Display Settings:

Format

Send to:

Choose Destination
We are sorry, but NCBI web applications do not support your browser and may not function properly. More information
Neuroimage. 2010 Feb 1;49(3):2352-65. doi: 10.1016/j.neuroimage.2009.10.026. Epub 2009 Oct 24.

Fast and robust multi-atlas segmentation of brain magnetic resonance images.

Author information

  • 1Knowledge Intensive Services, VTT Technical Research Centre of Finland, PO Box 1300 street address Tekniikankatu 1, FIN-33101 Tampere, Finland. jyrki.lotjonen@vtt.fi

Abstract

We introduce an optimised pipeline for multi-atlas brain MRI segmentation. Both accuracy and speed of segmentation are considered. We study different similarity measures used in non-rigid registration. We show that intensity differences for intensity normalised images can be used instead of standard normalised mutual information in registration without compromising the accuracy but leading to threefold decrease in the computation time. We study and validate also different methods for atlas selection. Finally, we propose two new approaches for combining multi-atlas segmentation and intensity modelling based on segmentation using expectation maximisation (EM) and optimisation via graph cuts. The segmentation pipeline is evaluated with two data cohorts: IBSR data (N=18, six subcortial structures: thalamus, caudate, putamen, pallidum, hippocampus, amygdala) and ADNI data (N=60, hippocampus). The average similarity index between automatically and manually generated volumes was 0.849 (IBSR, six subcortical structures) and 0.880 (ADNI, hippocampus). The correlation coefficient for hippocampal volumes was 0.95 with the ADNI data. The computation time using a standard multicore PC computer was about 3-4 min. Our results compare favourably with other recently published results.

Copyright (c) 2009 Elsevier Inc. All rights reserved.

PMID:
19857578
[PubMed - indexed for MEDLINE]
PubMed Commons home

PubMed Commons

0 comments
How to join PubMed Commons

    Supplemental Content

    Icon for Elsevier Science
    Loading ...
    Write to the Help Desk