Nonrigid medical image registration technique as a composition of local warpings

被引：10

作者：

Castellanos, NP ^{[1
]}

Angel, PLD

Medina, V

机构：

[1] Univ Autonoma Metropolitana Iztapalapa, Elect Engn Dept, Mexico City 09340, DF, Mexico

[2] Ctr Invest & Matemat, Guanajuato 36240, Mexico

来源：

PATTERN RECOGNITION | 2004年 / 37卷 / 11期

关键词：

hybrid genetic algorithm; nonrigid image registration; nonlinear spatial transformation; normalized mutual information;

D O I：

10.1016/j.patcog.2003.09.019

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We introduce a new technique for nonrigid image registration based on the composition of local deformations. The warping model is analyzed in order to guarantee continuity, differentiability and a one-to-one transformation by constraining the parameters of the nonlinear spatial transformation. A genetic algorithm solves the model by global optimization, handling constraints, and maximizing the normalized mutual information. The composition of local transformations goes throughout several levels of resolution, from coarse to fine. The performance of our technique was tested in synthetic and real medical images. The proposed method was always able to improve the similarity criterion between image pairs, demonstrating the robustness of the method for several modalities of images. (C) 2004 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.

引用

页码：2141 / 2154

页数：14

共 42 条

[1] Deformation of MR images using a local linear transformation [J].

Castellanos, P ;

del Angel, PL ;

Medina, V .

MEDICAL IMAGING: 2001: IMAGE PROCESSING, PTS 1-3, 2001, 4322 :909-916

[2] Volumetric transformation of brain anatomy [J].

Christensen, GE ;

Joshi, SC ;

Miller, MI .

IEEE TRANSACTIONS ON MEDICAL IMAGING, 1997, 16 (06) :864-877

[3] Spatial transformation and registration of brain images using elastically deformable models [J].

Davatzikos, C .

COMPUTER VISION AND IMAGE UNDERSTANDING, 1997, 66 (02) :207-222

[4] A physics-based coordinate transformation for 3-D image matching [J].

Davis, MH ;

Khotanzad, A ;

Flamig, DP ;

Harms, SE .

IEEE TRANSACTIONS ON MEDICAL IMAGING, 1997, 16 (03) :317-328

[5] Automatic fusion of freehand endoscopic brain images to three-dimensional surfaces: Creating stereoscopic panoramas [J].

Dey, D ;

Gobbi, DG ;

Slomka, PJ ;

Surry, KJM ;

Peters, TM .

IEEE TRANSACTIONS ON MEDICAL IMAGING, 2002, 21 (01) :23-30

[6] An evolutionary algorithm for the registration of 3-d surface representations [J].

Fischer, D ;

Kohlhepp, P ;

Bulling, F .

PATTERN RECOGNITION, 1999, 32 (01) :53-69

[7] On matching brain volumes [J].

Gee, JC .

PATTERN RECOGNITION, 1999, 32 (01) :99-111

[8] Three-dimensional multimodal brain warping using the demons algorithm and adaptive intensity corrections [J].

Guimond, A ;

Roche, A ;

Ayache, N ;

Meunier, J .

IEEE TRANSACTIONS ON MEDICAL IMAGING, 2001, 20 (01) :58-69

[9] Biomechanical modeling of the human head for physically based, nonrigid image registration [J].

Hagemann, A ;

Rohr, K ;

Stiehl, HS ;

Spetzger, U ;

Gilsbach, JM .

IEEE TRANSACTIONS ON MEDICAL IMAGING, 1999, 18 (10) :875-884

[10]

HAJNAL JV, 2001, MED IMAGE REGISTRATI, P12

← 1 2 3 4 5 →