Application of Artificial Intelligence in Disease Prediction and Diagnosis: A Deep Learning Approach for Monkeypox Skin Lesion Classification
Ajeet Kumar
Research Scholar, Department of Computer Science and Engineering, Sagar Institute of Technology & Management, Barabanki, U.P.
Author
Rajesh Kumar Sharma
Assistant Professor, Department of Computer Science and Engineering, Sagar Institute of Technology & Management, Barabanki, U.P.
Author
Dr. J. B. Singh
Professor, Department of Computer Science and Engineering, Sagar Institute of Technology & Management, Barabanki, U.P.
Author
📌 DOI: https://doi.org/10.63920/tjths.091026005
🔑 Keywords: Monkeypox; Convolutional Neural Network; ResNet50; EfficientNet; Transfer Learning; Skin Lesion Classification; Optimizers
📅 Publication Date: 15 September 2026
📜 License:
This work is licensed under a Creative Commons Attribution 4.0 International License
- Share — Copy and Redistribute the material
- Adapt — Remix, Transform, and build upon the material
- The licensor cannot revoke these freedoms as long as you follow the license terms.
Abstract:
Manual sample collection and visual diagnosis remain the dominant methods for identifying contagious skin diseases, exposing clinicians to infection risk while offering diagnostic accuracy that rarely exceeds 60% on unaided visual inspection. The COVID-19 pandemic highlighted the urgent need for touch-free, automated diagnostic tools, and the subsequent emergence of monkeypox as a globally notifiable disease reinforced this need. This paper presents a convolutional neural network (CNN)-based framework for the early, non-invasive detection of monkeypox from skin-lesion images. A dataset of monkeypox and non-monkeypox (measles, chickenpox, smallpox, cowpox) images was curated through manual web extraction, preprocessed, and expanded through augmentation (rotation, reflection, shearing). Three transfer-learning architectures — ResNet50, EfficientNetB3 and EfficientNetB7 — were fine-tuned and compared, and three optimizers (Adam, SGD and RMSprop) were evaluated for their effect on prediction accuracy and model loss. EfficientNetB3 achieved the best overall performance with 87% accuracy, 92% precision, 87% recall and an F1-score of 90, outperforming ResNet50 (84% accuracy) and EfficientNetB7, whose accuracy degraded with increasing epochs. Among optimizers, Adam consistently yielded the highest prediction accuracy (82%) and the lowest sustained model loss, followed by RMSprop and SGD. The results confirm that lightweight, pre-trained CNN architectures combined with careful hyper-parameter tuning can provide a practical, contact-free screening aid for monkeypox and related dermatological conditions.
Download Full PDF Paper
📖 How to Cite
Ajeet K., Rajesh K. S., J. B. Singh(2026). Application of Artificial Intelligence in Disease Prediction and Diagnosis: A Deep Learning Approach for Monkeypox Skin Lesion Classification. TEJAS J. Technol. Humanit. Sci., Vol. 05, Issue 03. https://doi.org/10.63920/tjths.091026005
📊 Article Metrics
References
[1] World Health Organization, “Monkeypox fact sheet,” 2022. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/monkeypox.
[2] R. G. Tiwari, A. Misra, V. Khullar, A. K. Agarwal, S. Gupta, and A. P. Srivastava, “Identifying microscopic augmented images using pre-trained deep convolutional neural networks,” in Proc. Int. Conf. Technological Advancements and Innovations (ICTAI), 2021, pp. 32–37.
[3] S. Majumder and M. A. Ullah, “Feature extraction from dermoscopy images for an effective diagnosis of melanoma skin cancer,” in Proc. Int. Conf. Electrical and Computer Engineering (ICECE), 2018.
[4] S. M. Jaisakthi, P. Mirunalini, and C. Aravindan, “Automated skin lesion segmentation of dermoscopic images using GrabCut and k-means algorithms,” IET Computer Vision, vol. 12, no. 8, pp. 1088–1095, 2018.
[5] M. A. Al-Masni et al., “Skin lesion segmentation in dermoscopy images via deep full resolution convolutional networks,” Computer Methods and Programs in Biomedicine, vol. 162, pp. 221–231, 2018.
[6] R. D. Seeja and A. Suresh, “Melanoma classification employing inter-neighbor statistical color and mean order pattern texture feature,” Multimedia Tools and Applications, vol. 80, no. 13, pp. 20045–20064, 2021.
[7] N. Moura et al., “Combining ABCD rule, texture features and transfer learning in automatic diagnosis of melanoma,” in Proc. IEEE Symp. Computers and Communications (ISCC), 2018.
[8] I. Z. Mukti and D. Biswas, “Transfer learning based plant diseases detection using ResNet50,” in Proc. Int. Conf. Electrical Information and Communication Technology (EICT), 2019, pp. 1–6.
[9] G. S. Ghalejoogh, H. M. Kordy, and F. Ebrahimi, “A hierarchical structure based on stacking approach for skin lesion classification,” Expert Systems with Applications, vol. 145, Art. no. 113127, 2020.
[10] S. R. Salian and S. D. Sawarkar, “Melanoma skin lesion classification using improved EfficientNetB3,” Jordanian Journal of Computers and Information Technology, vol. 8, no. 1, 2022.
[11] M. Tan and Q. Le, “EfficientNet: Rethinking model scaling for convolutional neural networks,” in Proc. Int. Conf. Machine Learning (ICML), 2019.
[12] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770–778.
[13] S. N. Ali et al., “Monkeypox skin lesion detection using deep learning models: A feasibility study,” arXiv preprint arXiv:2207.03342, 2022.
[14] A. Srivastava and M. Agarwal, “Advanced cybersecurity and surveillance frameworks for 5G–IoT ecosystems: Integrating Web 3.0, blockchain, and zero trust architecture,” TEJAS Journal of Technologies and Humanitarian Science, vol. 4, no. 4. doi: 10.63920/tjths.44008.
[15] Y. Bajpai, A. Joshi, and A. Srivastava, “Reducing FastText's limits in Romanized language detection,” TEJAS Journal of Technologies and Humanitarian Science, vol. 4, no. 4, 2025, doi: 10.63920/tjths.44001.