Mpox skin lesions may exhibit visual similarities with other infectious skin conditions, particularly chickenpox and measles, making reliable image-based differentiation challenging. This study presents an LBP InceptionV3 hybrid approach for Mpox detection using skin lesion images. The proposed framework combines high level visual representations extracted using pretrained InceptionV3 with complementary local texture information generated using Local Binary Pattern (LBP). The secondary dataset comprised 228 original images. 102 images belong to Mpox class, while 126 images belong to the others class (chickenpox and measles). The images were expanded through augmentation to 3,192 images comprising 1,428 Mpox and 1,764 Other images. Images were standardized to 224 × 224 pixels and divided into training, validation, and testing sets using a 70:15:15 ratio. InceptionV3 generated a 2,048-dimensional deep feature representation, while LBP texture maps were processed through a shallow convolutional network to obtain 512 texture features. The resulting 2,560-dimensional representation was fused for classification. The proposed model achieved 94.15% accuracy, 94.16% precision, 94.15% recall, 94.16% F1 score, and an AUC of 0.99. On the 479 image test set, 451 images were correctly classified, including 202 Mpox and 249 Other images. The ablation study demonstrated that incorporating LBP improved accuracy from 88.72% for InceptionV3 alone to 94.15%, representing a 5.43 percentage point improvement, while AUC increased from 0.95 to 0.99. In addition, clinically sourced images from Owerri General Hospital were used to provide an independent assessment of the model on previously unseen skin lesion samples. The findings demonstrate that combining deep visual and local texture representations provides an effective approach for Mpox skin lesion classification.
| Published in | American Journal of Neural Networks and Applications (Volume 12, Issue 2) |
| DOI | 10.11648/j.ajnna.20261202.12 |
| Page(s) | 57-75 |
| Creative Commons |
This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited. |
| Copyright |
Copyright © The Author(s), 2026. Published by Science Publishing Group |
Mpox Detection, Local Binary Pattern, InceptionV3, Skin Lesion Classification, Deep Learning, Texture Features
| [1] | R. A. Farahat, R. Sah, A. A. El-Sakka, A. Y. Benmelouka, M. Kundu, F. Labieb, et al., “Human monkeypox disease (MPX),” Le Infezioni in Medicina, vol. 30, no. 3, pp. 372–391, 2022, |
| [2] | M. M. Ahsan, K. A. Momin, M. R. Uddin, M. Farjana, A. N. Sakib, and S. A. Luna, “Image data collection and implementation of deep learning-based model in detecting monkeypox disease using modified VGG16,” arXiv preprint arXiv: 2206.01862, 2022, |
| [3] | O. A. Alrusaini, “Deep learning models for the detection of monkeypox skin lesion on digital skin images,” International Journal of Advanced Computer Science and Applications, vol. 14, no. 1, pp. 637–644, 2023, |
| [4] | T. Islam, M. A. Hussain, F. U. H. Chowdhury, and B. M. R. Islam, “A web-scraped skin image database of monkeypox, chickenpox, smallpox, cowpox, and measles,” arXiv preprint arXiv: 2209.00751, 2022, |
| [5] | M. E. Haque, R. S. Nila, M. R. Ahmed, and S. Islam, “Classification of human monkeypox disease using deep learning models and attention mechanisms,” in Proc. 25th Int. Conf. Computer and Information Technology (ICCIT), pp. 647–652, 2022. |
| [6] | T. Mandina and P. Murali, “Intelligent deep learning based monkeypox detection,” Foundry, vol. 28, no. 6, pp. 415–424, 2024. |
| [7] | A. Shateri, N. Nourani, M. Dorrigiv, and H. Nasiri, “An explainable nature-inspired framework for monkeypox diagnosis: Xception features combined with NGBoost and African vultures optimization algorithm,” arXiv preprint arXiv: 2504.17540, pp. 1–52, 2025, |
| [8] | D. Devarajan, P. Dhana Lakshmi, S. Krishnaveni, and S. Senthilkumar, “Human monkeypox disease prediction using novel modified restricted Boltzmann machine-based equilibrium optimizer,” Scientific Reports, vol. 14, no. 1, Art. no. 16252, 2024, |
