Monkeypox Diagnosis Using MRMR-Based Feature Selection and Hybrid Deep Learning Models: ResNet50V2, NASNetMobile, and InceptionV3

Abstract

Monkeypox, like many other epidemics diseases, has been spreading rapidly. Its transmission through both respiratory droplets and physical contact has significantly contributed to its fast dissemination. The emergence of the first major outbreaks in the African region in 2022, followed by the disease spreading at an epidemic level, has raised global concerns. Although this potentially fatal disease can be partially detected through PCR methods, it often exhibits symptoms similar to other skin diseases, making accurate diagnosis challenging. At this point, computer-aided detection systems, particularly those based on image processing techniques, become crucial. The primary aim of this study is to enable the automatic diagnosis of monkeypox using deep learning methods by enhancing classification performance through the selection of the most significant features among multiple models. In this study, a hybrid deep learning approach is proposed that integrates transfer learning models such as ResNet50V2, NASNetMobile, and InceptionV3 with the mRMR (Minimum Redundancy Maximum Relevance) feature selection method. The features extracted from each model were concatenated to form a unified feature vector, from which the 10 most relevant features were selected using the mRMR algorithm. Finally, classification was performed based on these selected features. Experiments were conducted on three different datasets—MSLD, MSCI, and MSID—containing various skin lesion diseases. The proposed approach achieved accuracy rates of 92.00%, 92.50%, and 87.65%, respectively. Among these, the highest accuracy was observed on the MSCI dataset, with a rate of 92.50%. This hybrid approach demonstrated high performance across diverse datasets and significantly contributed to clinical diagnosis processes by enabling the accurate identification of not only monkeypox but also other visually similar skin lesions.

Keywords

• Monkeypox
• ResNet50V2
• NASNetMobile
• InceptionV3
• mRMR

References

1. J. Zhang, F. Zhong, K. He, M. Ji, S. Li, and C. Li, “Recent advancements and perspectives in the diagnosis of skin diseases using machine learning and deep learning: A review,” Diagnostics, vol. 13, no. 23, p. 3506, 2023.
2. M. Pal, P. Dave, and R. Mahendra, “Ebola hemorrhagic fever: An emerging highly contagious and fatal viral zoonosis,” Int. J. Multidiscip. Res., vol. 2, pp. 1–2, 2014.
3. M. N. Lessani, Z. Li, F. Jing, S. Qiao, J. Zhang, B. Olatosi, and X. Li, “Human mobility and the infectious disease transmission: a systematic review,” Geo-Spatial Inf. Sci., vol. 27, no. 6, pp. 1824–1851, 2024.
4. N. Berthet, S. Descorps-Declère, C. Besombes, M. Curaudeau, A. A. Nkili Meyong, B. Selekon, and E. Nakoune, “Genomic history of human monkeypox infections in the Central African Republic between 2001 and 2018,” Sci. Rep., vol. 11, no. 1, Art. no. 13085, 2021.
5. R. P. Chauhan, R. Fogel, and J. Limson, “Overview of diagnostic methods, disease prevalence and transmission of MPOX (formerly monkeypox) in humans and animal reservoirs,” Microorganisms, vol. 11, no. 5, p. 1186, 2023.
6. E. Alakunle, D. Kolawole, D. Diaz-Canova, F. Alele, O. Adegboye, U. Moens, and M. I. Okeke, “A comprehensive review of monkeypox virus and mpox characteristics,” Front. Cell. Infect. Microbiol., vol. 14, Art. no. 1360586, 2024.
7. M. M. Islam, P. Dutta, R. Rashid, S. S. Jaffery, A. Islam, E. Farag, et al., “Pathogenicity and virulence of monkeypox at the human-animal-ecology interface,” Virulence, vol. 14, no. 1, p. 2186357, 2023.
8. H. Harapan, Y. Ophinni, D. Megawati, A. Frediansyah, S. S. Mamada, M. Salampe, et al., “Monkeypox: A comprehensive review,” Viruses, vol. 14, no. 10, p. 2155, 2022.

