A radiomics-based model for the outcome prediction in COVID-19 positive patients through deep learning with both longitudinal chest x-ray and chest computed tomography images

The coronavirus disease 2019 (COVID-19) pandemic had a major impact on global health and was associated with millions of deaths worldwide. During the pandemic, imaging characteristics of chest X-ray (CXR) and chest computed tomography (CT) played an important role in the screening, diagnosis and monitoring the disease progression. Various studies suggested that quantitative image analysis methods including artificial intelligence and radiomics can greatly boost the value of imaging in the management of COVID-19. However, few studies have explored the use of longitudinal multi-modal medical images with varying visit intervals for outcome prediction in COVID-19 patients. This study aims to explore the potential of longitudinal multimodal radiomics in predicting the outcome of COVID-19 patients by integrating both CXR and CT images with variable visit intervals through deep learning. 2274 patients who underwent CXR and/or CT scans during disease progression were selected for this study. Of these, 946 patients were treated at the University of Pennsylvania Health System (UPHS) and the remaining 1328 patients were acquired at Stony Brook University (SBU) and curated by the Medical Imaging and Data Resource Center (MIDRC). 532 radiomic features were extracted with the Cancer Imaging Phenomics Toolkit (CaPTk) from the lung regions in CXR and CT images at all visits. We employed two commonly used deep learning algorithms to analyze the longitudinal multimodal features, and evaluated the prediction results based on the area under the receiver operating characteristic curve (AUC). Our models achieved testing AUC scores of 0.816 and 0.836, respectively, for the prediction of mortality. © 2023 SPIE.

COVID-19 and Pneumonia classification Using Ensembling with Transfer Learning

The world has been rapidly devastated by the Covid-19 virus, which first appeared in the Republic of China. For medical imaging, deep learning-based algorithms show promising results for quick and accurate diagnosis. Various research has been done for the earlier diagnosis of the disease using various deep learning models. Researchers use different medical imaging for the classification of COVID-19. This study explores COVID-19 diagnosis using a chest X-Ray. The Chest X-Ray images were classified with the help of transfer learning using VGG16, DenseNet, and MobileNet. To ensure better results Ensemble Learning is incorporated to provide a strong learner by using the aggregation of weak learners. These models are trained on three different classes of patients: COVID-19, Pneumonia, and Normal. The final testing results using ensembling aggregation show an overall accuracy of 95.2%, which is significantly higher than the model performances individually. The result obtained through the proposed model can be used in conjunction with the X-Ray images to classify COVID-19, thus the process can be implemented as an alternative to RT-PCR. © 2022 IEEE.

Impact and challenges for the indian education system due to the COVID-19 pandemic

Coronavirus has upset the world in the years 2019-20. Every business and sector got affected due to the circumstances created by this epidemic. We should know the virology, epidemiology, and safeguards needed to take in this pandemic to understand its impact. Due to its highly contiguous nature, it is essential to save the next generation from its impact as much as possible. The education sector is one of the sectors, which have a huge number of youngsters evolved. Governments around the world have closed their educational institutes physically to stop its spread in public. But, this has raised the issue of hampering continuous education. Our article discussed the impacts, policies, capabilities, and responses taken by the Indian education sector during this pandemic lockdown. Also, we have examined the role of Information and Communications Technology (ICT) Tools and the Indian Government, which have enabled the students of Indian educational institutes to learn and continue their knowledge acquiring process. © 2021 Nova Science Publishers, Inc.

A Review on COVID-19 Diagnosis Using Imaging and Artificial Intelligence

The coronavirus epidemic is still on a surge and has harsh impacts on various factors across the globe including the economy and health. Though the recovery rate is also increasing, daily reporting cases are also increasing substantially. The best way till now is to take precautions and following the government guidelines. Till today, many different countries are line up to produce effective vaccination, but still, no such vaccine has completed its trial, and further, it will take a long time for the production and distribution among common citizens. We currently have a test process known as reverse transcription-polymerase chain reaction (RT-PCR) that is not reliable during the early stage of the disease. Also, a fast diagnosis is required as RT-PCR is time taking operation. Hence, imaging can be useful for the diagnosis as it can be quick and more reliable even in the early stage of the COVID-19 disease. Artificial techniques can be applied to radiological images such as CT scans and X-rays. In this article, we review the various research and responses in diagnosing the said disease using AI techniques on radiological images. Our findings suggest that using AI techniques like Convolution Neural Networks plays an important role in the diagnosing the COVID-19 by providing quick results and accuracy. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.