GPSSI: Gaussian Process for Sampling Segmentations of Images
Medical image segmentation is often a prerequisite for clinical applications. As an ill-posed problem, it leads to uncertain estimations of the region of interest which may have a significant impact on downstream applications, such as therapy planning. To quantify the uncertainty related to image segmentations, a classical approach is to measure the effect of using various plausible segmentations. In this paper, a method for producing such image segmentation samples from a single expert segmentation is introduced. A probability distribution of image segmentation boundaries is defined as a Gaussian process, which leads to segmentations that are spatially coherent and consistent with the presence of salient borders in the image. The proposed approach outperforms previous generative segmentation approaches, and segmentation samples can be generated efficiently. The sample variability is governed by a parameter which is correlated with a simple DICE score. We show how this approach can have multiple useful applications in the field of uncertainty quantification, and an illustration is provided in radiotherapy planning.
KeywordsImage Segmentation Gaussian Process Discrete Fourier Transform Clinical Target Volume Gross Tumor Volume
Unable to display preview. Download preview PDF.
- 5.Williams, O., Fitzgibbon, A.: Gaussian process implicit surfaces. In: Gaussian Proc. in Practice (2007)Google Scholar
- 6.Gerardo-Castro, M.P., Peynot, T., Ramos, F.: Laser-radar data fusion with gaussian process implicit surfaces. In: Corke, P., Mejias, L., Roberts, J. (eds.) The 9th Int. Conf. on Field and Service Robotics, Brisbane, Australia (2013)Google Scholar
- 8.Rasmussen, C.E.: Gaussian processes for machine learning (2006)Google Scholar
- 9.Kozintsev, B.: Computations with Gaussian random fields (1999)Google Scholar