutic intervention.

Detection of COVID-19 Infection Using Convolutional Neural Network

Coronavirus disease (COVID-19) is a newly discovered viral sickness that can be fatal. The majority of patients will experience mild to severe respiratory problems and will improve without need for special treatment. Persons over 65, and for those who are underlying medical disorders such cardiovascular disease, asthma, respiratory illness, and cancer, are more prone for developing severe symptoms. In these conditions, 3D volumetric imaging has proven to be a useful technique for COVID-19 patient diagnosis and prognosis. We present a new approach for detecting and classifying COVID-19 infection using 3D volumetric lung imaging in this work. For the detection and classification process, we have used 3D volumetric image processing and deep learning techniques, respectively. Early recognition and finding are basic elements to stop COVID-19 spreading. Various profound learning-based approaches had been proposed for COVID-19 separating CT examines as an instrument to computerize and assist with finding. These methods suffer with at least one of the faults listed below: (i) They treat each CT scan individually (ii) These methods are trained and tested on the same dataset. To address these two challenges, we present an accurate deep learning technique for COVID-19 screening using a democratic framework in this paper. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Detection of Pathological Artifacts Caused by COVID-19 Using U-Net

SARS-COV-2 disease also known as (COVID-19) is a newly discovered viral disease that can be fatal. The majority of patients will experience mild to severe respiratory problems and will improve without need for special treatment. Deep learning (DL) has proven beneficial in medical imaging, and several research have begun to study Deep Learning based solutions for the aided detection of lung disorders in the aftermath of the recent COVID19 epidemic. While previous research has focused on Chest Tomography scans, this study investigates the use of DL approaches to analyse lung ultrasound data. We provide a new completely annotated dataset of LUS pictures gathered from multiple Italian hospitals, with labels reflecting the severity of illness at the frame and pixel levels. In the proposed system, a deep network named Convolutional Neural Networks (CNN) based transfer learning (Mobile-Net) is used, developed from Spatial Transformer Networks (STN) that which predicts the disease from the given image. Once after the disease prediction, we will use UNet for the segmentation of the predicted disease part from the given image. © 2022 IEEE.