Detection of Covid-19 using Mask R-CNN

Deep learning has been widely used to analyze radiographic pictures such as chest scans. These radiographic pictures include a wealth of information, including patterns and cluster-like formations, which aid in the discovery and conformance of COVID-19-like pandemics. The COVID-19 pandemic is wreaking havoc on global well-being and public health. Until present, more than 27 million confirmed cases have been recorded globally. Due to the increasing number of confirmed cases and issues with COVID-19 variants, fast and accurate categorization of healthy and infected individuals is critical for COVID-19 management and treatment. In medical image analysis and classification, artificial intelligence (AI) approaches in general, and region-based convolutional neural networks (CNNs) in particular, have yielded promising results. In this study, a deep Mask R-CNN architecture based on chest image classification is suggested for the diagnosis of COVID-19. An effective and reliable Mask R-CNN classification was difficult due to a lack of sufficient size and high-quality chest image datasets. These complications are addressed with Mask Region-based convolutional neural networks (R-CNNs) as a framework for detecting COVID-19 patients from chest pictures using an open-source dataset. First, the model was evaluated using 100 photos from the original processed dataset, and it was found to be accurate. The model was then validated against an independent dataset of COVID-19 X-ray pictures. The suggested model outperformed all other models in general and specifically when tested using an independent testing set. © 2023 IEEE.

COVID-19 Cases Prediction Using Different LSTM Models and Comparison of Effectiveness of Different Models

Large infectivity and transmissibility of COVID-19 caused severe damage to the economy, education and health of many countries. Due to the increasing number of COVID-19 cases in the world, some predictive methods are therefore needed to forecast the number of cases of COVID-19 in the future. Long short-term memory (LSTM) predicts the correlation between confirmed cases and predicts COVID-19 spread over time. The system shall be trained using training data containing confirmed cases. Various parameters considered are the no of positive cases, the number of recovered cases and the no of deaths every day. LSTM models in different types are evaluated for the time series forecasting confirmed cases, deaths and recovery and the accuracy of the prediction is compared. Different LSTM models like bidirectional LSTM, Gated Recurrent unit, W-LSTM and simple LSTM are helps to predict the no of cases in each country. Model performance is measured using the root mean square error, mean absolute percentage error and r2-score indices. Proposed method can be used to predict other types of pandemics for improved planning. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Anti-Obesity Siddha Medicinal Plants-A Preclinical Review

Obesity is a complex multi factorial preventable disease affecting all age groups of both the sexes. Now one third of world’s population is overweight or obese. From 1980 the world-wide prevalence of obesity has become doubled. Overweight and obesity were the 5th foremost causes of death globally. Obesity is associated with many co morbid diseases. Prevalence of obesity with co morbidities is on big alarm throughout the world. Recently in COVID-19 pandemic most of the obese people get affected due to the co morbidities and reduced immunity. The anti-obesity properties of medicinal plants were known from ancient times in traditional Siddha medicine some thousand years ago. Many Siddha medicinal plants showed anti-obesity activities that can be utilized in the management of obesity, through which the complications of obesity can be prevented. Most researches explored the anti-obesity potentials of medicinal plants. Terminalia chebula, Phyllanthus niruri, zingiber officinale, Piper longum, Curcuma longa, Elettaria cardamomum, Cuminum cyminum, Picrorhiza kurroa, Ipomea turpethum, Tinospora cordifolia, Michelia champaka are some medicinal plants possess anti-obesity properties that had been indicated in Siddha classical text. The objective of this review is to validate the anti-obesity potentials of Siddha medicinal plants scientifically through various research reports. Due to the presence of Phyto compounds like phenols, flavonoids, terpenoids, alkaloids, anti-oxidants these medicinal plants revealed anti-obesity activities and its anti-obesity mechanism had been proven scientifically through various animal experimental studies collected from many research articles. Modern anti-obesity drugs produce numerous side effects. Regular consumption of Siddha anti-obesity medicinal plants, in the prescribed dose and duration, can induce gradual and sustainable weight loss effectively. Furthermore, in future, there is a need for the development of standardized, safe and effective anti-obesity drugs from medicinal plants and highly economical too. Hence eventually exploration of anti-obesity Siddha medicinal plants will lead to safe and effective treatment for obesity.

The Course of COVID-19 in a Patient with Aplastic Anemia and Paroxysmal Nocturnal Hemoglobinuria Clone: A Case Report and Literature Review

Introduction: Aplastic anemia (AA) and paroxysmal nocturnal hemoglobinuria (PNH) are bone marrow failure syndromes. A 20-40% of patients with AA have a PNH clone at diagnosis. To date, there are little data about the course of COVID-19 in patients with AA and PNH. Case Presentation: A 36-year-old gentleman, who was previously diagnosed as a case of AA with PNH clones off immune-suppressive therapy, presented with fever and cough and was diagnosed with mild pneumonia due to COVID-19 with positive nasopharyngeal swab polymerase chain reaction (PCR) for severe acute respiratory syndrome coronavirus 2. His clinical course was benign except transient thrombocytopenia. He was asymptomatic after day 4, and viral PCR was negative on day 21. Discussion: Though studies have shown that COVID-19 is associated with lymphopenia, our patient had a normal to high lymphocyte count. The neutrophil to lymphocyte ratio (NLR) was <1 during COVID-19, which correlates with the mild course of the disease. To know whether elevated lymphocyte count, low NLR, and benign course of COVID-19 is a standard feature for all patients with underlying AA, we need more case reports and series. The significance of this case report is that it describes the course of COVID-19 in a patient with AA and PNH clones and, up to our knowledge, is the first report showcasing the association between these rare combinations of diseases.

Prolonged viral shedding in six COVID-19 patients

COVID-19 has surfaced as a multi-organ disease predominantly affecting the respiratory system. Detection of the viral RNA through reverse transcriptase-PCR (RT-PCR) from a nasopharyngeal or throat sample is the preferred method of diagnosis. Recent evidence has suggested that COVID-19 patients can shed the SARS-CoV-2 for several weeks. Herein, we report six cases of COVID-19 who had persistently positive SARS-CoV-2 on repeat RT-PCR testing reaching up to 9 weeks. The spectrum of cases described ranges from asymptomatic infection to severe COVID-19 pneumonia. A full understanding of the virus's transmission dynamics needs further research. Prolonged viral shedding currently has unclear implications on the management and isolation decisions - the role of the cycle threshold (Ct) value in guiding therapeutic decisions is yet to be clarified. More data on the relationship between Ct values and viral cultivation are needed, especially in patients with prolonged viral shedding, to understand the virus's viability and infectivity.