Docteur de l'université Automatic Segmentation and Shape Analysis ...

More documents

Recommendations

Info

24 Chapter 2 Literature Review amygdala structures. It is initialized by the manual definition of a bounding box ROI and the seeds placed by the operator in each of the structures. The region growing is guided by the landmark and boundary detection based on extensive use of anatomical priors and image features. The deformation of the region is regularized by Markov random field (MRF), solved using iterative conditional modes algorithm (Besag, 1993). With the automatic definition of the seed point, the fast marching for automated segmentation of the hippocampus (FMASH) by Bishop et al. (2011) propagates the region along the path with smallest resistance defined by a potential function of image intensity using the 3D fast marching method (Sethian, 1996; Deschamps and Cohen, 2000). 2.1.2.2 Shape and appearance based methods Active shape models (ASM, Cootes et al., 1995) are used in medical image segmentation by fitting a parametric shape model to automatically detected image features or manually defined landmarks (Shen et al., 2002). Using shape information, the elastic deformation of the model to match the intensity profile can be restricted to a prior shape subspace learned from the training set (Kelemen et al., 1999). Knowledge of relative position and distance between anatomical structures, and texture descriptors have also been added to the ASM segmentation of hippocampus (Pitiot et al., 2004). A shape-intensity joint prior model for both hippocampus and amygdala (Yang and Duncan, 2004) has been developed with neighbor constraints and the level set formulation of shape (Yang et al., 2004). The active appearance model (AAM, Cootes et al., 2001) is a generative model that accounts for the image intensity and texture, i.e. the ‘appearance,’ in addition to the shape structure of the landmarks. Using the image intensity profile along the normal of the structure boundary, the profile appearance model (Babalola et al., 2007, 2008, 2009) produces the segmentation by matching the model to the image minimizing the square of residual differences. A Bayesian approach for AAM method models the conditional distribution of intensity given shape, and the segmentation is obtained by the MAP estimation of the shape given image
Chapter 2 Literature Review 25 intensities (Patenaude et al., 2011; the implementation is available from FMRIB Software Library, Smith et al., 2004; Woolrich et al., 2009) The state-of-the-art segmentation method publicly available in the FreeSurfer package (Dale et al., 1999; Fischl et al., 1999) labels 37 areas for the whole brain, including 18 subcortical structures. Based on the nonstationary anisotropic MRF modeling of the segmentation, it uses the spatial information from a template in the Talairach space, and a nonlinear transform to account for the inter-subject anatomical variability (Fischl et al., 2002). Forward models of the imaging process are embedded in the segmentation method to achieve the sequence independence (Fischl et al., 2004). 2.1.2.3 Atlas based methods Atlas based segmentation methods are widely employed in medical image analysis. Using manually delineated atlas as gold standard, this method transform the label map of the atlas to the query image by the registration algorithms from the atlas to the query. Registration methods such as elastic (Miller et al., 1993; Iosifescu et al., 1997; Christensen and Johnson, 2001), fluid (Haller et al., 1996, 1997; Hogan et al., 2000; Crum et al., 2001), and optical flow based registration (Baillard et al., 2001; Dawant et al., 1999; Hartmann et al., 1999) have been involved in matching the image with the atlas. In ANIMAL framework (Collins et al., 1995; Collins and Evans, 1997), the subject image is used as the source, and the atlas as the target in the non-rigid registration, and the mapping of the labels is achieved by the inverse transformation recovered by ANIMAL. Based on an initial FreeSurfer labeling, the method by Khan et al. (2008) uses the Large Deformation Diffeomor- phic Metric Mapping (LDDMM, Beg et al., 2005) to search for optimal nonlinear transform between the image and the atlas. Appearance model based methods have been proposed to guide the deformation (Duchesne et al., 2002; Klemencic et al., 2004). Besides the atlas of segmented individual, probabilistic atlases are also used in segmentation, providing the spatial priors such as in the Bayesian
