{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T11:29:33Z","timestamp":1787138973627,"version":"build-2736575974"},"reference-count":44,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T00:00:00Z","timestamp":1787097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.3390\/diagnostics16162637","type":"journal-article","created":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T11:04:12Z","timestamp":1787137452000},"page":"2637","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["FedSwin-LHTP: Structure-Aware Hessian-Inspired Token Pruning for Efficient Federated Skin Lesion Classification"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3791-4140","authenticated-orcid":false,"given":"Muhammad","family":"Awais","sequence":"first","affiliation":[{"name":"Department of Computer Science, College of Computer, Qassim University, Buraydah 52571, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Riaz Hussain","family":"Junejo","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, COMSATS University Islamabad, Wah Campus, Wah Cantt 47040, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,19]]},"reference":[{"key":"ref_1","unstructured":"American Cancer Society (2026). Melanoma Skin Cancer Survival Rates by Stage, American Cancer Society."},{"key":"ref_2","unstructured":"(1996). Health Insurance Portability and Accountability Act of 1996, United States Congress. Public Law 104-191."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Barbaria, S., Jemai, A., Ceylan, H.I., Muntean, R.I., Dergaa, I., and Boussi Rahmouni, H. (2025). Advancing Compliance with HIPAA and GDPR in Healthcare: A Blockchain-Based Strategy for Secure Data Exchange in Clinical Research Involving Private Health Information. Healthcare, 13.","DOI":"10.3390\/healthcare13202594"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1145\/3501813","article-title":"Federated Learning for Healthcare: Systematic Review and Architecture Proposal","volume":"13","author":"Antunes","year":"2022","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"579","DOI":"10.61822\/amcs-2024-0039","article-title":"An expert system for leukocyte classification using probabilistic deep feature optimization via distribution estimation","volume":"34","author":"Awais","year":"2024","journal-title":"Int. J. Appl. Math. Comput. Sci."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"166326","DOI":"10.1109\/ACCESS.2025.3612477","article-title":"Federated ViT: A Distributed Deep Learning Framework for Skin Cancer Classification","volume":"13","author":"Junejo","year":"2025","journal-title":"IEEE Access"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Domingues, M., Santos, F., and Bernardino, J. (2023). Comparing Vision Transformers and Convolutional Neural Networks for Image Classification: A Literature Review. Appl. Sci., 13.","DOI":"10.3390\/app13095521"},{"key":"ref_8","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale. arXiv."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"83048","DOI":"10.52202\/079017-2642","article-title":"QT-ViT: Improving Linear Attention in ViT with Quadratic Taylor Expansion","volume":"37","author":"Xu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Wang, H., Dedhia, B., and Jha, N.K. (2023). Zero-TPrune: Zero-Shot Token Pruning through Leveraging of the Attention Graph in Pre-Trained Transformers. arXiv.","DOI":"10.1109\/CVPR52733.2024.01521"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Kim, S., Shen, S., Thorsley, D., Gholami, A., Kwon, W., Hassoun, J., and Keutzer, K. (2022). Learned Token Pruning for Transformers. Proceedings of the KDD \u201922: 28th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, ACM.","DOI":"10.1145\/3534678.3539260"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Awais, M., Qamar, A.M., Khalid, U., and Khan, R.U. (2026). Federated Gastrointestinal Lesion Classification with Clinical-Entropy Guided Quantum-Inspired Token Pruning in Vision Transformers. Diagnostics, 16.","DOI":"10.3390\/diagnostics16071027"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., and Guo, B. (2021). Swin Transformer: Hierarchical Vision Transformer using Shifted Windows. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), IEEE.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref_14","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., and J\u00e9gou, H. (2021, January 18\u201324). Training Data-Efficient Image Transformers & Token Pruning Analysis. Proceedings of the International Conference on Machine Learning, Virtual Event."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"835","DOI":"10.1109\/JBHI.2022.3149288","article-title":"Federated machine learning for detection of skin diseases and enhancement of internet of medical things (IoMT) security","volume":"27","author":"Hossen","year":"2022","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2605","DOI":"10.1038\/s41598-024-82402-x","article-title":"Minimal sourced and lightweight federated transfer learning models for skin cancer detection","volume":"15","author":"Khullar","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Bdair, T., Navab, N., and Albarqouni, S. (2021). FedPerl: Semi-supervised peer learning for skin lesion classification. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer.","DOI":"10.1007\/978-3-030-87199-4_32"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Nazir, S., and Kaleem, M. (2023). Federated learning for medical image analysis with deep neural networks. Diagnostics, 13.","DOI":"10.3390\/diagnostics13091532"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1955","DOI":"10.1109\/TMI.2022.3233405","article-title":"Fedmix: Mixed supervised federated learning for medical image segmentation","volume":"42","author":"Wicaksana","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2364145","DOI":"10.1080\/08839514.2024.2364145","article-title":"Effective skin cancer diagnosis through federated learning and deep convolutional neural networks","volume":"38","author":"Alqahtani","year":"2024","journal-title":"Appl. Artif. Intell."