Role of deep learning strategies in detecting COVID-19 pneumonia

The COVID-19 outbreak caused by SARS-Cov-2, has affected several million people across the world. Artificial intelligence (AI) techniques have aided in the management of the COVID-19 epidemic in a variety of ways. These include diagnosis, estimation of epidemic trends, prognosis, and exploration of effective and safe drugs and vaccines. The primary goal of this chapter is to provide insights on the most recent research on deep learning (DL) applications used for COVID-19 pneumonia detection. Recent studies show the potential of AI as a screening tool to detect COVID-19 pneumonia based on chest x-ray (CXR) and CT images. However, issues on the datasets and study designs from medical and technical perspectives, as well as questions on the vulnerability and robustness of AI algorithms have emerged. The researchers have included the latest frameworks such as Inception V3, Inception ResNet V2 and DenseNet 201 for processing of imaging datasets. Despite the challenges such as limited availability of data, and technical issues, the hybrid algorithms have successfully predicted results with higher accuracy. An elaborate discussion of such algorithms, techniques and also their performance has been reported in this chapter. We have also compared various systems, datasets and their implementations. The chapter concludes with discussions on limitations and future directions.