Surgical Planning Laboratory - Brigham & Women's Hospital - Boston, Massachusetts USA - a teaching affiliate of Harvard Medical School

Surgical Planning Laboratory

The Publication Database hosted by SPL

All Publications | Upload | Advanced Search | Gallery View | Download Statistics | Help | Import | Log in

A Hierarchical Algorithm for MR Brain Image Parcellation

Surgical Planning Laboratory, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, USA.
IEEE Transactions on Medical Imaging.
Publication Date:
Volume Number:
Issue Number:
IEEE Transactions on Medical Imaging. 2007 Sep;26(9):1201-12.
PubMed ID:
Automatic Segmentation, Expectation-Maximization, Parcellation, Data Tree, Statistical Group Comparison Study, MRI, Projects:ShapeBasedSegmentationAndRegistration
Appears in Collections:
R01 AA005965/AA/NIAAA NIH HHS/United States
U01 AA013521/AA/NIAAA NIH HHS/United States
K02 MH001110/MH/NIMH NIH HHS/United States
P41 RR013218/RR/NCRR NIH HHS/United States
R01 AA016748/AA/NIAAA NIH HHS/United States
R01 MH040799/MH/NIMH NIH HHS/United States
R01 MH050747/MH/NIMH NIH HHS/United States
R01 NS051826/NS/NINDS NIH HHS/United States
U24 RR021382/RR/NCRR NIH HHS/United States
U54 EB005149/EB/NIBIB NIH HHS/United States
MIND foundation
Brain Science Foundation
Department of Veterans Affairs Merit Awards
Research Enhancement Award Program
Middleton Award from the Department of Veterans Affairs
Generated Citation:
Pohl K.M., Bouix S., Nakamura M., Rohlfing T., McCarley R.W., Kikinis R., Grimson W.E.L., Shenton M.E., Wells III W.M. A Hierarchical Algorithm for MR Brain Image Parcellation. IEEE Transactions on Medical Imaging. 2007 Sep;26(9):1201-12. PMID: 17896593. PMCID: PMC2768067.
Downloaded: 3675 times. [view map]
Paper: Download, View online
Export citation:
Google Scholar: link

We introduce an algorithm for segmenting brain magnetic resonance (MR) images into anatomical compartments such as the major tissue classes and neuro-anatomical structures of the gray matter. The algorithm is guided by prior information represented within a tree structure. The tree mirrors the hierarchy of anatomical structures and the sub-trees correspond to limited segmentation problems. The solution to each problem is estimated via a conventional classifier. Our algorithm can be adapted to a wide range of segmentation problems by modifying the tree structure or replacing the classifier. We evaluate the performance of our new segmentation approach by revisiting a previously published statistical group comparison between firstepisode schizophrenia patients, first-episode affective psychosis patients, and comparison subjects. The original study is based on 50 MR volumes in which an expert identified the brain tissue classes as well as the superior temporal gyrus, amygdala, and hippocampus. We generate analogous segmentations using our new method and repeat the statistical group comparison. The results of our analysis are similar to the original findings, except for one structure (the left superior temporal gyrus) in which a trend-level statistical significance (p=0.07) was observed instead of statistical significance.

Additional Material
1 File (655.281kB)
Pohl-TMI2007-fig6.jpg (655.281kB)