Journal of Machine and Computing


MetaFusion-FL: A Cross Modality Federated Meta Learning Framework for Robust and Explainable Healthcare System



Journal of Machine and Computing

Received On : 02 April 2025

Revised On : 28 May 2025

Accepted On : 16 June 2025

Published On : 05 July 2025

Volume 05, Issue 03

Pages : 1787-1802


Abstract


Mpox is a re-emerging zoonotic viral disease that attracted the attention of the whole world because of its spreading transmission and clinical similarity with other skin diseases. It is highly important that this identification is fast and accurate, even in remotely located areas or resource-limited settings. However, the conventional centralized deep learning models exhibit severe limitations regarding data privacy, modality variation, and scalability across varied clinical environments. To this end, this paper presents MetaFusion-FL, a new federated meta-learning framework that combines cross-modality image analysis based on a hybrid Transformer-Capsule model with Hierarchical Attention-Based Multimodal Fusion (HAMFM). The model can work on multi-source images as input, namely smartphone images, dermoscopic images, and clinical images, which are processed locally at edge hospitals without raw data transmission. Reptile federated meta-learning strategy guarantees quick personalization of models and global generalization. When evaluated on a wide dataset, MetaFusion-FL has a higher classification accuracy of 99.46%, precision of 99.52%, recall of 99.40%, and F1-score of 99.46% compared to other current models, including ViT-RLXGBFL (99.12%) and ResViT-FLBoost (98.78%). The framework is also resistant to image noise and is consistent and stable across federated clients. Besides, SHAP and Grad-CAM++ explanations are used to ensure interpretability in a clinical context. MetaFusion-FL is therefore a leap in the development of AI-based, privacy-preserving, and generalizable skin disease classification, particularly Mpox.


Keywords


Mpox Detection, Cross-Modality, Federated Learning, Meta-Learning, Capsule Network, Transformer, Medical Imaging, Multimodal Fusion.


  1. S. Krumova et al., “Monkeypox in Bulgaria: Significance of Various Clinical Samples, Clinical Manifestation, and Molecular Detection,” Journal of Clinical Medicine, vol. 13, no. 16, p. 4856, Aug. 2024, doi: 10.3390/jcm13164856.
  2. J. Calabria de Araujo, A. P. A. Carvalho, C. D. Leal, M. Natividade, M. Borin, A. Guerra, N. Carobin, A. Sabino, M. Almada, M. Costa, F. C. M. Saia, L. V. Frutuoso, F. C. M. Iani, T. Adelino, V. Fonseca, M. Giovanetti, & L. C. J. Alcantara, “Detection of Multiple Human Viruses, including Mpox, Using a Wastewater Surveillance Approach in Brazil. Pathogens,” 13(7), 589, (2024), DOI: 10.3390/pathogens13070589.
  3. R. Rossotti, D. Calzavara, M. Cernuschi, F. D’Amico, A. De Bona, R. Repossi, D. Moschese, S. Bossolasco, A. Tavelli, C. Muccini, G. Mulé, & A. d’Arminio Monforte, “Detection of Asymptomatic Mpox Carriers among High-Ri Men Who Have Sex with Men: A Prospective Analysis,” Pathogens, 12(6), 798, (2023), Doi: 10.3390/pathogens12060798.
  4. S. Kumar, D. Guruparan, K. Karuppanan, & K. J. S. Kumar, “Comprehensive Insights into Monkeypox (mpox): Recent Advances in Epidemiology, Diagnostic Approaches and Therapeutic Strategies,” Pathogens, 14(1), 1, (2025), DOI: 10.3390/pathogens14010001.
  5. E. Kinganda-Lusamaki, L. K. Baketana, E. Ndomba-Mukanya, J. Bouillin, G. Thaurignac, A. A. Aziza, G. Luakanda-Ndelemo, N. F. Nuñez, T. Kalonji-Mukendi, E. S. Pukuta, A. Nkuba-Ndaye, E. L. Lofiko, E. M. Kibungu, R. S. Lushima, A. Ayouba, P. Mbala-Kingebeni, J.-J. Muyembe-Tamfum, E. Delaporte, M. Peeters, & S. Ahuka-Mundeke, “Use of Mpox Multiplex Serology in the Identification of Cases and Outbreak Investigations in the Democratic Republic of the Congo (DRC),” Pathogens, 12(7), 916, (2023), DOI: 10.3390/pathogens12070916.
  6. M. Patel et al., “Current Insights into Diagnosis, Prevention Strategies, Treatment, Therapeutic Targets, and Challenges of Monkeypox (Mpox) Infections in Human Populations,” Life, vol. 13, no. 1, p. 249, Jan. 2023, doi: 10.3390/life13010249.
  7. N. Thakur, Y. N. Duggal, and Z. Liu, “Analyzing Public Reactions, Perceptions, and Attitudes during the MPox Outbreak: Findings from Topic Modeling of Tweets,” Computers, vol. 12, no. 10, p. 191, Sep. 2023, doi: 10.3390/computers12100191.
  8. S. Asif, M. Zhao, Y. Li, F. Tang, S. Ur Rehman Khan, and Y. Zhu, “AI-Based Approaches for the Diagnosis of Mpox: Challenges and Future Prospects,” Archives of Computational Methods in Engineering, vol. 31, no. 6, pp. 3585–3617, Mar. 2024, doi: 10.1007/s11831-024-10091-w.
  9. N. Atceken, I. Bayaki, B. Can, D. Yigci, and S. Tasoglu, “Mpox disease, diagnosis, and point of care platforms,” Bioengineering & Translational Medicine, vol. 10, no. 3, Jan. 2025, doi: 10.1002/btm2.10733.
  10. T. Bunse et al., “Analytical and clinical evaluation of a novel real-time PCR-based detection kit for Mpox virus,” Medical Microbiology and Immunology, vol. 213, no. 1, Aug. 2024, doi: 10.1007/s00430-024-00800-4.
  11. F. Zhao et al., “A field diagnostic method for rapid and sensitive detection of mpox virus,” Journal of Medical Virology, vol. 96, no. 2, Feb. 2024, doi: 10.1002/jmv.29469.
  12. M. L. Cavuto et al., “Portable molecular diagnostic platform for rapid point-of-care detection of mpox and other diseases,” Nature Communications, vol. 16, no. 1, Mar. 2025, doi: 10.1038/s41467-025-57647-3.
  13. Y. Zong et al., “Ocular Manifestations of Mpox and Other Poxvirus Infections: Clinical Insights and Emerging Therapeutic and Preventive Strategies,” Vaccines, vol. 13, no. 5, p. 546, May 2025, doi: 10.3390/vaccines13050546.
  14. S. Aggarwal, P. Agarwal, K. Nigam, N. Vijay, P. Yadav, and N. Gupta, “Mapping the Landscape of Health Research Priorities for Effective Pandemic Preparedness in Human Mpox Virus Disease,” Pathogens, vol. 12, no. 11, p. 1352, Nov. 2023, doi: 10.3390/pathogens12111352.
  15. F. M. Liotti et al., “Performance of a Novel Real-Time PCR-Based Assay for Rapid Monkeypox Virus Detection in Human Samples,” Microorganisms, vol. 11, no. 10, p. 2513, Oct. 2023, doi: 10.3390/microorganisms11102513.
  16. M. A. Garcia-Junior et al., “Oral Infection, Oral Pathology and Salivary Diagnostics of Mpox Disease: Relevance in Dentistry and OMICs Perspectives,” International Journal of Molecular Sciences, vol. 24, no. 18, p. 14362, Sep. 2023, doi: 10.3390/ijms241814362.
  17. M. A. Zinnah et al., “The Re-Emergence of Mpox: Old Illness, Modern Challenges,” Biomedicines, vol. 12, no. 7, p. 1457, Jul. 2024, doi: 10.3390/biomedicines12071457.
  18. S. Vuran, M. Ucan, M. Akin, & M. Kaya, “Multi-Classification of Skin Lesion Images Including Mpox Disease Using Transformer-Based Deep Learning Architectures,” Diagnostics, 15(3), 2025, DOI: 10.3390/diagnostics15030374.
  19. N. Kamaratos-Sevdalis, I. Kourampi, N. B. Ozturk, A. C. Mavromanoli, and C. Tsagkaris, “Mpox and Surgery: Protocols, Precautions, and Recommendations,” Microorganisms, vol. 12, no. 9, p. 1900, Sep. 2024, doi: 10.3390/microorganisms12091900.
  20. F. Mohamed Abdoul-Latif et al., “Mpox Resurgence: A Multifaceted Analysis for Global Preparedness,” Viruses, vol. 16, no. 11, p. 1737, Nov. 2024, doi: 10.3390/v16111737.

