COVID-19 Diagnosis-Based Deep Learning Approaches for COVIDx Dataset: A Preliminary Survey
Esraa Hassan, Mahmoud Y. Shams, Noha A. Hikal, Samir Elmougy
Abstract
This chapter presents a comprehensive review of the utilization of deep learning (DL) approaches to COVID-19 identification and lung segmentation. It also presents a review of articles using DL approaches to classify the enrolled images using COVIDX dataset. This dataset is commonly used recently to classify infected or normal patients. In supervised learning, convolutional neural networks and recurrent neural networks are preferred to achieve precise diagnosis and classification in real time for medical images. Abbasi et al. [29] proposed an independent COVID-19 diagnosis and severity prediction method, which uses deep feature maps from chest X-ray (CXR) imaging to diagnose COVID-19 and predict its severity. The results of COVID-19 image retrieval and diagnosis tasks show that the proposed model can serve as a robust solution for CXR analysis. The availability of a large public database is one of the problems in developing a reliable and accurate COVID-19 diagnosis system.