| [9] | H. Saleh, S. Mostafa, A. H. Ismail, S. Srivastava, and S. H. Alsamhi, “Swin-PSO-SVM: A novel hybrid model for monkeypox early detection,” IEEE Access, vol. 12, pp. 187373–187385, 2024, |
| [10] | D. Kundu, M. M. Rahman, A. Rahman, D. Das, U. R. Siddiqi, M. G. R. Alam, et al., “Federated deep learning for monkeypox disease detection on GAN-augmented dataset,” IEEE Access, vol. 12, pp. 32812–32829, 2024, |
| [11] | M. Waqar, Z. A. Khan, S. T. Khawaja, N. I. Chaudhary, S. Khan, K. M. Cheema, et al., “Explainable clinical diagnosis through unexploited yet optimized fine-tuned ConvNeXt models for accurate monkeypox disease classification,” SLAS Technology, vol. 33, Art. no. 100336, 2025, |
| [12] | V. Vandana, C. Sharma, and M. A. Shah, “MRpoxNet: An enhanced deep learning approach for early detection of monkeypox using modified ResNet50,” Digital Health, vol. 11, pp. 1–18, 2025, |
| [13] | Yuan, H., Yan, B., Chong, Y., Wang, L., & Jiang, Y. (2025). Time trend of measles burden on children and adolescents in BRICS-plus countries from 1990 to 2021 and prediction to 2032. Frontiers in Microbiology, 16, 1612124. |
| [14] | Kumar, K. (2023). Reservoir computing in epidemiological forecasting: Predicting chicken pox incidence. 1-17. medRxiv. |
| [15] | Quach, H. Q., Jones, S. P., Joseph, I., Powell, A. J., Ovsyannikova, I. G., Warner, N. D.,... Kennedy, R. B. (2025). Low measles seropositivity in vaccinated children. JAMA Network Open, 8(1), e2452345. |
| [16] | Wittenberg, R., Damant, J., Rehill, A., Knapp, M., Adeyemi, T., & Matthews, I. (2025). Estimated value of productivity lost due to childhood chickenpox in the United Kingdom: A survey of parents. *Expert Review of Pharmacoeconomics & Outcomes Research, 25(2), 197–203. |
APA Style
Nlemedim, V. I., John-Otumu, A. M., Esomonu, N. F., Ogene, F. (2026). LIMD: LBP-InceptionV3 Hybrid Approach for Mpox Detection Using Skin Lesion Images. American Journal of Neural Networks and Applications, 12(2), 57-75. https://doi.org/10.11648/j.ajnna.20261202.12
ACS Style
Nlemedim, V. I.; John-Otumu, A. M.; Esomonu, N. F.; Ogene, F. LIMD: LBP-InceptionV3 Hybrid Approach for Mpox Detection Using Skin Lesion Images. Am. J. Neural Netw. Appl. 2026, 12(2), 57-75. doi: 10.11648/j.ajnna.20261202.12
AMA Style
Nlemedim VI, John-Otumu AM, Esomonu NF, Ogene F. LIMD: LBP-InceptionV3 Hybrid Approach for Mpox Detection Using Skin Lesion Images. Am J Neural Netw Appl. 2026;12(2):57-75. doi: 10.11648/j.ajnna.20261202.12
Share This Article
Twitter
Linked In
Facebook
Copy
Download@article{10.11648/j.ajnna.20261202.12,
author = {Vivian Ifeoma Nlemedim and Adetokunbo MacGregor John-Otumu and Nkechi Faustina Esomonu and Ferguson Ogene},
title = {LIMD: LBP-InceptionV3 Hybrid Approach for Mpox Detection Using Skin Lesion Images},
journal = {American Journal of Neural Networks and Applications},
volume = {12},
number = {2},
pages = {57-75},
doi = {10.11648/j.ajnna.20261202.12},
url = {https://doi.org/10.11648/j.ajnna.20261202.12},
eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajnna.20261202.12},
abstract = {Mpox skin lesions may exhibit visual similarities with other infectious skin conditions, particularly chickenpox and measles, making reliable image-based differentiation challenging. This study presents an LBP InceptionV3 hybrid approach for Mpox detection using skin lesion images. The proposed framework combines high level visual representations extracted using pretrained InceptionV3 with complementary local texture information generated using Local Binary Pattern (LBP). The secondary dataset comprised 228 original images. 