TY - JOUR
T1 - Whole brain segmentation
T2 - Automated labeling of neuroanatomical structures in the human brain
AU - Fischl, Bruce
AU - Salat, David H.
AU - Busa, Evelina
AU - Albert, Marilyn
AU - Dieterich, Megan
AU - Haselgrove, Christian
AU - Van Der Kouwe, Andre
AU - Killiany, Ron
AU - Kennedy, David
AU - Klaveness, Shuna
AU - Montillo, Albert
AU - Makris, Nikos
AU - Rosen, Bruce
AU - Dale, Anders M.
N1 - Funding Information:
This Human Brain Project/Neuroinformatics research is funded jointly by the National Institute of Neurological Disorders and Stroke, the National Institute of Mental Health, and the National Cancer Institute (R01-NS39581, R01-NS34189). Further support was provided by the National Center for Research Resources (P41-RR14075 and R01-RR13609). We thank Maureen Glessner for extensive testing of the proposed algorithms. We also thank Sean Marrett for helpful comments on the manuscript.
PY - 2002/1/31
Y1 - 2002/1/31
N2 - We present a technique for automatically assigning a neuroanatomical label to each voxel in an MRI volume based on probabilistic information automatically estimated from a manually labeled training set. In contrast to existing segmentation procedures that only label a small number of tissue classes, the current method assigns one of 37 labels to each voxel, including left and right caudate, putamen, pallidum, thalamus, lateral ventricles, hippocampus, and amygdala. The classification technique employs a registration procedure that is robust to anatomical variability, including the ventricular enlargement typically associated with neurological diseases and aging. The technique is shown to be comparable in accuracy to manual labeling, and of sufficient sensitivity to robustly detect changes in the volume of noncortical structures that presage the onset of probable Alzheimer's disease.
AB - We present a technique for automatically assigning a neuroanatomical label to each voxel in an MRI volume based on probabilistic information automatically estimated from a manually labeled training set. In contrast to existing segmentation procedures that only label a small number of tissue classes, the current method assigns one of 37 labels to each voxel, including left and right caudate, putamen, pallidum, thalamus, lateral ventricles, hippocampus, and amygdala. The classification technique employs a registration procedure that is robust to anatomical variability, including the ventricular enlargement typically associated with neurological diseases and aging. The technique is shown to be comparable in accuracy to manual labeling, and of sufficient sensitivity to robustly detect changes in the volume of noncortical structures that presage the onset of probable Alzheimer's disease.
UR - http://www.scopus.com/inward/record.url?scp=18244406829&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=18244406829&partnerID=8YFLogxK
U2 - 10.1016/S0896-6273(02)00569-X
DO - 10.1016/S0896-6273(02)00569-X
M3 - Article
C2 - 11832223
AN - SCOPUS:18244406829
SN - 0896-6273
VL - 33
SP - 341
EP - 355
JO - Neuron
JF - Neuron
IS - 3
ER -