Significance of deep learning for Covid-19: state-of-the-art review
- 20 March 2021
- journal article
- review article
- Published by Springer Nature in Research on Biomedical Engineering
- Vol. 38 (1) , 243-266
Abstract
The appearance of the 2019 novel coronavirus (Covid-19), for which there is no treatment or a vaccine, formed a sense of necessity for new drug discovery advances. The pandemic of NCOV-19 (novel coronavirus-19) has been engaged as a public health disaster of overall distress by the World Health Organization. Different pandemic models for NCOV-19 are being exploited by researchers all over the world to acquire experienced assessments and impose major control measures. Among the standard techniques for NCOV-19 global outbreak prediction, epidemiological and simple statistical techniques have attained more concern by researchers. Insufficiency and deficiency of health tests for identifying a solution became a major difficulty in controlling the spread of NCOV-19. To solve this problem, deep learning has emerged as a novel solution over a dozen of machine learning techniques. Deep learning has attained advanced performance in medical applications. Deep learning has the capacity of recognizing patterns in large complex datasets. They are identified as an appropriate method for analyzing affected patients of NCOV-19. Conversely, these techniques for disease recognition focus entirely on enhancing the accurateness of forecasts or classifications without the ambiguity measure in a decision. Knowing how much assurance present in a computer-based health analysis is necessary for gaining clinicians’ expectations in the technology and progress treatment consequently. Today, NCOV-19 diseases are the main healthcare confront throughout the world. Detecting NCOV-19 in X-ray images is vital for diagnosis, treatment, and evaluation. Still, analytical ambiguity in a report is a difficult yet predictable task for radiologists.Keywords
This publication has 85 references indexed in Scilit:
- V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation2016
- Deep learningNature, 2015
- Brain Tumor Detection based on Machine Learning AlgorithmsInternational Journal of Computer Applications, 2014
- Machine learning models for the differential diagnosis of vascular parkinsonism and Parkinson’s disease using [123I]FP-CIT SPECTEuropean Journal of Nuclear Medicine and Molecular Imaging, 2014
- Individual Detection of Patients with Parkinson Disease using Support Vector Machine Analysis of Diffusion Tensor Imaging Data: Initial ResultsAmerican Journal of Neuroradiology, 2012
- Discrimination between parkinsonian syndrome and essential tremor using artificial neural network classification of quantified DaTSCAN dataNuclear Medicine Communications, 2006
- Long Short-Term MemoryNeural Computation, 1997
- Nonlinear principal component analysis using autoassociative neural networksAIChE Journal, 1991
- Learning representations by back-propagating errorsNature, 1986
- Coronaviruses, a New Group of Animal RNA Viruses1970