Advertisement

Smooth Ride: Low-Pass Filtering of Manual Segmentations Improves Consensus

  • Jennifer MaierEmail author
  • Marianne Black
  • Mary Hall
  • Jang-Hwan Choi
  • Marc Levenston
  • Garry Gold
  • Rebecca Fahrig
  • Bjoern Eskofier
  • Andreas Maier
Conference paper
Part of the Informatik aktuell book series (INFORMAT)

Zusammenfassung

In this paper, we investigate slice-wise manual segmentation of knee anatomy. Due to high inter-rater variability between annotators, often a high number of raters is required to obtain a reliable ground truth consensus. We conducted an extensive study in which cartilage surface was segmented manually by six annotators on three scans of the knee. The slice-wise annotation results in high-frequency artifact that can be reduced by averaging over the segmentations of the annotators. A similar effect can also be obtained by smoothing the surface using low-pass filtering. In our results, we demonstrate that such filtering increases the consistency of the annotation of all raters. Furthermore, due to the smoothness of the cartilage surface, strong filtering produces surfaces that show differences to the ground truth that are in the same order of magnitude as the inter-rater variation. The remaining root mean squared error lies in the range of 0:11 to 0:14 mm. These findings show that appropriate pre-processing techniques result in segmentations close to the consensus of multiple raters, suggesting that in the future fewer annotators are required to achieve a reliable segmentation.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Literatur

  1. 1.
    Pham DL, Xu C, Prince JL. Current methods in medical image segmentation. Annu Rev Biomed Eng. 2000;2(1):315–337.CrossRefGoogle Scholar
  2. 2.
    Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation. In: Proc MICCAI. vol. 9351. Springer; 2015. p. 234–241.Google Scholar
  3. 3.
    Milletari F, Navab N, Ahmadi SA. V-Net: fully convolutional neural networks for volumetric medical image segmentation. In: Proc 3DV. IEEE; 2016. p. 565–571.Google Scholar
  4. 4.
    Choi JH, Fahrig R, Keil A, et al. Fiducial marker-based correction for involuntary motion in weight-bearing C-arm CT scanning of knees: part 1: numerical modelbased optimization. Med Phys. 2013;40(9):091905–1–12.CrossRefGoogle Scholar
  5. 5.
    Choi JH, Maier A, Keil A, et al. Fiducial marker-based correction for involuntary motion in weight-bearing C-arm CT scanning of knees: part 2: experiment. Med Phys. 2014;41(6):061902–16.Google Scholar

Copyright information

© Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature 2019

Authors and Affiliations

  • Jennifer Maier
    • 1
    Email author
  • Marianne Black
    • 2
  • Mary Hall
    • 2
  • Jang-Hwan Choi
    • 3
  • Marc Levenston
    • 2
  • Garry Gold
    • 2
  • Rebecca Fahrig
    • 4
  • Bjoern Eskofier
    • 1
  • Andreas Maier
    • 1
  1. 1.Pattern Recognition LabFriedrich-Alexander-Universität Erlangen-NürnbergErlangenDeutschland
  2. 2.Stanford UniversityStanfordUSA
  3. 3.College of EngineeringEwha Womans UniversitySeoulKorea
  4. 4.Siemens Healthcare GmbHErlangenDeutschland

Personalised recommendations