Capturing the multiscale anatomical shape variability with polyaffine transformation trees

被引:28
作者
Seiler, Christof [1 ,2 ]
Pennec, Xavier [2 ]
Reyes, Mauricio [1 ]
机构
[1] Univ Bern, Inst Surg Technol & Biomech, CH-3012 Bern, Switzerland
[2] INRIA Sophia Antipolis, Asclepios Res Grp, Sophia Antipolis, France
基金
瑞士国家科学基金会;
关键词
Parametrization of diffeomorphisms; Shape statistics; Locally affine registration; Multiscale hierarchy; Trees; NONRIGID REGISTRATION; BONE PLATES; FRAMEWORK; ALLOGRAFTS; FRACTURES;
D O I
10.1016/j.media.2012.05.011
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Mandible fractures are classified depending on their location. In clinical practice, locations are grouped into regions at different scales according to anatomical, functional and esthetic considerations. Implant design aims at defining the optimal implant for each patient. Emerging population-based techniques analyze the anatomical variability across a population and perform statistical analysis to identify an optimal set of implants. Current efforts are focused on finding clusters of patients with similar characteristics and designing one implant for each cluster. Ideally, the description of anatomical variability is directly connected to the clinical regions. This connection is what we present here, by introducing a new registration method that builds upon a tree of locally affine transformations that describes variability at different scales. We assess the accuracy of our method on 146 CT images of femurs. Two medical experts provide the ground truth by manually measuring six landmarks. We illustrate the clinical importance of our method by clustering 43 CT images of mandibles for implant design. The presented method does not require any application-specific input, which makes it attractive for the analysis of other multiscale anatomical structures. At the core of our new method lays the introduction of a new basis for stationary velocity fields. This basis has very close links to anatomical substructures. In the future, this method has the potential to discover the hidden and possibly sparse structure of the anatomy. (c) 2012 Elsevier B.V. All rights reserved.
引用
收藏
页码:1371 / 1384
页数:14
相关论文
共 35 条
[1]  
Martín-Fernández MA, 2009, LECT NOTES COMPUT SC, V5761, P156, DOI 10.1007/978-3-642-04268-3_20
[2]   Polyrigid and polyaffine transformations: A novel geometrical tool to deal with non-rigid deformations - Application to the registration of histological slices [J].
Arsigny, V ;
Pennec, X ;
Ayache, N .
MEDICAL IMAGE ANALYSIS, 2005, 9 (06) :507-523
[3]  
Arsigny V, 2006, LECT NOTES COMPUT SC, V4190, P924
[4]   A Fast and Log-Euclidean Polyaffine Framework for Locally Linear Registration [J].
Arsigny, Vincent ;
Commowick, Olivier ;
Ayache, Nicholas ;
Pennec, Xavier .
JOURNAL OF MATHEMATICAL IMAGING AND VISION, 2009, 33 (02) :222-238
[5]  
Bonaretti S., 2011, MESH PROC MED IM AN
[6]  
Bou-Sleiman H, 2011, LECT NOTES COMPUT SC, V6892, P409, DOI 10.1007/978-3-642-23629-7_50
[7]   Hierarchical adaptive local affine registration for fast and robust respiratory motion estimation [J].
Buerger, Christian ;
Schaeffter, Tobias ;
King, Andrew P. .
MEDICAL IMAGE ANALYSIS, 2011, 15 (04) :551-564
[8]   Iconic feature based nonrigid registration: the PASHA algorithm [J].
Cachier, P ;
Bardinet, E ;
Dormont, D ;
Pennec, X ;
Ayache, N .
COMPUTER VISION AND IMAGE UNDERSTANDING, 2003, 89 (2-3) :272-298
[9]   Design and experimental evaluation of adjustable bone plates for mandibular fracture fixation [J].
Cervantes, Thomas M. ;
Slocum, Alexander H., Jr. ;
Seldin, Edward B. .
JOURNAL OF BIOMECHANICS, 2012, 45 (01) :172-178
[10]   An efficient locally affine framework for the smooth registration of anatomical structures [J].
Commowick, O. ;
Arsigny, V. ;
Isambert, A. ;
Costa, J. ;
Dhermain, F. ;
Bidault, F. ;
Bondiau, P. -Y. ;
Ayache, N. ;
Malandain, G. .
MEDICAL IMAGE ANALYSIS, 2008, 12 (04) :427-441