Title: Novel approaches for classification COVID-19 and pneumonia disease from CT scans using radiomics features

Authors: Linda Ait Mohammed; Fatiha Alim-Ferhat; Mohammed Abdelaziz

Addresses: Division Architecture et Système Multimédia, Centre de Développement des Technologies Avancées, Cité, 20 Août 1956, Baba Hassen, 16081, Algeria ' Division Architecture et Système Multimédia, Centre de Développement des Technologies Avancées, Cité, 20 Août 1956, Baba Hassen, 16081, Algeria ' Division Architecture et Système Multimédia, Centre de Développement des Technologies Avancées, Cité, 20 Août 1956, Baba Hassen, 16081, Algeria

Abstract: COVID-19 is a highly infectious and fatal pneumonia-like disease. Despite the time-consuming nature of RT-PCR (reverse transcription-polymerase chain reaction), it remains a proven testing method for detecting coronavirus infection. Therefore, COVID-19 screening can be adopted using X-ray and computed tomography (CT) images of an individual's lungs to assist the traditional RT-PCR method in making an accurate clinical diagnosis. This imaging-based diagnosis will facilitate the detection of coronavirus infection and provide insight into the status of the disease, its form, and its degree of risk to the patient's life. CT scanning has become the benchmark test for COVID-19 and other pneumonia diseases. It allows visualisation and precise localisation of lesions in the lungs and branches. This study aims to classify COVID-19 among other types of pneumonia using a new preprocessing method, a set of parameters relevant to matching the random forest model, and a hybrid segmentation method based on level set and morphological tools. With an accuracy of 98.30%, an AUC of 0.98 for classification, and a dice score of 76% for segmentation, this method yielded promising results comparable to those found in the literature and allowed automatic and accurate deferral between COVID-19 and other pneumonia infections.

Keywords: CT scans; radiomics features; pneumonia; COVID-19; random forest.

DOI: 10.1504/IJBET.2024.136921

International Journal of Biomedical Engineering and Technology, 2024 Vol.44 No.2, pp.191 - 204

Received: 22 Sep 2022
Accepted: 19 Apr 2023
Published online: 29 Feb 2024 *

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