Segmentation of Fat and Fascias in Canine Ultrasound Images

  • Oleksiy Rybakov
  • Daniel Stromer
  • Irina Mischewski
  • Andreas Maier
Conference paper
Part of the Informatik aktuell book series (INFORMAT)


The connective tissue between fat and muscle termed fascia has been of interest to the recent clinical and biological research. However, in the canine and human medicine, the anatomic knowledge is still limited. To analyze the superficial fascia in canine medicine, a database with around 200 ultrasound images of one dog has been created. The superficial fascia contains fat compartments and is closely connected to the surrounding structures such as the skin’s dermis and the epimysium of the muscles. This work proposes a semi-automatic and fully-automatic segmentation algorithm separating the different layers of ultrasound images of canine. Both algorithms were evaluated on a set of 24 expert-labeled images achieving high accuracy scores up to 95.9%.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Pope JA. Medical Physics: Imaging. Heinemann; 1999.Google Scholar
  2. 2.
    Szabo TL. Diagnostic Ultrasound Imaging: Inside Out. Academic Press Series in Biomedical Engineering. Academic Press; 2013.Google Scholar
  3. 3.
    Gonzalez RC, Woods RE, Eddins SL. Digital Image Processing using MATLAB. Upper Saddle River, NJ: Prentice Hall; 2002.Google Scholar
  4. 4.
    Nelson TR, Pretorius DH, Hull A, et al. Sources and impact of artifacts on clinical three-dimensional ultrasound imaging. Ultrasound Obstetr Gyn. 2000;16(4):374–383.Google Scholar
  5. 5.
    Boussouar A, Meziane F, Crofts G. Plantar fascia segmentation and thickness estimation in ultrasound images. Comp Med Imaging Graph. 2017;56:60–73.Google Scholar
  6. 6.
    Tomasi C, Manduchi R; IEEE. Bilateral filtering for gray and color images. Proc ICCV. 1998; p. 839–846.Google Scholar
  7. 7.
    He K, Sun J, Tang X. Guided image filtering. IEEE Trans Pattern Anal Mach Intell. 2013;35(6):1397–1409.Google Scholar
  8. 8.
    Frangi AF, Niessen WJ, Vincken KL, et al. Multiscale vessel enhancement filtering. In: Proc MICCAI. Springer; 1998. p. 130–137.Google Scholar
  9. 9.
    Heijmans HJ. Connected morphological operators for binary images. Comp Vis Image Underst. 1999;73(1):99–120.Google Scholar
  10. 10.
    Goutte C, Gaussier E; Springer. A probabilistic interpretation of precision, recall and F-score, with implication for evaluation. Proc ECIR. 2005;5:345–359.Google Scholar

Copyright information

© Springer-Verlag GmbH Deutschland 2018

Authors and Affiliations

  • Oleksiy Rybakov
    • 1
  • Daniel Stromer
    • 1
  • Irina Mischewski
    • 2
  • Andreas Maier
    • 1
  1. 1.Pattern Recognition LabFriedrich-Alexander-University Erlangen-NurembergErlangenDeutschland
  2. 2.Institut für Spezielle Zoologie und Evolutionsbiologie mit Phyletischem MuseumFriedrich-Schiller-University JenaJenaDeutschland

Personalised recommendations