Please use this identifier to cite or link to this item: https://doi.org/10.1016/j.mri.2012.02.010
Title: Atlas-based automatic mouse brain image segmentation revisited: Model complexity vs. image registration
Authors: Bai, J.
Trinh, T.L.H.
Chuang, K.-H.
Qiu, A. 
Keywords: Diffeomorphic mapping
Markov random field
Mouse brain segmentation
Issue Date: Jul-2012
Source: Bai, J., Trinh, T.L.H., Chuang, K.-H., Qiu, A. (2012-07). Atlas-based automatic mouse brain image segmentation revisited: Model complexity vs. image registration. Magnetic Resonance Imaging 30 (6) : 789-798. ScholarBank@NUS Repository. https://doi.org/10.1016/j.mri.2012.02.010
Abstract: Although many atlas-based segmentation methods have been developed and validated for the human brain, limited work has been done for the mouse brain. This paper investigated roles of image registration and segmentation model complexity in the mouse brain segmentation. We employed four segmentation models [single atlas, multiatlas, simultaneous truth and performance level estimation (STAPLE) and Markov random field (MRF) via four different image registration algorithms (affine, B-spline free-form deformation (FFD), Demons and large deformation diffeomorphic metric mapping (LDDMM)] for delineating 19 structures from in vivo magnetic resonance microscopy images. We validated their accuracies against manual segmentation. Our results revealed that LDDMM outperformed Demons, FFD and affine in any of the segmentation models. Under the same registration, increasing segmentation model complexity from single atlas to multiatlas, STAPLE or MRF significantly improved the segmentation accuracy. Interestingly, the multiatlas-based segmentation using nonlinear registrations (FFD, Demons and LDDMM) had similar performance to their STAPLE counterparts, while they both outperformed their MRF counterparts. Furthermore, when the single-atlas affine segmentation was used as reference, the improvement due to nonlinear registrations (FFD, Demons and LDDMM) in the single-atlas segmentation model was greater than that due to increasing model complexity (multiatlas, STAPLE and MRF affine segmentation). Hence, we concluded that image registration plays a more crucial role in the atlas-based automatic mouse brain segmentation as compared to model complexity. Multiple atlases with LDDMM can best improve the segmentation accuracy in the mouse brain among all segmentation models tested in this study. © 2012 Elsevier Inc.
Source Title: Magnetic Resonance Imaging
URI: http://scholarbank.nus.edu.sg/handle/10635/66938
ISSN: 0730725X
DOI: 10.1016/j.mri.2012.02.010
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

24
checked on Dec 7, 2017

WEB OF SCIENCETM
Citations

23
checked on Nov 22, 2017

Page view(s)

47
checked on Dec 10, 2017

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.