EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

FedSwin-LHTP: Structure-Aware Hessian-Inspired Token Pruning for Efficient Federated Skin Lesion Classification

Muhammad Awais iD, Riaz Hussain Junejo

Diagnostics · 19.08.2026 · 16 (16) · 2637

DOI: 10.3390/diagnostics16162637 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 19.08.2026. Verfasst von Muhammad Awais und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, College of Computer, Qassim University, Buraydah 52571, Saudi Arabia. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Skin cancer encompasses a diverse range of malignancies and remains a significant global health challenge. Accurate machine-learning-assisted diagnosis can substantially improve patient outcomes through early detection and timely clinical intervention. Federated Learning (FL) enables privacy-preserving collaborative model training across multiple healthcare institutions while ensuring that sensitive patient data remain decentralized. However, deploying advanced architectures such as Vision Transformers (ViTs) in clinical environments is challenging due to the high computational demands of self-attention mechanisms.

Methods

This work proposes FedSwin-LHTP, an efficient federated learning framework for skin lesion classification that integrates a Swin Transformer backbone with a Lightweight Hessian-Inspired Token Pruning (LHTP) mechanism. LHTP estimates token importance using a second-order Taylor approximation around converged local model parameters to identify less informative patch tokens, enabling the early pruning of redundant representations without explicitly computing the Hessian matrix. Furthermore, the framework incorporates the FedProx optimization objective to mitigate client drift under heterogeneous non-IID data distributions. The proposed framework is evaluated on the HAM10000 and ISIC datasets under realistic non-IID federated settings.

Results

Experimental results demonstrate stable convergence, effective knowledge aggregation, and robust diagnostic discrimination across distributed clients. By adaptively pruning approximately 60% of Stage-1 tokens, the proposed framework substantially reduces the computational burden of local transformer processing while maintaining high multiclass classification performance, achieving an accuracy of up to 96.1% on the evaluated datasets.

Conclusions

These results highlight the potential of FedSwin-LHTP as a practical, privacy-preserving, and resource-efficient solution for collaborative healthcare intelligence.

Schlagwörter

Stichwörter der Autor:innen

AIcomputer visiondeep learningfederated learningmedical imagingoptimizationvision transformers

Autor:innen und Institutionen

  • Department of Computer Science, College of Computer, Qassim University, Buraydah 52571, Saudi Arabia.
  • Department of Computer Engineering, COMSATS University Islamabad, Wah Campus, Wah Cantt 47040, Pakistan.

ORCID-Profile: Muhammad Awais

Zitieren

APA

Awais, M., & Junejo, R. H. (2026). FedSwin-LHTP: Structure-Aware Hessian-Inspired Token Pruning for Efficient Federated Skin Lesion Classification. Diagnostics, 16(16), 2637. https://doi.org/10.3390/diagnostics16162637

Vancouver

Awais M, Junejo RH. FedSwin-LHTP: Structure-Aware Hessian-Inspired Token Pruning for Efficient Federated Skin Lesion Classification. Diagnostics. 2026;16(16):2637. doi:10.3390/diagnostics16162637

BibTeX
@article{Awais2026,
  author = {Awais, Muhammad and Junejo, Riaz Hussain},
  title = {FedSwin-LHTP: Structure-Aware Hessian-Inspired Token Pruning for Efficient Federated Skin Lesion Classification},
  journal = {Diagnostics},
  year = {2026},
  volume = {16},
  number = {16},
  pages = {2637},
  doi = {10.3390/diagnostics16162637}
}
Kostenlos starten →