Comprehensive and Integrated Deep Learning Approaches-based Intelligent Skin Disease Diagnosis System for Pox Detection
Article Sidebar
Main Article Content
Abstract
Chickenpox, measles, monkeypox, and smallpox are skin diseases that exhibit very similar signs, making accurate distinction difficult. In this study, an automated deep learning system is developed to classify pox-related skin diseases into six classes, which are Chicken_Pox, Measles, Monkey_Pox, Small_Pox, Normal, and Unknown. The system uses MobileNet to extract features efficiently using a dataset of 4099 training and 1104 evaluation images. The three tested model variants: inception-based CNN, Deep Belief Network, and MobileNet-LSTM-hybrid, Deep Belief Network (DBN) with the SGD optimizer, incurred the best classification accuracy, showing to be more effective at similar tasks to retrieve spatial and temporal features. This will ensure more efficient and quicker detection of the pox, particularly in those regions that do not have specialists in dermatology. Although it is not a replacement for clinical expertise, the system provides a potent instrument in screening and diagnosis of early diseases. The comparative evaluation of these models offers insights into the most effective approach for medical image classification of pox diseases.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
Marin, M.; Meissner, H. C.; Seward, J. F. J. P. Varicella prevention in the United States: a review of successes and challenges. Pediatrics 2008, 122(3), e744–e751. https://doi.org/10.1542/peds.2008-0567
Henderson, D. A.; et al. Smallpox as a biological weapon: medical and public health management. J. Am. Med. Assoc. 1999, 281(22), 2127–2137. https://doi.org/10.1001/jama.281.22.2127
Beber, A. A. C.; Benvegnú, A. M.; da Pieve, D.; Dallazem, L. N. D.; Neumaier, L. F. T. Viral infections. In Dermatology in Public Health Environments: A Comprehensive Textbook; Springer, 2023; pp 203–291. https://doi.org/10.1007/978-3-031-13505-7_10
Robbins, H.; Monro, S. J. T. a. o. m. s. A stochastic approximation method. Ann. Math. Stat. 1951, 22(3), 400–407. https://doi.org/10.1214/aoms/1177729586
Kononenko, I. J. A. I. i. m. Machine learning for medical diagnosis: history, state of the art and perspective. Artif. Intell. Med. 2001, 23(1), 89–109. https://doi.org/10.1016/S0933-3657(01)00077-X
Savaş, S. J. J. o. i. i. i. m. Enhancing disease classification with deep learning: a two-stage optimization approach for monkeypox and similar skin lesion diseases. J. Intell. Inf. Manag. 2024, 37(2), 778–800. https://doi.org/10.1007/s10278-023-00941-7
Idroes, G. M.; Noviandy, T. R.; Emran, T. B.; Idroes, R. J. H. J. o. A. S. Explainable Deep Learning Approach for Mpox Skin Lesion Detection with Grad-CAM. Hasanuddin J. Appl. Sci. 2024, 2(2), 54–63. https://doi.org/10.60084/hjas.v2i2.216
Vuran, S.; Ucan, M.; Akin, M.; Kaya, M. J. D. Multi-Classification of Skin Lesion Images Including Mpox Disease Using Transformer-Based Deep Learning Architectures. Diagnostics 2025, 15(3), 374. https://doi.org/10.3390/diagnostics15030374
Uysal, F. J. D. Detection of monkeypox disease from human skin images with a hybrid deep learning model. Diagnostics 2023, 13(10), 1772. https://doi.org/10.3390/diagnostics13101772
Uzun Ozsahin, D.; Mustapha, M. T.; Uzun, B.; Duwa, B.; Ozsahin, I. J. D. Computer-aided detection and classification of monkeypox and chickenpox lesion in human subjects using deep learning framework. Diagnostics 2023, 13(2), 292. https://doi.org/10.3390/diagnostics13020292
Abdelrahim, E. M.; Hashim, H.; Atlam, E.-S.; Osman, R. A.; Gad, I. J. D. TMS: Ensemble Deep Learning Model for Accurate Classification of Monkeypox Lesions Based on Transformer Models with SVM. Diagnostics 2024, 14(23), 2638. https://doi.org/10.3390/diagnostics14232638
Khan, S. U. R.; Asif, S.; Bilal, O.; Ali, S. J. I. J. o. I. S. Deep hybrid model for Mpox disease diagnosis from skin lesion images. Int. J. Imaging Syst. Technol. 2024, 34(2), e23044. https://doi.org/10.1002/ima.23044
Siddick, B.; et al. Hybrid Approach of Classification of Monkeypox Disease: Integrating Transfer Learning with ViT and Explainable AI. Int. J. Adv. Comput. Sci. Appl. 2024, 15(12), 656–664. (Page numbers assumed based on typical journal article length, as they were missing.) https://doi.org/10.14569/IJACSA.2024.0151286
Chakroborty, S. J. m. H-MpoxNet: A Hybrid Deep Learning Framework for Mpox Detection from Image Data. 2024. (Preprint, pages not applicable.) https://doi.org/10.1101/2024.11.26.24318006
Das, B.; Dagdogen, H. A.; Kaya, M. O.; Das, R. J. I. F. A novel hybrid model combining Vision Transformers and Graph Convolutional Networks for monkeypox disease effective diagnosis. Inf. Fusion 2025, 117, 102858. https://doi.org/10.1016/j.inffus.2024.102858
Nazeeruddin, E.; Latif, G.; Mohammad, N. Monkeypox and Chickenpox Skin Lesions Classification Using Hybrid Deep Learning Features. In 2025 International Conference on Inventive Computation Technologies (ICICT); IEEE, 2025; pp 1005–1010. https://doi.org/10.1109/ICICT64420.2025.11004913
Rashid, S.; Bariq, A.; Ali, I.; Sultana, S.; Siddiqa, A.; Elagan, S. K. J. S. R. Dynamic analysis and optimal control of a hybrid fractional monkeypox disease model in terms of external factors. Sci. Rep. 2025, 15(1), 2944. https://doi.org/10.1038/s41598-024-83691-y
Gülmez, B. J. I. R. E. S. MonkeypoxHybridNet: A hybrid deep convolutional neural network model for monkeypox disease detection. Int. Res. Educ. Sci. 2022, 3(2), 49–64. (Assuming the missing issue number is 2).
Ali, S. N.; et al. A web-based mpox skin lesion detection system using state-of-the-art deep learning models considering racial diversity. Biomed. Signal Process. Control 2024, 98, 106742. https://doi.org/10.1016/j.bspc.2024.106742
Balasubramaniam. Pox Dataset. Kaggle, 2022. https://www.kaggle.com/datasets/balasubramaniamv/pox-dataset (accessed 2025-06-06).
