Optimal feature selection for COVID-19 detection with CT images enabled by metaheuristic optimization and artificial intelligence.
Multimed Tools Appl
; : 1-31, 2023 Mar 20.
Article
in English
| MEDLINE | ID: covidwho-2284373
ABSTRACT
There is a broad range of novel Coronaviruses (CoV) such as the common cold, cough, and severe lung infections. The mutation of this virus, which originally started as COVID-19 in Wuhan, China, has continued the rapid spread globally. As the mutated form of this virus spreads across the world, testing and screening procedures of patients have become tedious for healthcare departments in largely populated countries such as India. To diagnose COVID-19 pneumonia by radiological methods, high-resolution computed tomography (CT) of the chest has been considered the most precise method of examination. The use of modern artificial intelligence (AI) techniques on chest high-resolution computed tomography (HRCT) images can help to detect the disease, especially in remote areas with a lack of specialized physicians. This article presents a novel metaheuristic algorithm for automatic COVID-19 detection using a least square support vector machine (LSSVM) classifier for three classes namely normal, COVID, and pneumonia. The proposed model results in a classification accuracy of 87.2% and an F1-score of 86.3% for multiclass classifications from simulations. The analysis of information transfer rate (ITR) revealed that the modified quantum-based marine predators algorithm (Mq-MPA) feature selection algorithm reduces the classification time of LSSVM by 23% when compared to the deep learning models.
Full text:
Available
Collection:
International databases
Database:
MEDLINE
Type of study:
Diagnostic study
/
Prognostic study
Language:
English
Journal:
Multimed Tools Appl
Year:
2023
Document Type:
Article
Similar
MEDLINE
...
LILACS
LIS