Page 20 - AIH-2-1

Artificial Intelligence in Health

ORIGINAL RESEARCH ARTICLE
Diagnosis of COVID-19 from computed

tomography slices using flower pollination
algorithm, k-nearest neighbor, and support

vector machine classifiers

1
Betshrine Rachel Jibinsingh 1 , Khanna Nehemiah Harichandran * ,
Kabilasri Jayakannan 2 , Rebecca Mercy Victoria Manoharan 3 , and
Anisha Isaac 1
1 Ramanujan Computing Centre, College of Engineering Guindy, Anna University, Chennai,
Tamil Nadu, India
2 Department of Information Science and Technology, College of Engineering Guindy, Anna
University, Chennai, Tamil Nadu, India
3 Department of Computer Science and Engineering, College of Engineering Guindy, Anna University,
Chennai, Tamil Nadu, India

*Corresponding author:
Khanna Nehemiah Harichandran Abstract
(nehemiah@annauniv.edu)
Coronavirus disease 19 (COVID-19), caused by the severe acute respiratory syndrome-
Citation: Jibinsingh BR,
Harichandran KN, Jayakannan K, coronavirus-2 virus, is commonly diagnosed through imaging techniques such as
Manoharan RMV, Isaac A. computed tomography (CT) scans, which reveal characteristic lung lesions. In this
Diagnosis of COVID-19 from study, we propose a computer-aided diagnosis (CAD) system to assist in the early
computed tomography slices
using flower pollination algorithm, detection of COVID-19 from CT lung slices, leveraging advanced machine-learning
k-nearest neighbor, and support algorithms for precise and efficient analysis. To achieve this, we developed a CAD
vector machine classifiers. Artif system that diagnoses COVID-19 from CT lung slices. An adaptive Wiener filter was
Intell Health. 2025;2(1):14-28.
doi: 10.36922/aih.3349 applied to remove noise from the CT images. The chest tissues were then segmented
using an optimal thresholding method to extract regions of interest, which represent
Received: April 3, 2024
the COVID-19 lesions under investigation. The feature vectors were divided into
1st revised: May 22, 2024 training and testing with an 80/20 ratio. A wrapper-based flower pollination
2nd revised: June 17, 2024 algorithm was employed alongside the k-nearest neighbor classifier to select the
optimal feature set. These selected features were subsequently used to train a
Accepted: June 24, 2024
support vector machine (SVM) classifier. With feature selection, the SVM achieved
Published Online: October 23, an accuracy of 91.30% on a real-time dataset, outperforming seven other machine
2024
learning classifiers (radial basis function-SVM, k nearest neighbor, linear discriminant
Copyright: © 2024 Author(s). analysis, random forest, naïve Bayes, AdaBoost, extreme gradient boosting) and four
This is an Open-Access article deep learning classifiers (convolutional neural network, recurrent neural network,
distributed under the terms of the
Creative Commons Attribution long short term memory, Bidirectional long short term memory). For the publicly
License, permitting distribution, available COVID-19 CT dataset, an accuracy of 88.18% was achieved. In conclusion,
and reproduction in any medium, our COVID-19 CAD system improves diagnostic accuracy, with future work aimed at
provided the original work is
properly cited. enhancing efficiency and expanding to covariant detection and severity assessment.
Publisher’s Note: AccScience
Publishing remains neutral with Keywords: Support vector machine; Flower pollination algorithm; k-nearest neighbor;
regard to jurisdictional claims in
published maps and institutional Coronavirus disease 19; Coronavirus disease 19 computed tomography dataset
affiliations.

Volume 2 Issue 1 (2025) 14 doi: 10.36922/aih.3349