Szczegóły publikacji
Opis bibliograficzny
Validation of various normalization methods for brain tumor segmentation: can federated learning overcome this heterogeneity? / Jan Fiszer, Dominika Ciupek, Maciej MALAWSKI // W: Bridging regulatory science and medical imaging evaluation; and distributed, collaborative, and federated learning : first international workshop, BRIDGE 2025 and 6th international workshop, DeCaF 2025 held in conjunction with MICCAI 2025 : Daejeon, South Korea, September 23 and September 27, 2025 : proceedings / eds. Ghada Zamzmi [et al.]. — Cham : Springer Nature Switzerland, cop. 2026. — ( Lecture Notes in Computer Science ; ISSN 0302-9743 ; LNCS 16135 ). — ISBN: 978-3-032-05662-7; e-ISBN: 978-3-032-05663-4. — S. 121–130. — Bibliogr., Abstr. — Publikacja dostępna online od: 2025-09-25. — J. Fiszer, M. Malawski - dod. afiliacja: Sano Centre for Computational Medicine, Krakow
Autorzy (3)
- AGHFiszer Jan
- Ciupek Dominika
- AGHMalawski Maciej
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 166461 |
|---|---|
| Data dodania do BaDAP | 2026-04-13 |
| DOI | 10.1007/978-3-032-05663-4_12 |
| Rok publikacji | 2026 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Springer |
| Konferencja | Medical Image Computing and Computer-Assisted Intervention 2025 |
| Czasopismo/seria | Lecture Notes in Computer Science |
Abstract
Deep learning (DL) has been increasingly applied in medical imaging, however, it requires large amounts of data, which raises many challenges related to data privacy, storage, and transfer. Federated learning (FL) is a training paradigm that overcomes these issues, though its effectiveness may be reduced when dealing with non-independent and identically distributed (non-IID) data. This study simulates non-IID conditions by applying different MRI intensity normalization techniques to separate data subsets, reflecting a common cause of heterogeneity. These subsets are then used for training and testing models for brain tumor segmentation. The findings provide insights into the influence of the MRI intensity normalization methods on segmentation models, both training and inference. Notably, the FL methods demonstrated resilience to inconsistently normalized data across clients, achieving the 3D Dice score of 92%, which is comparable to a centralized model (trained using all data). These results indicate that FL is a solution to effectively train high-performing models without violating data privacy, a crucial concern in medical applications. The code is available at: https://github.com/SanoScience/fl-varying-normalization.
