Artificial Intelligence in Medical Virology by Unknown

Author:Unknown
Language: eng
Format: epub
ISBN: 9789819903696
Publisher: Springer Nature Singapore

6.2 Related Works

In 2020, Shi et al. (2020) published a paper discussing the use of artificial intelligence (AI) in the context of COVID-19. The authors highlighted the potential of AI to provide safe, accurate, and efficient imaging methods for COVID-19 diagnosis and treatment. The intelligent imaging methods, clinical analysis, and spearheading research are evaluated in detail, covering the whole pipeline of AI-engaged imaging applications in COVID-19. Two imaging techniques, i.e., X-ray and CT, are utilized to exhibit the effectiveness of AI-enabled clinical imaging for COVID-19. Here in Farooq and Hafeez (2020), the Bayesian DL classifier has been prepared using the move learning procedure on Coronavirus CXR pictures to assess model weakness. Their investigation has demonstrated a solid connection between model vulnerability and precision of expectation. The target (Ghoshal and Tucker 2020) is to build open source and open access datasets and present a solid CNN framework for isolating Coronavirus cases from other pneumonia cases. This work involves top-tier getting-ready techniques, including dynamic resizing, designed learning rate finding, and discriminative learning rates to plan fast and precise excess NNs. Zhang et al. (2020) aimed to develop a new deep anomaly detection model for rapid and reliable screening of COVID-19. The use of deep learning models for anomaly detection has gained popularity in recent years, as they are capable of detecting patterns and deviations in large amounts of data, making them well suited for medical imaging analysis. We have gathered 100 CXR pictures of 70 patients affirmed with COVID-19 from the GitHub archive to assess the model execution. Nguyen (n.d.) conducted a review of the various AI techniques being used in different applications in the fight against the COVID-19 pandemic and highlighted the key roles of AI research currently. Gozes et al. (2020) created AI-based mechanized CT picture examination means for detection, measurement and following of COVID and show that they can separate coronavirus patients from the individuals who do not have the malady (Zhu et al. 2020). VHP (Virus-Host Prediction) was introduced to predict prospective virus hosts using DL computing. According to their findings, 2019-nCoV shares close infectivity with other human coronaviruses, namely the severe acute respiratory syndrome coronavirus (SARS-CoV), Bat SARS-like Coronaviruses, and the Middle East respiration syndrome coronavirus (MERS-CoV). Considering COVID-19 radiographical changes in CT pictures, authors planned to develop a DL procedure that could eliminate COVID-19’s graphical features to give a clinical end before the pathogenic test, this way saving significant time for disease control (Wang et al. 2020). Sujath et al. (2020) performed logistic regression (LR), Multi-layer Perceptron (MLP), and Vector Autoregression (VAR) models to make predictions on the Coronavirus Kaggle data to estimate the epidemiological pattern and rate of Coronavirus 2019 cases in India. The authors aimed to use machine learning techniques to better understand the spread and evolution of the COVID-19 pandemic in India and to provide insights into the future evolution of the disease. To detect COVID-19 from 3D CT images, a pitifully regulated DL-based programming method was created (Zheng et al. 2020). The

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.