Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Deformable Templates Guided Discriminative Models for Robust 3D Brain MRI Segmentation

Deformable Templates Guided Discriminative Models for Robust 3D Brain MRI Segmentation Automatically segmenting anatomical structures from 3D brain MRI images is an important task in neuroimaging. One major challenge is to design and learn effective image models accounting for the large variability in anatomy and data acquisition protocols. A deformable template is a type of generative model that attempts to explicitly match an input image with a template (atlas), and thus, they are robust against global intensity changes. On the other hand, discriminative models combine local image features to capture complex image patterns. In this paper, we propose a robust brain image segmentation algorithm that fuses together deformable templates and informative features. It takes advantage of the adaptation capability of the generative model and the classification power of the discriminative models. The proposed algorithm achieves both robustness and efficiency, and can be used to segment brain MRI images with large anatomical variations. We perform an extensive experimental study on four datasets of T1-weighted brain MRI data from different sources (1,082 MRI scans in total) and observe consistent improvement over the state-of-the-art systems. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Neuroinformatics Springer Journals

Deformable Templates Guided Discriminative Models for Robust 3D Brain MRI Segmentation

Liu, Cheng-Yi; Iglesias, Juan; Tu, Zhuowen
Neuroinformatics , Volume 11 (4) – Jul 9, 2013
Download PDF
22 pages

Loading next page...
 
/lp/springer-journals/deformable-templates-guided-discriminative-models-for-robust-3d-brain-d5tZ6S0qg5
Publisher
Springer Journals
Copyright
Copyright © 2013 by Springer Science+Business Media New York
Subject
Biomedicine; Neurosciences; Bioinformatics; Computational Biology/Bioinformatics; Computer Appl. in Life Sciences; Neurology
ISSN
1539-2791
eISSN
1559-0089
DOI
10.1007/s12021-013-9190-5
pmid
23836390
Publisher site
See Article on Publisher Site

Abstract

Automatically segmenting anatomical structures from 3D brain MRI images is an important task in neuroimaging. One major challenge is to design and learn effective image models accounting for the large variability in anatomy and data acquisition protocols. A deformable template is a type of generative model that attempts to explicitly match an input image with a template (atlas), and thus, they are robust against global intensity changes. On the other hand, discriminative models combine local image features to capture complex image patterns. In this paper, we propose a robust brain image segmentation algorithm that fuses together deformable templates and informative features. It takes advantage of the adaptation capability of the generative model and the classification power of the discriminative models. The proposed algorithm achieves both robustness and efficiency, and can be used to segment brain MRI images with large anatomical variations. We perform an extensive experimental study on four datasets of T1-weighted brain MRI data from different sources (1,082 MRI scans in total) and observe consistent improvement over the state-of-the-art systems.

