Point to Point Registration Based on MRI sequences

Author

Jin, Quan ; Cheng, Yuanzhi ; Guo, Changyong ; Li, Guixian ; Sato, Yoshinobu

Author_Institution

Sch. of Mechatron. Eng., Harbin Inst. of Technol., Harbin, China

Volume

3

fYear

2009

fDate

19-21 May 2009

Firstpage

381

Lastpage

384

Abstract

The purpose of this study is to develop a new method for the registration of 3D cartilage plates in the MR data set. This technique traces local cartilage thickness changes over time. In a first rough registration step, the principal axes transformation (PAX) and landmark methods are used. In the second step, an improved iterative closest point (ICP) method is used. The point sets from segmentation of MRI sequences are registratered in these processes. The experimental results demonstrate the effectiveness of this method for the registration of the MRI of knee cartilage over time based on the cartilage and bone interfaces.

Keywords

biology computing; biomedical MRI; image registration; image sequences; 3D cartilage plate; MRI sequences segmentation; bone interface; iterative closest point; knee cartilage; point to point registration; principal axes transformation; Biomedical imaging; Bones; Clouds; Image sequence analysis; Intelligent systems; Iterative closest point algorithm; Joints; Knee; Magnetic resonance imaging; Mechatronics; ICP; Landmark; MRI; registration;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Systems, 2009. GCIS '09. WRI Global Congress on

Conference_Location

Xiamen

Print_ISBN

978-0-7695-3571-5

Type

conf

DOI

10.1109/GCIS.2009.250

Filename

5209121