Asynchronous federated learning for web-based OCT image analysis
Asynchronous FL via FedBuff offers a promising, privacy-preserving approach for medical image classification, particularly when synchronous participation is impractical. However, its scalability to complex classification tasks remains limited. Web-based implementations have the potential to broaden access to collaborative AI tools, but limitations of the current technologies need to be further investigated.
Authors
- Matthias Eiletz
- Abdulrahman Mohamed Selim (ORCID: https://orcid.org/0000-0002-4984-6686)
- Michael Barz (ORCID: https://orcid.org/0000-0001-6730-2466)
- Hasan Md Tusfiqur Alam (ORCID: https://orcid.org/0000-0003-1479-7690)
- Tim Maurer
- Daniel Sonntag
Institutions
- German Research Centre for Artificial Intelligence (DE)
- Saarland University (DE)
Publication Details
- Journal
- Journal of Medical Imaging
- Published
- 2026-01-05
- DOI
- https://doi.org/10.1117/1.jmi.13.1.014501
- Primary Topic
- Retinal Imaging and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 0.00