102 images belong to Mpox class, while 126 images belong to the others class (chickenpox and measles). The images were expanded through augmentation to 3,192 images comprising 1,428 Mpox and 1,764 Other images. Images were standardized to 224 × 224 pixels and divided into training, validation, and testing sets using a 70:15:15 ratio. InceptionV3 generated a 2,048-dimensional deep feature representation, while LBP texture maps were processed through a shallow convolutional network to obtain 512 texture features. The resulting 2,560-dimensional representation was fused for classification. The proposed model achieved 94.15% accuracy, 94.16% precision, 94.15% recall, 94.16% F1 score, and an AUC of 0.99. On the 479 image test set, 451 images were correctly classified, including 202 Mpox and 249 Other images. The ablation study demonstrated that incorporating LBP improved accuracy from 88.72% for InceptionV3 alone to 94.15%, representing a 5.43 percentage point improvement, while AUC increased from 0.95 to 0.99. In addition, clinically sourced images from Owerri General Hospital were used to provide an independent assessment of the model on previously unseen skin lesion samples. The findings demonstrate that combining deep visual and local texture representations provides an effective approach for Mpox skin lesion classification.},
year = {2026}
}
TY - JOUR T1 - LIMD: LBP-InceptionV3 Hybrid Approach for Mpox Detection Using Skin Lesion Images AU - Vivian Ifeoma Nlemedim AU - Adetokunbo MacGregor John-Otumu AU - Nkechi Faustina Esomonu AU - Ferguson Ogene Y1 - 2026/09/28 PY - 2026 N1 - https://doi.org/10.11648/j.ajnna.20261202.12 DO - 10.11648/j.ajnna.20261202.12 T2 - American Journal of Neural Networks and Applications JF - American Journal of Neural Networks and Applications JO - American Journal of Neural Networks and Applications SP - 57 EP - 75 PB - Science Publishing Group SN - 2469-7419 UR - https://doi.org/10.11648/j.ajnna.20261202.12 AB - Mpox skin lesions may exhibit visual similarities with other infectious skin conditions, particularly chickenpox and measles, making reliable image-based differentiation challenging. This study presents an LBP InceptionV3 hybrid approach for Mpox detection using skin lesion images. The proposed framework combines high level visual representations extracted using pretrained InceptionV3 with complementary local texture information generated using Local Binary Pattern (LBP). The secondary dataset comprised 228 original images. 102 images belong to Mpox class, while 126 images belong to the others class (chickenpox and measles). The images were expanded through augmentation to 3,192 images comprising 1,428 Mpox and 1,764 Other images. Images were standardized to 224 × 224 pixels and divided into training, validation, and testing sets using a 70:15:15 ratio. InceptionV3 generated a 2,048-dimensional deep feature representation, while LBP texture maps were processed through a shallow convolutional network to obtain 512 texture features. The resulting 2,560-dimensional representation was fused for classification. The proposed model achieved 94.15% accuracy, 94.16% precision, 94.15% recall, 94.16% F1 score, and an AUC of 0.99. On the 479 image test set, 451 images were correctly classified, including 202 Mpox and 249 Other images. The ablation study demonstrated that incorporating LBP improved accuracy from 88.72% for InceptionV3 alone to 94.15%, representing a 5.43 percentage point improvement, while AUC increased from 0.95 to 0.99. In addition, clinically sourced images from Owerri General Hospital were used to provide an independent assessment of the model on previously unseen skin lesion samples. The findings demonstrate that combining deep visual and local texture representations provides an effective approach for Mpox skin lesion classification. VL - 12 IS - 2 ER -
Department of Information Technology, Federal University of Technology, Owerri, Nigeria
Department of Information Technology, Federal University of Technology, Owerri, Nigeria
Department of Information Technology, Federal University of Technology, Owerri, Nigeria
Department of Computer Science & Information Technology, Petroleum Training Institute, Effurun, Nigeria
Information