Sampling Image Segmentations for Uncertainty Quantification - Archive ouverte HAL Access content directly
Journal Articles Medical Image Analysis Year : 2016

Sampling Image Segmentations for Uncertainty Quantification


In this paper, we introduce a method to automatically produce plausible image segmentation samples from a single expert segmentation. A probability distribution of image segmentation boundaries is defined as a Gaussian process, which leads to segmentations which are spatially coherent and consistent with the presence of salient borders in the image. The proposed approach is computationally efficient, and generates visually plausible samples. The variability between the samples is mainly governed by a parameter which may be correlated with a simple Dice's coefficient, or easily set by the user from the definition of probable regions of interest. The method is extended to the case of several neighboring structures, but also to account for under or over segmentation, and the presence of excluded regions. We also detail a method to sample segmentations with more general non-stationary covariance functions which relies on supervoxels. Furthermore, we compare the generated segmentation samples with several manual clinical segmentations of a brain tumor. Finally, we show how this approach can have useful applications in the field of uncertainty quantification, and an illustration is provided in radiotherapy planning, where segmentation sampling is applied to both the clinical target volume and the organs at risk.
Fichier principal
Vignette du fichier
mle_preprint.pdf (4.21 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01304646 , version 1 (20-04-2016)



Matthieu Lê, Jan Unkelbach, Nicholas Ayache, Hervé Delingette. Sampling Image Segmentations for Uncertainty Quantification. Medical Image Analysis, 2016, 34, pp.42-51. ⟨10.1016/⟩. ⟨hal-01304646⟩


232 View
1384 Download



Gmail Facebook X LinkedIn More