Journal

Neuroinformatics – Springer Journals

Published: Jul 9, 2013

References

  • Unified segmentation
    Ashburner, J; Friston, K
  • Symmetric diffeomorphic image registration with cross-correlation: evaluating automated labeling of elderly and neurodegenerative brain
    Avants, B; Epstein, C; Grossman, M; Gee, J
  • Topology-preserving tissue classification of magnetic resonance brain images
    Bazin, PL; Pham, D
  • Homeomorphic brain image segmentation with topological and statistical atlases
    Bazin, PL; Pham, D
  • Random forests
    Breiman, L
  • A non-local fuzzy segmentation method: application to brain MRI
    Caldairou, B; Passat, N; Habas, PA; Studholme, C; Rousseau, F
  • On learning, representing and generalizing a task in a humanoid robot. Special issue on robot learning by observation, demonstration and imitation
    Calinon, S.; Guenter, F.; Billard, A.
  • Active contours without edges
    Chan, T; Vese, L
  • Mutual information-based CT-MR brain image registration using generalized partial volume joint histogram estimation
    Chen, HM; Varshney, P
  • Efficient multilevel brain tumor segmentation with integrated Bayesian model classification
    Corso, J; Sharon, E; Dube, S; El-Saden, S; Sinha, U; Yuille, A
  • Whole brain diffeomorphic metric mapping via integration of sulcal and gyral curves, cortical surfaces, and images
    Du, J; Younes, L; Qiu, A
  • An integrated software system for surface-based analyses of cerebral cortex
    Essen, DCV; Dickson, J; Harwell, J; Hanlon, D; Anderson, CH; Drury, HA
  • COMPARE: classification of morphological patterns using adaptive regional elements
    Fan, Y; Shen, D; Gur, RC; Gur, RE; Davatzikos, C
  • Representation and detection of deformable shapes
    Felzenszwalb, PF
  • Whole brain segmentation: automated labeling of neuroanatomical structures in the human brain
    Fischl, B
  • Sequence-independent segmentation of magnetic resonance images
    Fischl, B; Salat, DH; Kouwe, AJ; Makris, N; Segonne, F; Quinn, BT; AM, AMD
  • Retrospective intermodality registration techniques for images of the head: surface-based versus volume-based
    Fitzpatrick, J; Wang, MY; Dawant, BM; Maurer, CRJ; Kessler, RM; Maciunas, RJ
  • Human brain function
    Frackowiak, R; Friston, K; Frith, C; Dolan, R; Price, C; Zeki, S; Ashburner, J; Penny, W
  • A decision-theoretic generalization of on-line learning and an application to boosting
    Freund, Y; Schapire, R
  • Spatial decision forests for ms lesion segmentation in multi-channel magnetic resonance images
    Geremia, E; Clatz, O; Menze, BH; Konukoglu, E; Criminisi, A; Ayache, N
  • Subcortical structure segmentation using probabilistic atlas priors
    Gouttard, S
  • Automatic anatomical brain MRI segmentation combining label propagation and decision fusion
    Heckemann, R; Hajnal, J; Aljabar, P; Rueckert, D; Hammers, A
  • Hybrid generative-discriminative visual categorization.
    Holub, A; Welling, M; Perona, P
  • A review on MR image intensity inhomogeneity correction
    Hou, Z
  • Optimizing power to track brain degeneration in Alzheimer’s disease and mild cognitive impairment with tensor-based morphometry: an ADNI study of 515 subjects
    Hua, X
  • The Alzheimer’s disease neuroimaging initiative (ADNI): The MR imaging protocol
    Jack, C
  • Machine learning: discriminative and generative
    Jebara, T
  • Evaluation of automated brain MR image segmentation and volumetry methods
    Klauschen, F; Goldman, A; Barra, V; Meyer-Lindenberg, A; Lundervold, A
  • Evaluation of 14 nonlinear deformation algorithms applied to human brain MRI registration
    Klein, A
  • Automated segmentation of multiple sclerosis lesions by model outlier detection
    Leemput, KV; Maes, F; Vandermeulen, D; Colchester, A; Suetens, P
  • Automated model-based tissue classification of MR images of the brain
    Leemput, KV; Maes, F; Vandermeulen, D; Suetens, P
  • Knowledge-based classification and tissue labeling of MR images of human brain
    Li, C; Goldgof, D; Hall, L
  • A survey of shape analysis techniques
    Loncaric, S
  • Comparison of adaboost and support vector machines for detecting Alzheimer’ss disease through automated hippocampal segmentation
    Morra, JH; Tu, Z; Apostolova, L; Green, AE; Toga, A; Thompson, P
  • Adaptive fuzzy segmentation of magnetic resonance images
    Pham, D; Prince, J
  • Deformable m-reps for 3D medical image segmentation.
    Pizer, SM
  • A Bayesian model for joint segmentation and registration
    Pohl, K; Fisher, J; Kikinis, R; Grimson, W; Wells, W
  • Automatic brain tumor segmentation by subject specific modification of atlas priors
    Prastawa, M; Bullitt, E; Moon, N; Leemput, KV; Gerig, G
  • A generative model for image segmentation based on label fusion
    Sabuncu, M; Yeo, B; Leemput, KV; Fischl, B; Golland, P
  • Distributed local MRF models for tissue and structure brain segmentation
    Scherrer, B; Forbes, F; Garbay, C; Dojat, M
  • Initiative: nonlinear time course of brain volume loss in cognitively normal and impaired elders
    Schuff, N; Tosun, D; Insel, P; Chiang, G; Truran, D; Aisen, P; Jack, CJ; Weiner, MADN
  • Magnetic resonance image tissue classification using a partial volume model
    Shattuck, D; Sandor-Leahy, S; Schaper, K; Rottenberg, D; Leahy, R
  • Construction of a 3D probabilistic atlas of human cortical structures
    Shattuck, DW
  • A nonparametric method for automatic correction of intensity non-uniformity in MRI data
    Sled, J; Zijdenbos, A; Evans, A
  • Fast robust automated brain extraction
    Smith, S
  • Regression shrinkage and selection via the lasso
    Tibshirani, R
  • Auto-context and its application to high-level vision tasks and 3D brain image segmentation
    Tu, Z; Bai, X
  • Brain anatomical structure segmentation by hybrid discriminative/generative models
    Tu, Z; Narr, K; Dollar, P; Dinov, I; Thompson, P; Toga, A
  • Estimation of dependences based on empirical data
    Vapnik, V
  • Statistical learning theory
    Vapnik, V
  • Multi-parametric tissue characterization of brain neoplasms and their recurrence using pattern classification of MR images
    Verma, R; Zacharaki, EI; Ou, Y; Cai, H; Chawl, S; Lee, SK; Melhem, ER; Wolf, R; Davatzikos, C
  • The Alzheimer’s disease neuroimaging initiative: a learning-based wrapper method to correct systematic errors in automatic image segmentation: consistently improved performance in hippocampus, cortex and brain segmentation
    Wang, H; Das, S; Suh, J; Altinay, M; Pluta, J; Craige, C; Avants, B; Yushkevich, P
  • Adaptive segmentation of MRI data
    Wells, W; Kikinis, R; Grimson, W; Jolesz, F
  • A discriminative model-constrained EM approach to 3D MRI brain tissue classification and intensity non-uniformity correction
    Wels, M; Zheng, Y; Huber, M; Hornegger, J; Comaniciu, D
  • MRI-PET registration with automated algorithm
    Woods, R; Mazziotta, J; Cherry, S
  • Variational Bayes inference of spatial mixture models for segmentation
    Woolrich, M; Behrens, T
  • A novel framework for segmentation of deep brain structures based on Markov dependence tree
    Wu, J; Chung, A
  • White matter lesion segmentation based on feature joint occurrence probability and χ 2 random field theory from magnetic resonance (MR) images
    Yang, F; Shan, ZY; Kruggel, F
  • Neighbor-constrained segmentation with level set based 3D deformable models
    Yang, J; Staib, L; Duncan, J
  • User-guided 3D active contour segmentation of anatomical structures: significantly improved efficiency and reliability
    Yushkevich, PA; Piven, J; Hazlett, H.C; Smith, R.G; Ho, S; Gee, JC; Gerig, G
  • Segmentation of subcortical brain structures using fuzzy templates
    Zhou, J; Rajapakse, J
  • Region competition: unifying snake/balloon, region growing and Bayes/MDL/energy for multi-band image segmentation
    Zhu, S; Yuille, A