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Fan, S., Ahmed, A., Zeng, X., Xi, R., and Hou, M. (2025). A personalized multimodal federated learning framework for skin cancer diagnosis. Electronics, 14.","DOI":"10.3390\/electronics14142880"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1804","DOI":"10.1109\/TMI.2023.3348982","article-title":"Model-Heterogeneous Semi-Supervised Federated Learning for Medical Image Segmentation","volume":"43","author":"Ma","year":"2024","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"921","DOI":"10.1007\/s44174-025-00434-x","article-title":"SkinFLNet: A federated learning approach for skin cancer detection utilizing skin dermoscopy images","volume":"4","author":"Saha","year":"2026","journal-title":"Biomed. Mater. Devices"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Yaqoob, M.M., Alsulami, M., Khan, M.A., Alsadie, D., Saudagar, A.K.J., and AlKhathami, M. (2023). Federated machine learning for skin lesion diagnosis: An asynchronous and weighted approach. Diagnostics, 13.","DOI":"10.3390\/diagnostics13111964"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"75","DOI":"10.54254\/2755-2721\/49\/20241065","article-title":"Federated learning algorithm-based skin cancer detection","volume":"49","author":"Hu","year":"2024","journal-title":"Appl. Comput. Eng."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"111347","DOI":"10.1016\/j.compbiomed.2025.111347","article-title":"Med-VCD: Mitigating hallucination for medical large vision language models through visual contrastive decoding","volume":"200","author":"Mahdavi","year":"2026","journal-title":"Comput. Biol. Med."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"114045","DOI":"10.1016\/j.asoc.2025.114045","article-title":"Medical image classification with KAN-integrated transformers and dilated neighborhood attention","volume":"186","author":"Manzari","year":"2025","journal-title":"Appl. Soft Comput."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"100302","DOI":"10.1016\/j.hcc.2025.100302","article-title":"FedViTBloc: Secure and privacy-enhanced medical image analysis with federated vision transformer and blockchain","volume":"5","author":"Amaizu","year":"2025","journal-title":"High-Confid. Comput."},{"key":"ref_29","first-page":"1177","article-title":"A Custom Federated Weighted Learning Model for Melanoma Detection Using Deep Neural Networks","volume":"30","author":"Jewalikar","year":"2025","journal-title":"Ing. Syst. D\u2019Inf."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Arshed, M.A., Mumtaz, S., Ibrahim, M., Ahmed, S., Tahir, M., and Shafi, M. (2023). Multi-class skin cancer classification using vision transformer networks and convolutional neural network-based pre-trained models. Information, 14.","DOI":"10.3390\/info14070415"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"24559","DOI":"10.1007\/s11227-024-06309-0","article-title":"Convolutional neural network (CNN) and federated learning-based privacy preserving approach for skin disease classification","volume":"80","author":"Divya","year":"2024","journal-title":"J. Supercomput."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"40114","DOI":"10.1109\/ACCESS.2024.3374650","article-title":"Federated learning approach for breast cancer detection based on DCNN","volume":"12","author":"AlSalman","year":"2024","journal-title":"IEEE Access"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Mendon\u00e7a, T., Ferreira, P.M., Marques, J.S., Mar\u00e7al, A.R.S., and Rozeira, J. (2013). PH2: A dermoscopic image database for research and benchmarking. Proceedings of the 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), IEEE.","DOI":"10.1109\/EMBC.2013.6610779"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Huang, H.Y., Nagisetti, Y., Mukundan, A., Karmarkar, R., Libu, S.A., Liu, T.Y., and Wang, H.C. (2026). SAVE: Spectrum-Aided Visual Enhancement for AI-Based Skin Cancer Detection. Diagnostics, 16.","DOI":"10.3390\/diagnostics16121864"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"9619079","DOI":"10.1155\/2021\/9619079","article-title":"A Computer-Aided Diagnosis System Using Deep Learning for Multiclass Skin Lesion Classification","volume":"2021","author":"Arshad","year":"2021","journal-title":"Comput. Intell. Neurosci."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1007\/s10489-024-05990-1","article-title":"QEFS: A novel plant disease prediction approach using quantum-inspired evolutionary feature selection","volume":"55","author":"Anand","year":"2025","journal-title":"Appl. Intell."},{"key":"ref_37","first-page":"13937","article-title":"Dynamicvit: Efficient vision transformers with dynamic token sparsification","volume":"34","author":"Rao","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"180161","DOI":"10.1038\/sdata.2018.161","article-title":"The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions","volume":"5","author":"Tschandl","year":"2018","journal-title":"Sci. Data"},{"key":"ref_39","unstructured":"(2026, August 09). ISIC 2019: A Challenge Dataset for Lesion Diagnosis. In Proceedings of the International Skin Imaging Collaboration (ISIC) 2019 Challenge; Dermatology Image Dataset for Multi-Class Skin Lesion Classification. Available online: https:\/\/challenge.isicarchive.com\/data\/#2019."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Kang, Y., Shi, Y., Wen, M., He, J., Yang, J., Xue, Z., Feng, J., and Liu, X. (2025). SwiftPrune: Hessian-Free Weight Pruning for Large Language Models. Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, Association for Computational Linguistics.","DOI":"10.18653\/v1\/2025.findings-emnlp.690"},{"key":"ref_41","unstructured":"Kay, S.M. (1993). Statistical Signal Processing: Estimation Theory, Prentice Hall. Chapter\u20133."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"81004","DOI":"10.1109\/ACCESS.2024.3410026","article-title":"FedArtML: A Tool to Facilitate the Generation of Non-IID Datasets in a Controlled Way to Support Federated Learning Research","volume":"12","author":"Gutierrez","year":"2024","journal-title":"IEEE Access"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"130937","DOI":"10.1016\/j.eswa.2025.130937","article-title":"FedLSC: Federated Learning with Layer Similarity Comparison for Cross-Institutional Skin Cancer Image Classification","volume":"306","author":"Liu","year":"2026","journal-title":"Expert Syst. Appl."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"130417","DOI":"10.1016\/j.neucom.2025.130417","article-title":"Vision Transformers on the Edge: A Comprehensive Survey of Model Compression and Acceleration Strategies","volume":"643","author":"Saha","year":"2025","journal-title":"Neurocomputing"}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/16\/2637\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T11:19:24Z","timestamp":1787138364000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/16\/2637"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,19]]},"references-count":44,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["diagnostics16162637"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16162637","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,19]]}}}