Real World Federated Learning with a Knowledge Distilled Transformer for Cardiac CT Imaging
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909884958638080 |
|---|---|
| author | Tölle, Malte Garthe, Philipp Scherer, Clemens Seliger, Jan Moritz Leha, Andreas Krüger, Nina Simm, Stefan Martin, Simon Eble, Sebastian Kelm, Halvar Bednorz, Moritz André, Florian Bannas, Peter Diller, Gerhard Frey, Norbert Groß, Stefan Hennemuth, Anja Kaderali, Lars Meyer, Alexander Nagel, Eike Orwat, Stefan Seiffert, Moritz Friede, Tim Seidler, Tim Engelhardt, Sandy |
| author_facet | Tölle, Malte Garthe, Philipp Scherer, Clemens Seliger, Jan Moritz Leha, Andreas Krüger, Nina Simm, Stefan Martin, Simon Eble, Sebastian Kelm, Halvar Bednorz, Moritz André, Florian Bannas, Peter Diller, Gerhard Frey, Norbert Groß, Stefan Hennemuth, Anja Kaderali, Lars Meyer, Alexander Nagel, Eike Orwat, Stefan Seiffert, Moritz Friede, Tim Seidler, Tim Engelhardt, Sandy |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_07557 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Real World Federated Learning with a Knowledge Distilled Transformer for Cardiac CT Imaging Tölle, Malte Garthe, Philipp Scherer, Clemens Seliger, Jan Moritz Leha, Andreas Krüger, Nina Simm, Stefan Martin, Simon Eble, Sebastian Kelm, Halvar Bednorz, Moritz André, Florian Bannas, Peter Diller, Gerhard Frey, Norbert Groß, Stefan Hennemuth, Anja Kaderali, Lars Meyer, Alexander Nagel, Eike Orwat, Stefan Seiffert, Moritz Friede, Tim Seidler, Tim Engelhardt, Sandy Image and Video Processing Computer Vision and Pattern Recognition 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. |
| title | Real World Federated Learning with a Knowledge Distilled Transformer for Cardiac CT Imaging |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.07557 |