FL-W3S: Cross-domain federated learning for weakly supervised semantic segmentation of white blood cells
The combination of federated learning for collaborative model training while preserving data privacy, alongside white blood cell segmentation techniques for precise cell identification, enhances diagnostic accuracy and personalized treatment strategies in clinical applications, particularly in hematology and pathology. More specifically, it involves isolating white blood cell from blood smear for further analysis such as automated blood cell counting, morphological analysis, cell classification, disease diagnosis and monitoring.
Authors
- Silvia Zottin (ORCID: https://orcid.org/0000-0003-0820-7260)
- Rao Muhammad Umer (ORCID: https://orcid.org/0000-0001-6179-5829)
- Carsten Marr (ORCID: https://orcid.org/0000-0003-2154-4552)
- Hussain Ahmad Madni (ORCID: https://orcid.org/0000-0003-1227-524X)
- Gian Luca Foresti (ORCID: https://orcid.org/0000-0002-8425-6892)
Institutions
- University of Udine (IT)
- Helmholtz Zentrum München (DE)
Publication Details
- Journal
- International Journal of Medical Informatics
- Published
- 2025-01-23
- DOI
- https://doi.org/10.1016/j.ijmedinf.2025.105806
- Citations
- 9
- Primary Topic
- Digital Imaging for Blood Diseases
- Type
- article
- Field-Weighted Citation Impact
- 11.48
Funders
- Università degli Studi di Udine
- Helmholtz Zentrum München