Loading [a11y]/accessibility-menu.js
Uncertainty quantification in brain tumor segmentation using CRFs and random perturbation models | IEEE Conference Publication | IEEE Xplore

Uncertainty quantification in brain tumor segmentation using CRFs and random perturbation models


Abstract:

Medical image segmentation is a challenging task and algorithms often struggle with the high variability of inhomogeneous clinical data, demanding different parameter set...Show More

Abstract:

Medical image segmentation is a challenging task and algorithms often struggle with the high variability of inhomogeneous clinical data, demanding different parameter settings or resulting in weak segmentation accuracy across different inputs. Assessing the uncertainty in the resulting segmentation therefore becomes crucial for both communicating with the end-user and calculating further metrics of interest based on it, for example, in tumor volumetry. In this paper, we quantify segmentation uncertainties in a energy minimisation method where computing probabilistic segmentations is non-trivial. We follow recently proposed work on random perturbation models that enables us to sample segmentations efficiently by repeatedly perturbing the energy function of the conditional random field (CRF) followed by maximum a posteriori (MAP) inference. We conduct experiments on brain tumor segmentation, with both voxel and supervoxel perturbations, and demonstrate the benefits of probabilistic segmentations by means of precision-recall curves and uncertainties in tumor volumetry along time.
Date of Conference: 13-16 April 2016
Date Added to IEEE Xplore: 16 June 2016
Electronic ISBN:978-1-4799-2349-6
Electronic ISSN: 1945-8452
Conference Location: Prague, Czech Republic

References

References is not available for this document.