Title :
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
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;
Conference_Titel :
Intelligent Systems, 2009. GCIS '09. WRI Global Congress on
Conference_Location :
Xiamen
Print_ISBN :
978-0-7695-3571-5
DOI :
10.1109/GCIS.2009.250
