A Deep Learning Based Approach for Detection and Severity Classification of Monkey pox Disease
DOI:
https://doi.org/10.20372/pjet.v4i1.3056Keywords:
Deep learning, Feature extraction, Segmentation, Severity, MonkeypoxAbstract
Mpox disease has become one of the serious global public health outbreaks globally. It is a major concern due to its rapid transmission, increasing outbreak frequency, and potential to cause severe illness and death. Detecting mpox disease in the early stage before widespread community transmission is a major challenge for clinicians in health care system settings. This study aims to design an early detection and severity level classification of mpox disease model using a deep learning approach. We used a deep Convolutional Neural Network (CNN) for detection and severity classification of mpox disease into different predefined class levels. A total of 3017 customized images were collected from online health sources and Kaggle, then annotated by radiologists at Felegehiwot Comprehensive Specialized Hospital in Bahir Dar, Ethiopia. The dataset was divided into training (70%), validation (15%), and testing (15%) subsets, with data augmentation applied to increase the limited dataset size. Segmentation techniques were applied to improve image quality case. The experimental result shows that the proposed model achieved an accuracy of 95.63%, Precision 95.73%, Recall 95.73%, and F1-Score 95.67% severity classification performance result. This study has great significance by enabling clinically meaningful stage-specific diagnosis, offering doctors a practical tool for early and efficient detection and management of mpox disease. The proposed model is a lightweight, faster, smaller-sized deep learning-based model that uniquely classifies mpox disease severity stages by integrating a threshold segmentation step before feature extraction, improving both accuracy and efficiency compared to existing approaches
References
1. I. D. Ladnyj, P. Ziegler, and E. Kima, “A human infection caused by mpox virus in Basankusu Territory, Democratic Republic of the Congo,” Bulletin of the World Health Organization, vol. 46, no. 5, pp. 593–597, 1972, doi: 10.2471/BLT.72.46.5.593
2. H. F. Alhasson, E. Almozainy, M. Alharbi, N. Almansour, S. S. Alharbi, and R. U. Khan, “A Deep Learning-Based mobile application for mpox detection,” Applied Sciences, vol. 13, no. 23, p. 12589, Nov. 2023, doi: 10.3390/app132312589.
3. S. Khattak et al., “The mpox diagnosis, treatments and prevention: A review,” Frontiers in Cellular and Infection Microbiology, vol. 12, p. 1088471, Feb. 2023, doi: 10.3389/fcimb.2022.1088471.
4. Y. Ortiz-Martínez and A. F. Henao-Martínez, “Time-related change in mpox (mpox) skin lesions and their progression,” in Elsevier eBooks, Elsevier, 2025, pp. 269–290. doi: 10.1016/b978-0-443-22123-1.00016-8.
5. S. Srivastava et al., “The Global Mpox (MPOx) Outbreak: A Comprehensive review,” Vaccines, vol. 11, no. 6, p. 1093, Jun. 2023, doi: 10.3390/vaccines11061093.
6. A. J. Porzucek et al., “Development of an accessible and scalable quantitative polymerase chain reaction assay for mpox virus detection,” The Journal of Infectious Diseases, vol. 227, no. 9, pp. 1084–1087, Oct. 2022, doi: 10.1093/infdis/jiac414.
7. A. Dosovitskiy et al., “An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale,” arXiv (Cornell University), Oct. 2020, doi: 10.48550/arxiv.2010.11929.
8. A. Gessain, E. Nakoune, and Y. Yazdanpanah, “Mpox,” New England Journal of Medicine, vol. 387, no. 19, pp. 1783–1793, Oct. 2022, doi: 10.1056/nejmra2208860.
9. S. Rampogu, “A review on the use of machine learning techniques in mpox disease prediction,” Science in One Health, vol. 2, p. 100040, Jan. 2023, doi: 10.1016/j.soh.2023.100040.
10. A. K. Gairola and V. Kumar, “Mpox Disease Diagnosis using Machine Learning Approach,” 2022 8th International Conference on Signal Processing and Communication (ICSC), pp. 423–427, Dec. 2022, doi: 10.1109/icsc56524.2022.10009135.
11. T. Nayak et al., “Deep learning based detection of mpox virus using skin lesion images,” Medicine in Novel Technology and Devices, vol. 18, p. 100243, Jun. 2023, doi: 10.1016/j.medntd.2023.100243.
12. A. S. Azar, A. Naemi, S. B. Rikan, J. B. Mohasefi, H. Pirnejad, and U. K. Wiil, “Mpox detection using deep neural networks,” BMC Infectious Diseases, vol. 23, no. 1, p. 438, Jun. 2023, doi: 10.1186/s12879-023-08408-4.
13. O. Chunhapran, M. Maliyeam, and G. Quirchmayr, “Mpox lesion and rash stage classification using deep learning technique,” in Lecture notes in networks and systems, 2024, pp. 141–149. doi: 10.1007/978-3-031-58561-6_14.
14. S. Maqsood and R. Damaševi?ius, Mpox Detection and Classification Using Deep Learning Based Features Selection and Fusion Approach. IEEE (Institute of Electrical and Electronics Engineers), 2023, pp. 1–8. doi: 10.1109/syscon53073.2023.10131067.
15. H. Talebi and P. Milanfar, “Learning to resize images for computer vision tasks,” arXiv.org, Mar. 17, 2021. https://arxiv.org/abs/2103.09950
16. C. Shorten and T. M. Khoshgoftaar, “A survey on Image Data Augmentation for Deep Learning,” Journal of Big Data, vol. 6, no. 1, Jul. 2019, doi: 10.1186/s40537-019-0197-0.
17. F. M. Mustafa, “Image Enhancement based on the Histogram Equalization and Multiresolution Discrete Stationary Wavelet Transforms,” Academic Journal of Nawroz University, vol. 11, no. 2, pp. 50–59, Apr. 2022, doi: 10.25007/ajnu.v11n2a1323.
18. X. Zhao, L. Wang, Y. Zhang, X. Han, M. Deveci, and M. Parmar, “A review of convolutional neural networks in computer vision,” Artificial Intelligence Review, vol. 57, no. 4, Mar. 2024, doi: 10.1007/s10462-024-10721-6.
19. S. N. Ali et al., “Mpox skin lesion detection Using Deep Learning Models: A Feasibility study,” arXiv.org, Jul. 06, 2022. https://arxiv.org/abs/2207.03342
20. E. Hassan, M. Y. Shams, N. A. Hikal, and S. Elmougy, “The effect of choosing optimizer algorithms to improve computer vision tasks: a comparative study,” Multimedia Tools and Applications, vol. 82, no. 11, pp. 16591–16633, Sep. 2022, doi: 10.1007/s11042-022-13820-0.
21. I. Salehin and D.-K. Kang, “A Review on Dropout Regularization Approaches for Deep Neural Networks within the Scholarly Domain,” Electronics, vol. 12, no. 14, p. 3106, Jul. 2023, doi: 10.3390/electronics12143106
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Poly Journal of Engineering and Technology (PJET)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
