DINO Adapted to X-Ray (DAX): Foundation Models for Intraoperative X-Ray Imaging

Scheuplein J, Rohleder M, Maier A, Kreher BW (2025)

Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Subtype: other

Publication year: 2025

Publisher: Springer Nature Switzerland

Series: Lecture Notes in Computer Science (LNCS)

City/Town: Cham

Book Volume: 15969

Pages Range: 138-148

Conference Proceedings Title: Medical Image Computing and Computer Assisted Intervention - MICCAI 2025

Event location: Daejeon KR

ISBN: 978-3-032-05127-1

DOI: 10.1007/978-3-032-05127-1_14

Abstract

Intraoperative X-ray imaging represents a key technology for guiding orthopedic interventions. Recent advancements in deep learning have enabled automated image analysis in this field, thereby streamlining clinical workflows and enhancing patient outcomes. However, many existing approaches depend on task-specific models and are constrained by the limited availability of annotated data. In contrast, self-supervised foundation models have exhibited remarkable potential to learn robust feature representations without label annotations. In this paper, we introduce DINO Adapted to X-ray (DAX), a novel framework that adapts DINO for training foundational feature extraction backbones tailored to intraoperative X-ray imaging. Our approach involves pre-training on a novel dataset comprising over 632,000 image samples, which surpasses other publicly available datasets in both size and feature diversity. To validate the successful incorporation of relevant domain knowledge into our DAX models, we conduct an extensive evaluation of all backbones on three distinct downstream tasks and demonstrate that small head networks can be trained on top of our frozen foundation models to successfully solve applications regarding (1) body region classification, (2) metal implant segmentation, and (3) screw object detection. The results of our study underscore the potential of the DAX framework to facilitate the development of robust, scalable, and clinically impactful deep learning solutions for intraoperative X-ray image analysis. Source code and model checkpoints are available at https://github.com/JoshuaScheuplein/DAX.

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 DE Germany (DE)

How to cite

APA:

Scheuplein, J., Rohleder, M., Maier, A., & Kreher, B.W. (2026). DINO Adapted to X-Ray (DAX): Foundation Models for Intraoperative X-Ray Imaging. In Gee JC, Alexander DC, Hong J, Iglesias JE, Sudre CH, Venkataraman A, Golland P, Kim JH, Park J (Eds.), Medical Image Computing and Computer Assisted Intervention - MICCAI 2025 (pp. 138-148). Daejeon, KR: Cham: Springer Nature Switzerland.

MLA:

Scheuplein, Joshua, et al. "DINO Adapted to X-Ray (DAX): Foundation Models for Intraoperative X-Ray Imaging." Proceedings of the 28th International Conference on Medical Image Computing and Computer Assisted Intervention, Daejeon Ed. Gee JC, Alexander DC, Hong J, Iglesias JE, Sudre CH, Venkataraman A, Golland P, Kim JH, Park J, Cham: Springer Nature Switzerland, 2026. 138-148.

BibTeX: Download