Enhanced ensemble model-based approach from deep learning for MonkeyPox detection using medical image

Author Identifier (ORCID)

Laizah Sashah Mutasa: https://orcid.org/0000-0003-1377-2862

Abstract

Monkeypox, commonly known as “Mpox,” is a viral disease caused by an orthopoxviral that spreads through contact with affected persons. Mpox causes painful rashes, leaves scars after treatment, enlarges lymph nodes with fever, and causes severe sickness, headache, and muscle aches which are not limited to these symptoms. The treatment of Mpox can effectively be done through supportive care for major symptoms such as pain and fever with good nutrition and a balanced diet, hydration, proper skin care, and deterrence of secondary infections and treatment. A deep learning concept specifically ResNet-50, EfficientNetB0, and MobileNetv2 is utilized for this study to detect Mpox using medical images. The MobileNetV2, ResNet-50, and EfficientNetB0 were combined to develop an enhanced ensemble model to boost the models’ performance. The method utilized is segmented into two distinct yet interconnected phases. The first phase concentrates on deep learning model development, encompassing key steps such as meticulous dataset preparation, thoughtful model design, rigorous training processes, and thorough performance evaluations. The model design phase involved selecting appropriate architectures and hyperparameters tailored to the specific characteristics of the monkeypox imaging data. The study’s results illustrate the trade-offs between accuracy, robustness, and computational efficiency. While ResNet-50 stands out for its accuracy, the ensemble model offers consistent performance across datasets, and EfficientNetB0 and MobileNetV2 provide scalable solutions for low-resource environments. Collectively, these models demonstrate the transformative potential of deep learning in enhancing monkeypox diagnosis, offering scalable and reliable tools for clinical and public health applications. These findings emphasize the potential of deep learning to revolutionize infectious disease diagnostics, paving the way for scalable, accurate, and efficient tools in healthcare.

Document Type

Conference Proceeding

Date of Publication

1-1-2026

Volume

2723 CCIS

Publication Title

Communications in Computer and Information Science

Publisher

Springer

School

School of Business and Law

RAS ID

88777

Comments

Asare, A., Asare, J. W., Ujakpa, M. M., Kyei, E. A., Mutasa, L. S., Freeman, E., Brown-Acquaye, W. L., & Lempogo, F. (2026). Enhanced ensemble model-based approach from deep learning for MonkeyPox detection using medical image. In Communications in Computer and Information Science (Vol. 2723, pp. 166–189). Springer. https://doi.org/10.1007/978-3-032-13056-3_14

Copyright

subscription content

First Page

166

Last Page

189

Share

 
COinS
 

Link to publisher version (DOI)

10.1007/978-3-032-13056-3_14