Discriminative, Semantic Segmentation of Brain Tissue in MR Images
- 1 January 2009
- book chapter
- conference paper
- Published by Springer Science and Business Media LLC in Lecture Notes in Computer Science
- Vol. 12, 558-565
- https://doi.org/10.1007/978-3-642-04271-3_68
Abstract
A new algorithm is presented for the automatic segmentation and classification of brain tissue from 3D MR scans. It uses discriminative Random Decision Forest classification and takes into account partial volume effects. This is combined with correction of intensities for the MR bias field, in conjunction with a learned model of spatial context, to achieve accurate voxel-wise classification. Our quantitative validation, carried out on existing labelled datasets, demonstrates improved results over the state of the art, especially for the cerebro-spinal fluid class which is the most difficult to label accurately.Keywords
This publication has 17 references indexed in Scilit:
- TextonBoost: Joint Appearance, Shape and Context Modeling for Multi-class Object Recognition and SegmentationLecture Notes in Computer Science, 2006
- Data-driven brain MRI segmentation supported on edge confidence and a priori tissue informationIEEE Transactions on Medical Imaging, 2005
- Morphometric analysis of lateral ventricles in schizophrenia and healthy controls regarding genetic and disease-specific factorsProceedings of the National Academy of Sciences of the United States of America, 2005
- Neighbor-Constrained Segmentation With Level Set Based 3-D Deformable ModelsIEEE Transactions on Medical Imaging, 2004
- An accurate and efficient Bayesian method for automatic segmentation of brain MRIIEEE Transactions on Medical Imaging, 2002
- Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithmIEEE Transactions on Medical Imaging, 2001
- Adaptive fuzzy segmentation of magnetic resonance imagesIEEE Transactions on Medical Imaging, 1999
- Partial-volume Bayesian classification of material mixtures in MR volume data using voxel histogramsIEEE Transactions on Medical Imaging, 1998
- Shape Quantization and Recognition with Randomized TreesNeural Computation, 1997
- Deformable models in medical image analysis: a surveyMedical Image Analysis, 1996