ABSTRACT
New Coronavirus 2019 (COVID-19) is a virus that causes severe pneumonia and affects many organs of the body. This infection was initially discovered in one of the cities in the Republic of China, Wuhan, in December 2019 and since then has been spread throughout the globe as a global pandemic. To prevent the virus from spreading, positive cases must be identified early and infected persons must be treated as soon as possible. As new instances emerge regularly, many developing countries are experiencing COVID-19 testing kit scarcity because the demand for testing kits has soared. As an alternative, radiological imaging techniques such as X-ray images have been proven to help in COVID-19 diagnosis because images from X-ray provide valuable information about the COVID-19 virus disease. This paper presents a survey of Deep learning-based methods in identifying COVID-19 with X-ray input images, and classifies these images into several categories, namely: no findings, normal, COVID, and pneumonia. Several studies have been included with details about their datasets, methodologies, and findings. A total of thirteen popular datasets and fifteen articles are reviewed in this paper. Research challenges and recommendations for future research directions are also provided as an evaluation of previous research. Search for research articles in well-known digital libraries, namely Scopus, IEEE Xplore, Springer, and ScienceDirect, was carried out to obtain a list of studies relevant to the scope of research. Related articles that have a high impact are considered in the list of studies. Also, in selecting studies related to the research scope, we apply some inclusion and exclusion criteria. The list of studies used in subsequent research is imported to the library. Then, studies that did not match the criteria for inclusion were eliminated. The clinical application of artificial intelligence, i.e., DL in diagnosing COVID-19, is promising, and further research is needed. Convolutional Neural Network (CNN) approaches could be used in collaboration through X-ray pictures to identify diseases quickly and accurately, reducing the shortage of testing equipment and their restrictions. It is expected that this work can help researchers understand the general picture and existing research gaps to decide on the appropriate architecture and approach in developing deep learning-based covid identification research. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.