Perturb-and-MPM: Quantifying Segmentation Uncertainty in Dense Multi-Label CRFs

Abstract

This paper proposes a novel approach for uncertainty quantification in dense Conditional Random Fields (CRFs). The presented approach, called Perturb-and-MPM, enables efficient, approximate sampling from dense multi-label CRFs via random perturbations. An analytic error analysis was performed which identified the main cause of approximation error as well as showed that the error is bounded. Spatial uncertainty maps can be derived from the Perturb-and-MPM model, which can be used to visualize uncertainty in image segmentation results. The method is validated on synthetic and clinical Magnetic Resonance Imaging data. The effectiveness of the approach is demonstrated on the challenging problem of segmenting the tumor core in glioblastoma. We found that areas of high uncertainty correspond well to wrongly segmented image regions. Furthermore, we demonstrate the potential use of uncertainty maps to refine imaging biomarkers in the case of extent of resection and residual tumor volume in brain tumor patients.

Deactivated review mode (line spacing)

References in corpus (4)

• Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional Neural Networks and 3D Conditional Random Fields
• Structured Stochastic Variational Inference