Deep Learning Approach to Detect the Covid-19 Infection Using Chest X-ray Image: A Review

ABSTRACT

The COVID 2019 outbreak has been designated by WHO as a pandemic since 2020. Various methods of diagnosis of COVID 19 have been developed by several researchers to cope with COVID 19. A proper and accurate diagnosis is crucial for the next treatment step. Deep learning has been widely applied in the image classification process with high accuracy. However, the selection of the right deep learning model for the detection of lung disorders caused by COVID-19 based on x-ray images of the chest has not been widely reviewed by several reference sources. Therefore, the purpose of this study is to do a paper review that reviews a deep learning approach to detect COVID 19 through chest X-ray images. The reference sources used in the preparation of this review paper are from various databases such as PubMed, IEEE-explore, and ScienceDirect in the period of 2020–2021. The results of the review and discussion show that deep learning with the convolution neural network (CNN) algorithm is more widely applied in the process of recognizing patterns of lung abnormalities caused by COVID 19. However, deep learning with transfer learning has the potential for better accuracy because it applies the architecture that has been used to solve the same previous problem. The conclusion that can be drawn from this study is that CNN is still the right method for diagnosing lung disorders caused by COVID 10 compared to conventional machine learning. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.