Cover Image

Real world federated learning with a knowledge distilled transformer for cardiac CT imaging

Federated learning is a renowned technique for utilizing decentralized data while preserving privacy. However, real-world applications often face challenges like partially labeled datasets, where only a few locations have certain expert annotations, leaving large portions of unlabeled data unused. L...

Full description

Saved in:
Bibliographic Details
Main Authors: Tölle, Malte (Author) , Garthe, Philipp (Author) , Scherer, Clemens (Author) , Seliger, Jan Moritz (Author) , Leha, Andreas (Author) , Krüger, Nina (Author) , Simm, Stefan (Author) , Martin, Simon (Author) , Eble, Sebastian (Author) , Kelm, Halvar (Author) , Bednorz, Moritz (Author) , André, Florian (Author) , Bannas, Peter (Author) , Diller, Gerhard (Author) , Frey, Norbert (Author) , Groß, Stefan (Author) , Hennemuth, Anja (Author) , Kaderali, Lars (Author) , Meyer, Alexander (Author) , Nagel, Eike (Author) , Orwat, Stefan (Author) , Seiffert, Moritz (Author) , Friede, Tim (Author) , Seidler, Tim (Author) , Engelhardt, Sandy (Author)
Format: Article (Journal)
Language:English
Published: 06 February 2025
In: npj digital medicine
Year: 2025, Volume: 8, Pages: 1-14
ISSN:2398-6352
DOI:10.1038/s41746-025-01434-3
Online Access:Verlag, kostenfrei, Volltext: https://doi.org/10.1038/s41746-025-01434-3
Verlag, kostenfrei, Volltext: https://www.nature.com/articles/s41746-025-01434-3
Get full text
Author Notes:Malte Tölle, Philipp Garthe, Clemens Scherer, Jan Moritz Seliger, Andreas Leha, Nina Krüger, Stefan Simm, Simon Martin, Sebastian Eble, Halvar Kelm, Moritz Bednorz, Florian André, Peter Bannas, Gerhard Diller, Norbert Frey, Stefan Groß, Anja Hennemuth, Lars Kaderali, Alexander Meyer, Eike Nagel, Stefan Orwat, Moritz Seiffert, Tim Friede, Tim Seidler & Sandy Engelhardt
Description
Summary:Federated learning is a renowned technique for utilizing decentralized data while preserving privacy. However, real-world applications often face challenges like partially labeled datasets, where only a few locations have certain expert annotations, leaving large portions of unlabeled data unused. Leveraging these could enhance transformer architectures’ ability in regimes with small and diversely annotated sets. We conduct the largest federated cardiac CT analysis to date (n = 8, 104) in a real-world setting across eight hospitals. Our two-step semi-supervised strategy distills knowledge from task-specific CNNs into a transformer. First, CNNs predict on unlabeled data per label type and then the transformer learns from these predictions with label-specific heads. This improves predictive accuracy and enables simultaneous learning of all partial labels across the federation, and outperforms UNet-based models in generalizability on downstream tasks. Code and model weights are made openly available for leveraging future cardiac CT analysis.
Item Description:Gesehen am 05.08.2025
Physical Description:Online Resource
ISSN:2398-6352
DOI:10.1038/s41746-025-01434-3

Similar Items