From Unlabeled Data to Clinical Applications: Foundation Models in Medical Imaging

Scheuplein J, Rohleder M, Kreher BW, Maier A (2026)

Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2026

Publisher: EasyChair

Series: EPiC Series in Health Sciences

Book Volume: 8

Pages Range: 152-155

Conference Proceedings Title: Proceedings of The 25th Annual Meeting of the International Society for Computer Assisted Orthopaedic Surgery

Event location: Davos CH

DOI: 10.29007/h2m6

Abstract

The performance of deep learning algorithms is highly dependent on the quantity and diversity of the available training data. However, obtaining sufficiently large datasets represents a significant challenge, particularly in the field of medical imaging. This study underscores the potential of self-supervised training strategies in the development of deep learning models for medical imaging tasks. It is demonstrated that workflows can be significantly optimized by incorporating the feature content of a large collection of medical X-ray images from intraoperative C-arm scans into a so-called foundation model. This approach facilitates the efficient adaptation to a variety of concrete applications by fine-tuning a small task-specific head network on top of the pre-trained foundation model, thereby reducing both computational demands and training time.

Authors with CRIS profile

Joshua Scheuplein Lehrstuhl für Informatik 5 (Mustererkennung) Maximilian Rohleder Lehrstuhl für Informatik 5 (Mustererkennung) Andreas Maier Lehrstuhl für Informatik 5 (Mustererkennung)

Involved external institutions

Siemens Healthineers (Germany) DE Germany (DE)

How to cite

APA:

Scheuplein, J., Rohleder, M., Kreher, B.W., & Maier, A. (2026). From Unlabeled Data to Clinical Applications: Foundation Models in Medical Imaging. In Joshua William Giles, Aziliz Guezou-Philippe (Eds.), Proceedings of The 25th Annual Meeting of the International Society for Computer Assisted Orthopaedic Surgery (pp. 152-155). Davos, CH: EasyChair.

MLA:

Scheuplein, Joshua, et al. "From Unlabeled Data to Clinical Applications: Foundation Models in Medical Imaging." Proceedings of the CAOS 2025: The 25th Annual Meeting of the International Society for Computer Assisted Orthopaedic Surgery, Davos Ed. Joshua William Giles, Aziliz Guezou-Philippe, EasyChair, 2026. 152-155.

BibTeX: Download