Font Augmentation

Implant and Surgical Tool Simulation for X-Ray Image Processing
  • Florian KordonEmail author
  • Andreas Maier
  • Benedict Swartman
  • Holger Kunze
Conference paper
Part of the Informatik aktuell book series (INFORMAT)


This study investigates a novel data augmentation approach for simulating surgical instruments, tools, and implants by image composition with transformed characters, numerals, and abstract symbols from open-source fonts. We analyse its suitability for the common spatial learning tasks of multi-label segmentation and anatomical landmark detection. The proposed technique is evaluated on 38 clinical intraoperative X-ray images with a high occurrence of objects overlaying the target anatomy. We demonstrate increased robustness towards superimposed surgical objects by incorporating our technique and provide an empirical rationale about the neglectable influence of realistic object shape and intensity information.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Keil H, Beisemann N, Swartman B, et al. Intra-operative imaging in trauma surgery. EFORT Open Reviews. 2018;3(10):541–549.Google Scholar
  2. 2.
    Hosny A, Parmar C, Quackenbush J, et al. Artificial intelligence in radiology. Nature Reviews Cancer. 2018;18(8):500–510.Google Scholar
  3. 3.
    Oktay O, Ferrante E, Kamnitsas K, et al. Anatomically constrained neural networks (ACNNs): Application to cardiac image enhancement and segmentation. IEEE Trans Med Imaging. 2018;37(2):384–395.Google Scholar
  4. 4.
    Unberath M, Zaech J, Lee S, et al. DeepDRR – A catalyst for machine learning in uoroscopy-guided procedures. Proc MICCAI. 2018; p. 98–106.Google Scholar
  5. 5.
    Gao C, Unberath M, Taylor R, et al. Localizing dexterous surgical tools in x-ray for image-based navigation. arXiv preprint. 2019; p. 98–106.Google Scholar
  6. 6.
    Kordon F, Lasowski R, Swartman B, et al. Improved x-ray bone segmentation by normalization and augmentation strategies. Proc BVM. 2019; p. 104–109.Google Scholar
  7. 7.
    Kordon F, Fischer P, Privalov M, et al. Multi-task localization and segmentation for x-ray guided planning in knee surgery. Proc Med Image Comput Comput Assist Interv. 2019; p. 622–630.Google Scholar
  8. 8.
    Ghiasi G, Lin T, Le Q. DropBlock: A regularization method for convolutional networks. Proceedings of the 32nd International Conference on Neural Information Processing Systems. 2018; p. 10750–10760.Google Scholar
  9. 9.
    Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation. Proc MICCAI. 2015;9351:234–241.Google Scholar

Copyright information

© Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature 2020

Authors and Affiliations

  • Florian Kordon
    • 1
    • 2
    • 3
    Email author
  • Andreas Maier
    • 1
  • Benedict Swartman
    • 4
  • Holger Kunze
    • 3
  1. 1.Pattern Recognition Lab, Department of Computer ScienceFriedrich-Alexander-Universität Erlangen-NürnbergErlangenDeutschland
  2. 2.Erlangen Graduate School in Advanced Optical Technologies (SAOT)Friedrich-Alexander-Universität Erlangen-NürnbergErlangenDeutschland
  3. 3.Advanced TherapiesSiemens Healthcare GmbHForchheimDeutschland
  4. 4.Department for Trauma and Orthopaedic SurgeryBG Trauma Center LudwigshafenLudwigshafenDeutschland

Personalised recommendations