Abstract
Interactive segmentation promises to combine the speed of automatic approaches with the reliability of manual techniques. Its performance, however, depends largely on live iterative inputs by a human supervisor. For the task of glioblastoma segmentation in MRI data using a Random Forest pixel classifier we quantify the benefit in terms of speed and segmentation quality of user inputs in falsely classified regions as opposed to guided annotations in regions of high classifier uncertainty. The former results in a significantly higher area under the curve of the Dice score over time in all tumor categories. Exponential fits reveal a significantly higher final Dice score for larger tumor regions (gross tumor volume and edema) but not for smaller regions (necrotic core, non-enhancing abnormalities and contrast-enhancing tumor). Time constants of the exponential fits do not differ significantly.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer-Verlag GmbH Deutschland
About this paper
Cite this paper
Petersen, J., Heiland, S., Bendszus, M., Debus, J., Maier-Hein, K.H. (2017). Quantification of Guidance Strategies in Online Interactive Semantic Segmentation of Glioblastoma MRI. In: Maier-Hein, geb. Fritzsche, K., Deserno, geb. Lehmann, T., Handels, H., Tolxdorff, T. (eds) Bildverarbeitung für die Medizin 2017. Informatik aktuell. Springer Vieweg, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-54345-0_53
Download citation
DOI: https://doi.org/10.1007/978-3-662-54345-0_53
Published:
Publisher Name: Springer Vieweg, Berlin, Heidelberg
Print ISBN: 978-3-662-54344-3
Online ISBN: 978-3-662-54345-0
eBook Packages: Computer Science and Engineering (German Language)