9. D. Hastari, S. Winanda, A. R. Pratama, N. Nurhaliza, and E. S. Ginting, “Application of Convolutional Neural Network ResNet-50 V2 on image classification of rice plant disease,” Public Res. J. Eng., Data Technol. Comput. Sci., vol. 1, no. 2, 2024.
10. S. Riyadi, F. A. Abidin, and N. Audita, “Comparison of ResNet50V2 and MobileNetV2 models in building architectural style classification,” in Proc. 2024 Int. Conf. Intelligent Syst. Comput. Vis. (ISCV), May 2024, pp. 1–8.
11. E. Gupta, M. Gupta, R. A. Sachdeva, P. Handa, and N. Goel, “Automatic seizure detection using rhythmicity spectrograms and inception-v3 architecture,” in Proc. 2023 10th Int. Conf. Signal Process. Integr. Networks (SPIN), Mar. 2023, pp. 131–136.
12. X. Zhao, L. Wang, Y. Zhang, X. Han, M. Deveci, and M. Parmar, “A review of convolutional neural networks in computer vision,” Artif. Intell. Rev., vol. 57, no. 4, p. 99, 2024.
13. İ. Aksoy and K. Adem, “Optimizing hyperparameters for enhanced performance in convolutional neural networks: A study using NASNetMobile and DenseNet201 models,” Mühendislik Bilimleri ve Araştırmaları Dergisi, vol. 6, no. 1, pp. 42–52, 2024.
14. A. O. Adedoja, P. A. Owolawi, T. Mapayi, and C. Tu, “Intelligent mobile plant disease diagnostic system using NASNet-mobile deep learning,” IAENG Int. J. Comput. Sci., vol. 49, no. 1, pp. 216–231, 2022.
15. K. Radhika, K. Devika, T. Aswathi, P. Sreevidya, V. Sowmya, and K. P. Soman, “Performance analysis of NASNet on unconstrained ear recognition,” in Nature Inspired Computing for Data Science, pp. 57–82, 2020.
16. V. Yelleti and P. S. V. S. Sai Prasad, “mRMR Feature Selection to Handle High Dimensional Datasets: Vertical Partitioning Based Iterative MapReduce Framework,” in Intelligent Systems Design and Applications, Lecture Notes in Networks and Systems, vol. 1050, pp. 79–90, July 2024, doi: 10.1007/978-3-031-64847-2_7.
17. M. Altun, H. Gürüler, O. Özkaraca, F. Khan, J. Khan, and Y. Lee, "Monkeypox detection using CNN with transfer learning," Sensors, vol. 23, no. 4, p. 1783, 2023.
18. O. Attallah, "MonDiaL-CAD: Monkeypox diagnosis via selected hybrid CNNs unified with feature selection and ensemble learning," Digit. Health, vol. 9, p. 20552076231180054, 2023.
19. S. U. R. Khan, S. Asif, O. Bilal, and S. Ali, "Deep hybrid model for Mpox disease diagnosis from skin lesion images," Int. J. Imaging Syst. Technol., vol. 34, no. 2, p. e23044, 2024.
20. S. Asif, M. Zhao, F. Tang, Y. Zhu, and B. Zhao, "Metaheuristics optimization-based ensemble of deep neural networks for Mpox disease detection," Neural Netw., vol. 167, pp. 342–359, 2023.
21. C. Sitaula and T. B. Shahi, "Monkeypox virus detection using pre-trained deep learning-based approaches," J. Med. Syst., vol. 46, no. 11, p. 78, 2022.
22. H. H. Luong, N. H. Khang, N. Q. Le, D. M. Canh, and P. S. Ha, "A proposed approach for monkeypox classification," Int. J. Adv. Comput. Sci. Appl., vol. 14, no. 8, 2023.
23. B. Gülmez, "MonkeypoxHybridNet: A hybrid deep convolutional neural network model for monkeypox disease detection," Int. Res. Eng. Sci., vol. 3, pp. 49–64, 2022.
24. S. Rampogu, "A review on the use of machine learning techniques in monkeypox disease prediction," Sci. One Health, p. 100040, 2023.
25. A. I. Saleh and A. H. Rabie, "Human monkeypox diagnose (HMD) strategy based on data mining and artificial intelligence techniques," Comput. Biol. Med., vol. 152, p. 106383, 2023.
26. F. Uysal, "Detection of monkeypox disease from human skin images with a hybrid deep learning model," Diagnostics, vol. 13, no. 10, p. 1772, 2023.
27. B. Tasci, "Ön eğitimli evrişimsel sinir ağı modellerinde öznitelik seçim algoritmasını kullanarak cilt lezyon görüntülerinin sınıflandırılması," Fırat Univ. J. Eng. Sci., vol. 34, no. 2, pp. 541–552, 2022.