Deep learning-based mediastinal lymph node assessment on PET/CT images without pixel-level annotations
The division of the problem setting into subtasks as well as the integration of prior knowledge enables better or comparable performance of models trained with and without segmentation masks.
Authors
- Daniel Drömann (ORCID: https://orcid.org/0000-0002-5878-8887)
- Yannic Elser
- Sofija Engelson (ORCID: https://orcid.org/0009-0007-2493-8107)
- Stefanie Schierholz
- Jan Ehrhardt
- Malte Maria Sieren
- H. Handels
- Julia Andresen
- Jörg Barkhausen
- Tobias Keck
Institutions
- University Hospital Schleswig-Holstein (DE)
- University of Lübeck (DE)
Publication Details
- Journal
- Journal of Medical Imaging
- Published
- 2026-02-18
- DOI
- https://doi.org/10.1117/1.jmi.13.1.014507
- Primary Topic
- Medical Imaging Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00