Atlas-Based Under-Segmentation
Authors:
Open Access
- 1 January 2014
- book chapter
- Published by Springer Nature
- Vol. 17 (Pt 1) , 315-322
Abstract
We study the widespread, but rarely discussed, tendency of atlas-based segmentation to under-segment the organs of interest. Commonly used error measures do not distinguish between under- and over-segmentation, contributing to the problem. We explicitly quantify over- and under-segmentation in several typical examples and present a new hypothesis for the cause. We provide evidence that segmenting only one organ of interest and merging all surrounding structures into one label creates bias towards background in the label estimates suggested by the atlas. We propose a generative model that corrects for this effect by learning the background structures from the data. Inference in the model separates the background into distinct structures and consequently improves the segmentation accuracy. Our experiments demonstrate a clear improvement in several applications.Keywords
This publication has 8 references indexed in Scilit:
- Contour-Driven Regression for Label Inference in Atlas-Based Segmentation2013
- Spatial Bias in Multi-Atlas Based Segmentation2012
- A Generative Model for Image Segmentation Based on Label FusionIEEE Transactions on Medical Imaging, 2010
- Dirichlet Process Gaussian Mixture Models: Choice of the Base DistributionJournal of Computer Science and Technology, 2010
- Automatic anatomical brain MRI segmentation combining label propagation and decision fusionNeuroImage, 2006
- Evaluation of atlas selection strategies for atlas-based image segmentation with application to confocal microscopy images of bee brainsNeuroImage, 2004
- A modified Hausdorff distance for object matching2002
- Measures of the Amount of Ecologic Association Between SpeciesEcology, 1945