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

Jennifer Maier, Marianne Black, Mary Hall, Jang Hwan Choi, Marc Levenston, Garry Gold, Rebecca Fahrig, Bjoern Eskofier, Andreas Maier

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


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 lowpass 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.

Original languageEnglish
Title of host publicationBildverarbeitung für die Medizin 2019
Subtitle of host publicationAlgorithmen – Systeme – Anwendungen - Proceedings des Workshops vom 17. bis 19. März 2019
EditorsAndreas Maier, Heinz Handels, Thomas M. Deserno, Thomas Tolxdorff, Klaus H. Maier-Hein, Christoph Palm
PublisherSpringer Berlin Heidelberg
Number of pages6
ISBN (Print)9783658253257
StatePublished - 2019
EventWorkshop on Bildverarbeitung fur die Medizin, 2019 - Lübeck, Germany
Duration: 17 Mar 201919 Mar 2019

Publication series

NameInformatik aktuell
ISSN (Print)1431-472X


ConferenceWorkshop on Bildverarbeitung fur die Medizin, 2019

Bibliographical note

Publisher Copyright:
© 2019, Springer Berlin Heidelberg. All rights reserved.


Dive into the research topics of 'Smooth Ride: Low-Pass Filtering of Manual Segmentations Improves Consensus'. Together they form a unique fingerprint.

Cite this