Automatic Structural Parcellation of Mouse Brain MRI Using Multi-Atlas Label Fusion

被引:49
作者
Ma, Da [1 ,2 ]
Cardoso, Manuel J. [1 ]
Modat, Marc [1 ]
Powell, Nick [1 ,2 ]
Wells, Jack [2 ]
Holmes, Holly [2 ]
Wiseman, Frances [3 ]
Tybulewicz, Victor [4 ]
Fisher, Elizabeth [3 ]
Lythgoe, Mark F. [2 ]
Ourselin, Sebastien [1 ]
机构
[1] UCL, Ctr Med Imaging Comp, London, England
[2] UCL, Div Med, Ctr Adv Biomed Imaging, London, England
[3] UCL, Inst Neurol, Dept Neurodegenerat Dis, London, England
[4] MRC Natl Inst Med Res, Div Immune Cell Biol, London, England
来源
PLOS ONE | 2014年 / 9卷 / 01期
基金
英国惠康基金; 英国国家替代、减少和改良动物研究中心; 英国工程与自然科学研究理事会; 英国医学研究理事会;
关键词
IN-VIVO; NONRIGID REGISTRATION; SEGMENTATION; IMAGE; DATABASE; PROPAGATION; COMBINATION; STRATEGIES; ASYMMETRY; FRAMEWORK;
D O I
10.1371/journal.pone.0086576
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
Multi-atlas segmentation propagation has evolved quickly in recent years, becoming a state-of-the-art methodology for automatic parcellation of structural images. However, few studies have applied these methods to preclinical research. In this study, we present a fully automatic framework for mouse brain MRI structural parcellation using multi-atlas segmentation propagation. The framework adopts the similarity and truth estimation for propagated segmentations (STEPS) algorithm, which utilises a locally normalised cross correlation similarity metric for atlas selection and an extended simultaneous truth and performance level estimation (STAPLE) framework for multi-label fusion. The segmentation accuracy of the multi-atlas framework was evaluated using publicly available mouse brain atlas databases with pre-segmented manually labelled anatomical structures as the gold standard, and optimised parameters were obtained for the STEPS algorithm in the label fusion to achieve the best segmentation accuracy. We showed that our multi-atlas framework resulted in significantly higher segmentation accuracy compared to single-atlas based segmentation, as well as to the original STAPLE framework.
引用
收藏
页数:12
相关论文
共 60 条
[1]   Local SIMPLE Multi Atlas-Based Segmentation Applied to Lung Lobe Detection on Chest CT [J].
Agarwal, M. ;
Hendriks, E. A. ;
Stoel, B. C. ;
Bakker, M. E. ;
Reiber, J. H. C. ;
Staring, M. .
MEDICAL IMAGING 2012: IMAGE PROCESSING, 2012, 8314
[2]  
Aljabar P, 2007, LECT NOTES COMPUT SC, V4791, P523
[3]  
Artaechevarria X, 2008, P SPIE INT SOC OPT P, V69141W-69141W-9
[4]   Combination Strategies in Multi-Atlas Image Segmentation: Application to Brain MR Data [J].
Artaechevarria, Xabier ;
Munoz-Barrutia, Arrate ;
Ortiz-de-Solorzano, Carlos .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2009, 28 (08) :1266-1277
[5]   The knockout mouse project [J].
Austin, CP ;
Battey, JF ;
Bradley, A ;
Bucan, M ;
Capecchi, M ;
Collins, FS ;
Dove, WF ;
Duyk, G ;
Dymecki, S ;
Eppig, JT ;
Grieder, FB ;
Heintz, N ;
Hicks, G ;
Insel, TR ;
Joyner, A ;
Koller, BH ;
Lloyd, KCK ;
Magnuson, T ;
Moore, MW ;
Nagy, A ;
Pollock, JD ;
Roses, AD ;
Sands, AT ;
Seed, B ;
Skarnes, WC ;
Snoddy, J ;
Soriano, P ;
Stewart, DJ ;
Stewart, F ;
Stillman, B ;
Varmus, H ;
Varticovski, L ;
Verma, IM ;
Vogt, TF ;
von Melchner, H ;
Witkowski, J ;
Woychik, RP ;
Wurst, W ;
Yancopoulos, GD ;
Young, SG ;
Zambrowicz, B .
NATURE GENETICS, 2004, 36 (09) :921-924
[6]   Morphometric analysis of the C57BL/6J mouse brain [J].
Badea, A. ;
Ali-Sharief, A. A. ;
Johnson, G. A. .
NEUROIMAGE, 2007, 37 (03) :683-693
[7]   Atlas-based automatic mouse brain image segmentation revisited: model complexity vs. image registration [J].
Bai, Jordan ;
Trinh, Thi Lan Huong ;
Chuang, Kai-Hsiang ;
Qiu, Anqi .
MAGNETIC RESONANCE IMAGING, 2012, 30 (06) :789-798
[8]   Human and mouse gene structure: Comparative analysis and application to exon prediction [J].
Batzoglou, S ;
Pachter, L ;
Mesirov, JP ;
Berger, B ;
Lander, ES .
GENOME RESEARCH, 2000, 10 (07) :950-958
[9]  
Boccardi M., 2013, ALZHEIMERS DEMENT, P1
[10]   In vivo multiple-mouse MRI at 7 Tesla [J].
Bock, NA ;
Nieman, BJ ;
Bishop, JB ;
Henkelman, RM .
MAGNETIC RESONANCE IN MEDICINE, 2005, 54 (05) :1311-1316