Expectation Maximization Strategies for Multi-atlas Multi-label Segmentation
- 1 January 2003
- book chapter
- Published by Springer Nature
- Vol. 18, 210-221
- https://doi.org/10.1007/978-3-540-45087-0_18
Abstract
It is well-known in the pattern recognition community that the accuracy of classifications obtained by combining decisions made by independent classifiers can be substantially higher that the accuracy of the individual classifiers. In order to combine multiple segmentations we introduce two extensions to an expectation maximization (EM) algorithm for ground truth estimation based on multiple experts (Warfield et al., MICCAI 2002). The first method repeatedly applies the Warfield algorithm with a subsequent integration step. The second method is a multi-label extension of the Warfield algorithm. Both extensions integrate multiple segmentations into one that is closer to the unknown ground truth than the individual segmentations. In atlas-based image segmentation, multiple classifiers arise naturally by applying different registration methods to the same atlas, or the same registration method to different atlases, or both. We perform a validation study designed to quantify the success of classifier combination methods in atlas-based segmentation. By applying random deformations, a given ground truth atlas is transformed into multiple segmentations that could result from imperfect registrations of an image to multiple atlas images. We demonstrate that a segmentation produced by combining multiple individual registration-based segmentations is more accurate for the two EM methods we propose than for simple label averaging.Keywords
This publication has 9 references indexed in Scilit:
- Segmentation of three-dimensional images using non-rigid registration: methods and validation with application to confocal microscopy images of bee brainsPublished by SPIE-Intl Soc Optical Eng ,2003
- Bee brains, B-splines and computational democracy: generating an average shape atlasPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Validation of Image Segmentation and Expert Quality with an Expectation-Maximization AlgorithmPublished by Springer Nature ,2002
- Automatic 3-D segmentation of internal structures of the head in MR images using a combination of similarity and free-form transformations. I. Methodology and validation on normal subjectsIEEE Transactions on Medical Imaging, 1999
- Nonrigid registration using free-form deformations: application to breast MR imagesIEEE Transactions on Medical Imaging, 1999
- On combining classifiersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1998
- Multimodality image registration by maximization of mutual informationIEEE Transactions on Medical Imaging, 1997
- Methods of combining multiple classifiers and their applications to handwriting recognitionIEEE Transactions on Systems, Man, and Cybernetics, 1992
- Free-form deformation of solid geometric modelsACM SIGGRAPH Computer Graphics, 1986