Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Jun 12;15(12):1500.
doi: 10.3390/diagnostics15121500.

Nature-Inspired Multi-Level Thresholding Integrated with CNN for Accurate COVID-19 and Lung Disease Classification in Chest X-Ray Images

Wafa Gtifa  1 , Ayoub Mhaouch  2 , Nasser Alsharif  3 , Turke Althobaiti  4 , Anis Sakly  1
Affiliations

Nature-Inspired Multi-Level Thresholding Integrated with CNN for Accurate COVID-19 and Lung Disease Classification in Chest X-Ray Images

Wafa Gtifa et al. Diagnostics (Basel). .

Abstract

Background/Objectives: Accurate classification of COVID-19 from chest X-rays is critical but remains limited by overlapping features with other lung diseases and the suboptimal performance of current methods. This study addresses the diagnostic gap by introducing a novel hybrid framework for precise segmentation and classification of lung conditions. Methods: The approach combines multi-level thresholding with the advanced metaheuristic optimization algorithms animal migration optimization (AMO), electromagnetism-like optimization (EMO), and the harmony search algorithm (HSA) to enhance image segmentation. A convolutional neural network (CNN) is then employed to classify segmented images into COVID-19, viral pneumonia, or normal categories. Results: The proposed method achieved high diagnostic performance, with 99% accuracy, 99% sensitivity, and 99.5% specificity, confirming its robustness and effectiveness in clinical image classification tasks. Conclusions: This study offers a novel and technically integrated solution for the automated diagnosis of COVID-19 and related lung conditions. The method's high accuracy and computational efficiency demonstrate its potential for real-world deployment in medical diagnostics.

Keywords: COVID-19 diagnosis; animal migration optimization; chest X-ray classification; convolutional neural network; electromagnetism-like optimization; harmony search algorithm; multi-level thresholding.

PubMed Disclaimer

Conflict of interest statement

All the authors declare that they have no competing interests.

Figures

Figure 1
Figure 1
Schematic overview of the proposed system.
Figure 2
Figure 2
An individual’s local neighborhood scheme in the AMO algorithm.
Figure 3
Figure 3
AMO algorithm.
Figure 4
Figure 4
CNN model architecture for lung X-ray image classification.
Figure 5
Figure 5
Visual comparison of COVID-19 lung X-ray segmentation results: ground truth vs. AMO, EMO, and HSA algorithms.
Figure 6
Figure 6
Comparative performance of AMO, EMO, and HSA for COVID-19 lung datasets based on the DSC (a) and Jaccard index (b).
Figure 7
Figure 7
Loss and accuracy curves for training and validation of the CNN model.
Figure 8
Figure 8
Confusion matrix for the CNN model classification of COVID-19, viral pneumonia, and normal lung X-ray images.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. World Health Organization . Global COVID-19 Situation Report—January 2024. WHO; Geneva, Switzerland: 2024. (WHO Technical Report Series).
    1. Zhang G., Zhang A., Zhang L., Zhu A., Li Z., Zhu W., Hu W., Ye C. The characteristics of the influenza virus epidemic around the SARS-CoV-2 epidemic period in the Pudong New Area of Shanghai. J. Epidemiol. Glob. Health. 2024;14:304–310. doi: 10.1007/s44197-024-00194-9. - DOI - PMC - PubMed
    1. Jang G., Kim J., Thompson R.N., Lee H. Modeling vaccine prioritization strategies for post-pandemic COVID-19 incorporating unreported rates and age groups in Republic of Korea. J. Infect. Public Health. 2025;18:102688. doi: 10.1016/j.jiph.2025.102688. - DOI - PubMed
    1. Lv C., Guo W., Yin X., Liu L., Huang X., Li S., Zhang L. Innovative applications of artificial intelligence during the COVID-19 pandemic. Infect. Med. 2024;3:100095. doi: 10.1016/j.imj.2024.100095. - DOI - PMC - PubMed
    1. Karcioglu O., editor. New COVID-19 Variants—Diagnosis and Management in the Post-Pandemic Era: Diagnosis and Management in the Post-Pandemic Era. BoD–Books on Demand; Hamburg, Germany: 2024.

LinkOut - more resources