Page 1: UNIVERSITE DE BOURGOGNE U.F.R. SCIE
Page 5 and 6: Résumé L’objectif de cette thè
Page 7 and 8: Abstract The aim of this thesis is
Page 9 and 10: TABLE DES MATIÈRES Acknowledgement
Page 11: TABLE DES MATIÈRES xi 4.1.4.3 Spec
Page 15 and 16: LISTE DES FIGURES 1.1 Cortical atro
Page 17: LISTE DES FIGURES xvii 5.6 The accu
Page 20 and 21: 2 Chapter 1 Introduction The resear
Page 22 and 23: 4 Chapter 1 Introduction .β.α .γ
Page 24 and 25: 6 Chapter 1 Introduction 1.1.2 Hipp
Page 26 and 27: 8 Chapter 1 Introduction Figure 1.4
Page 28 and 29: 10 Chapter 1 Introduction Functiona
Page 30 and 31: 12 Chapter 1 Introduction backgroun
Page 32 and 33: 14 Chapter 1 Introduction Figure 1.
Page 35 and 36: Chapter 2 Literature Review In this
Page 37 and 38: Chapter 2 Literature Review 19 Figu
Page 39 and 40: Chapter 2 Literature Review 21 Figu
Page 41: Chapter 2 Literature Review 23 does
Page 45 and 46: Chapter 2 Literature Review 27 In t
Page 47 and 48: Chapter 2 Literature Review 29 Wolz
Page 49 and 50: Chapter 2 Literature Review 31 . Pr
Page 51 and 52: Chapter 2 Literature Review 33 The
Page 53 and 54: Chapter 2 Literature Review 35 2.2.
Page 55 and 56: Chapter 2 Literature Review 37 2.2.
Page 57 and 58: Chapter 2 Literature Review 39 Apar
Page 59: Chapter 2 Literature Review 41 spec
Page 62 and 63: 44 Chapter 3 Hippocampal segmentati
Page 90 and 91: 72 Chapter 4 Statistical shape mode
Page 92 and 93:
74 Chapter 4 Statistical shape mode
Page 94 and 95:
Page 96 and 97:
Page 98 and 99:
Page 100 and 101:
Page 102 and 103:
Page 104 and 105:
Page 106 and 107:
Page 108 and 109:
Page 110 and 111:
Page 112 and 113:
Page 114 and 115:
Page 116 and 117:
Page 118 and 119:
100 Chapter 4 Statistical shape mod
Page 120 and 121:
Page 122 and 123:
Page 124 and 125:
Page 127 and 128:
Chapter 5 Quantitative shape analys
Page 129 and 130:
Page 131:
Page 134 and 135:
116 Chapter 5 Quantitative shape an
Page 136 and 137:
Page 138 and 139:
Page 140 and 141:
Page 142 and 143:
Page 144 and 145:
Page 146 and 147:
Page 148 and 149:
Page 150 and 151:
Page 152 and 153:
Page 155 and 156:
Chapter 6 Conclusions Topics in med
Page 157 and 158:
Chapter 6 Conclusions 139 Given the
Page 159:
Chapter 6 Conclusions 141 6.2.3 Sha
Page 162 and 163:
144 LIST OF PUBLICATIONS using dive
Page 164 and 165:
146 BIBLIOGRAPHY Alzheimer, A. (191
Page 166 and 167:
148 BIBLIOGRAPHY Baillard, C., Hell
Page 168 and 169:
150 BIBLIOGRAPHY of post mortem mag
Page 170 and 171:
152 BIBLIOGRAPHY B. (2008). Three-d
Page 172 and 173:
154 BIBLIOGRAPHY Cootes, T. F., Tay
Page 174 and 175:
156 BIBLIOGRAPHY head in MR images
Page 176 and 177:
158 BIBLIOGRAPHY Evans, A. C., Coll
Page 179 and 180:
BIBLIOGRAPHY 161 Ghanei, A., Soltan
Page 181 and 182:
BIBLIOGRAPHY 163 Heckemann, R. A.,
Page 183 and 184:
BIBLIOGRAPHY 165 R. C. (2003). MRI
Page 185 and 186:
BIBLIOGRAPHY 167 Konrad, C., Ukas,
Page 187 and 188:
BIBLIOGRAPHY 169 Mahony, R. and Man
Page 189 and 190:
BIBLIOGRAPHY 171 disease, mild cogn
Page 191 and 192:
BIBLIOGRAPHY 173 Petersen, R. C., S
Page 193 and 194:
BIBLIOGRAPHY 175 Rorden, C. and Bre
Page 195 and 196:
BIBLIOGRAPHY 177 Shen, K., Bourgeat
Page 197 and 198:
BIBLIOGRAPHY 179 Barillot, C., Hayn
Page 199 and 200:
BIBLIOGRAPHY 181 Tzourio-Mazoyer, N
Page 201 and 202:
BIBLIOGRAPHY 183 Vos, F. M., de Bru
Page 203 and 204:
BIBLIOGRAPHY 185 Woolrich, M. W., J
show all

Docteur de l'université Automatic Segmentation and Shape Analysis ...

You also want an ePaper? Increase the reach of your titles

Delete template?

Save as template?