TY - JOUR
T1 - A Bayesian model of shape and appearance for subcortical brain segmentation
AU - Patenaude, Brian
AU - Smith, Stephen M.
AU - Kennedy, David N.
AU - Jenkinson, Mark
N1 - Funding Information:
The authors wish to thank Dr Mojtaba Zarei for very helpful discussions about Alzheimer's Disease, as well as the UK EPSRC IBIM Grant and the UK BBSRC David Phillips Fellowship for funding this research. In addition, the authors extend thanks to all those involved in contributing data for this project: Christian Haselgrove, Centre for Morphometric Analysis, Harvard; Bruce Fischl, the Martinos Center for Biomedical Imaging, MGH ( NIH grants P41-RR14075 , R01 RR16594-01A1 , and R01 NS052585-01 ); Janis Breeze and Jean Frazier, the Child and Adolescent Neuropsychiatric Research Program, Cambridge Health Alliance (NIH grants K08 MH01573 and K01 MH01798 ); Larry Seidman and Jill Goldstein, the Department of Psychiatry of Harvard Medical School; Barry Kosofsky, Weill Cornell Medical Center (NIH grant R01 DA017905 ); Frederik Barkhof and Philip Scheltens, VU University Medical Center, Amsterdam.
PY - 2011/6/1
Y1 - 2011/6/1
N2 - Automatic segmentation of subcortical structures in human brain MR images is an important but difficult task due to poor and variable intensity contrast. Clear, well-defined intensity features are absent in many places along typical structure boundaries and so extra information is required to achieve successful segmentation. A method is proposed here that uses manually labelled image data to provide anatomical training information. It utilises the principles of the Active Shape and Appearance Models but places them within a Bayesian framework, allowing probabilistic relationships between shape and intensity to be fully exploited. The model is trained for 15 different subcortical structures using 336 manually-labelled T1-weighted MR images. Using the Bayesian approach, conditional probabilities can be calculated easily and efficiently, avoiding technical problems of ill-conditioned covariance matrices, even with weak priors, and eliminating the need for fitting extra empirical scaling parameters, as is required in standard Active Appearance Models. Furthermore, differences in boundary vertex locations provide a direct, purely local measure of geometric change in structure between groups that, unlike voxel-based morphometry, is not dependent on tissue classification methods or arbitrary smoothing. In this paper the fully-automated segmentation method is presented and assessed both quantitatively, using Leave-One-Out testing on the 336 training images, and qualitatively, using an independent clinical dataset involving Alzheimer's disease. Median Dice overlaps between 0.7 and 0.9 are obtained with this method, which is comparable or better than other automated methods. An implementation of this method, called FIRST, is currently distributed with the freely-available FSL package.
AB - Automatic segmentation of subcortical structures in human brain MR images is an important but difficult task due to poor and variable intensity contrast. Clear, well-defined intensity features are absent in many places along typical structure boundaries and so extra information is required to achieve successful segmentation. A method is proposed here that uses manually labelled image data to provide anatomical training information. It utilises the principles of the Active Shape and Appearance Models but places them within a Bayesian framework, allowing probabilistic relationships between shape and intensity to be fully exploited. The model is trained for 15 different subcortical structures using 336 manually-labelled T1-weighted MR images. Using the Bayesian approach, conditional probabilities can be calculated easily and efficiently, avoiding technical problems of ill-conditioned covariance matrices, even with weak priors, and eliminating the need for fitting extra empirical scaling parameters, as is required in standard Active Appearance Models. Furthermore, differences in boundary vertex locations provide a direct, purely local measure of geometric change in structure between groups that, unlike voxel-based morphometry, is not dependent on tissue classification methods or arbitrary smoothing. In this paper the fully-automated segmentation method is presented and assessed both quantitatively, using Leave-One-Out testing on the 336 training images, and qualitatively, using an independent clinical dataset involving Alzheimer's disease. Median Dice overlaps between 0.7 and 0.9 are obtained with this method, which is comparable or better than other automated methods. An implementation of this method, called FIRST, is currently distributed with the freely-available FSL package.
KW - Bayesian
KW - Classification
KW - Segmentation
KW - Shape model
KW - Subcortical structures
UR - http://www.scopus.com/inward/record.url?scp=79955484518&partnerID=8YFLogxK
U2 - 10.1016/j.neuroimage.2011.02.046
DO - 10.1016/j.neuroimage.2011.02.046
M3 - Article
C2 - 21352927
AN - SCOPUS:79955484518
VL - 56
SP - 907
EP - 922
JO - NeuroImage
JF - NeuroImage
SN - 1053-8119
IS - 3
ER -