CRediT Author Statement


The authors confirm contribution to the paper as follows:

Conceptualization: Kalphana K R, Maheskumar V, Vijayarajeswari R and Sasikala K; Methodology: Kalphana K R and Maheskumar V; Software: Vijayarajeswari R and Sasikala K; Data Curation: Kalphana K R and Maheskumar V; Writing- Original Draft Preparation: Kalphana K R, Maheskumar V, Vijayarajeswari R and Sasikala K; Visualization: Vijayarajeswari R and Sasikala K; Investigation: Kalphana K R and Maheskumar V; Supervision: Vijayarajeswari R and Sasikala K; Validation: Kalphana K R and Maheskumar V; Writing- Reviewing and Editing: Kalphana K R, Maheskumar V, Vijayarajeswari R and Sasikala K; All authors reviewed the results and approved the final version of the manuscript.


Acknowledgements


The author(s) received no financial support for the research, authorship, and/or publication of this article.


Funding


No funding was received to assist with the preparation of this manuscript.


Ethics declarations


Conflict of interest

The authors have no conflicts of interest to declare that are relevant to the content of this article.


Availability of data and materials


Data sharing is not applicable to this article as no new data were created or analysed in this study.


Author information


Contributions

All authors have equal contribution in the paper and all authors have read and agreed to the published version of the manuscript.


Corresponding author


Rights and permissions


Open Access This article is licensed under a Creative Commons Attribution NoDerivs is a more restrictive license. It allows you to redistribute the material commercially or non-commercially but the user cannot make any changes whatsoever to the original, i.e. no derivatives of the original work. To view a copy of this license, visit https://creativecommons.org/licenses/by-nc-nd/4.0/


Cite this article


Kalphana K R, Maheskumar V, Vijayarajeswari R and Sasikala K, “MetaFusion-FL: A Cross Modality Federated Meta Learning Framework for Robust and Explainable Healthcare System”, Journal of Machine and Computing, vol.5, no.3, pp. 1787-1802, July 2025, doi: 10.53759/7669/jmc202505141.


Copyright


© 2025 Kalphana K R, Maheskumar V, Vijayarajeswari R and Sasikala K. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.