Predicting the Severity of COVID-19 from Lung CT Images Using Novel Deep Learning

Ahmad Imwafak Alaiad; Esraa Ahmad Mugdadi; Ismail Ibrahim Hmeidi; Naser Obeidat; Laith Abualigah

doi:10.1007/s40846-023-00783-2

Predicting the Severity of COVID-19 from Lung CT Images Using Novel Deep Learning

J Med Biol Eng. 2023;43(2):135-146. doi: 10.1007/s40846-023-00783-2. Epub 2023 Mar 13.

Authors

Ahmad Imwafak Alaiad¹, Esraa Ahmad Mugdadi¹, Ismail Ibrahim Hmeidi¹, Naser Obeidat², Laith Abualigah^{3

4

5

6

7

8}

Affiliations

¹ Computer Information System, Jordan University of Science and Technology, Irbid, Jordan.
² Department of Diagnostic Radiology and Nuclear Medicine, Faculty of Medicine, Jordan University of Science and Technology, Irbid, Jordan.
³ Computer Science Department, Prince Hussein Bin Abdullah Faculty for Information Technology, Al al-Bayt University, Mafraq, 25113 Jordan.
⁴ College of Engineering, Yuan Ze University, Taoyuan, Taiwan.
⁵ Hourani Center for Applied Scientific Research, Al-Ahliyya Amman University, Amman, 19328 Jordan.
⁶ Faculty of Information Technology, Middle East University, Amman, 11831 Jordan.
⁷ Applied Science Research Center, Applied Science Private University, Amman, 11931 Jordan.
⁸ School of Computer Sciences, Universiti Sains Malaysia, 11800 Pulau Pinang, Malaysia.

Abstract

Purpose: Coronavirus 2019 (COVID-19) had major social, medical, and economic impacts globally. The study aims to develop a deep-learning model that can predict the severity of COVID-19 in patients based on CT images of their lungs.

Methods: COVID-19 causes lung infections, and qRT-PCR is an essential tool used to detect virus infection. However, qRT-PCR is inadequate for detecting the severity of the disease and the extent to which it affects the lung. In this paper, we aim to determine the severity level of COVID-19 by studying lung CT scans of people diagnosed with the virus.

Results: We used images from King Abdullah University Hospital in Jordan; we collected our dataset from 875 cases with 2205 CT images. A radiologist classified the images into four levels of severity: normal, mild, moderate, and severe. We used various deep-learning algorithms to predict the severity of lung diseases. The results show that the best deep-learning algorithm used is Resnet101, with an accuracy score of 99.5% and a data loss rate of 0.03%.

Conclusion: The proposed model assisted in diagnosing and treating COVID-19 patients and helped improve patient outcomes.

Keywords: COVID-19; Deep learning; Lungs ct; Mild; Moderate; Normal; Severe; Severity.

© Taiwanese Society of Biomedical Engineering 2023, Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.