Title: Data augmentation and denoising of computed tomography scan images in training deep learning models for rapid COVID-19 detection

Authors: Auwalu Saleh Mubarak; Sertan Serte; Fadi Al-Turjman; Zubaida Sa'id Ameen

Addresses: Artificial Intelligence Engineering Department, AI and Robotics Institute, Near East University, Mersin 10, Turkey; Research Center for AI and IoT, Faculty of Engineering, University of Kyrenia, Mersin 10, Turkey ' Department of Electrical and Electronics Engineering, Near East University, Mersin 10, Turkey ' Artificial Intelligence Engineering Department, AI and Robotics Institute, Near East University, Mersin 10, Turkey; Research Center for AI and IoT, Faculty of Engineering, University of Kyrenia, Mersin 10, Turkey ' Artificial Intelligence Engineering Department, AI and Robotics Institute, Near East University, Mersin 10, Turkey; Research Center for AI and IoT, Faculty of Engineering, University of Kyrenia, Mersin 10, Turkey

Abstract: The deadly respiratory disease corona virus-2 (COVID-19) which was declared a pandemic by the World Health Organization (WHO) has resulted in over a million deaths around the world within less than a year. With the rapid spread of the virus, the currently adopted COVID-19 test by the WHO is the reverse transcription polymerase chain reaction (RT-PCR) test, which is expensive, time-consuming and not accessed by underdeveloped countries. Computed tomography (CT) scan images that were used in profiling suspected COVID-19 patients can serve as an alternative to the RT PCR test method. In this study, two different pre-trained deep learning models ResNet-50 and ResNet-101 were trained to classify positive COVID-19 scan images. The best model which was trained on the augmented CT scan images achieved an accuracy of 98.3%, a sensitivity of 0.984, specificity of 0.983.

Keywords: artificial intelligence; deep learning; CT scan images; medical imagine; transfer learning; data augmentation; denoising.

DOI: 10.1504/IJBIDM.2024.136438

International Journal of Business Intelligence and Data Mining, 2024 Vol.24 No.2, pp.203 - 216

Accepted: 23 Feb 2023
Published online: 01 Feb 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article