SU-D-BRA-04: Computerized Framework for Marker-Less Localization of Anatomical Feature Points in Range Images Based On Differential Geometry Features for Image-Guided Radiation Therapy

2016 ◽  
Vol 43 (6Part4) ◽  
pp. 3340-33340
Author(s):  
M Soufi ◽  
H Arimura ◽  
K Nakamura ◽  
T Hirose ◽  
Y Umezu ◽  
...  
2012 ◽  
Vol 2012 ◽  
pp. 1-8
Author(s):  
Qingsong Zhu ◽  
Jia Gu ◽  
Yaoqin Xie

A novel deformable registration algorithm is proposed in the application of radiation therapy. The algorithm starts with autodetection of a number of points with distinct tissue features. The feature points are then matched by using the scale invariance features transform (SIFT) method. The associated feature point pairs are served as landmarks for the subsequent thin plate spline (TPS) interpolation. Several registration experiments using both digital phantom and clinical data demonstrate the accuracy and efficiency of the method. For the 3D phantom case, markers with error less than 2 mm are over 85% of total test markers, and it takes only 2-3 minutes for 3D feature points association. The proposed method provides a clinically practical solution and should be valuable for various image-guided radiation therapy (IGRT) applications.


2012 ◽  
Vol 57 (16) ◽  
pp. 5187-5204 ◽  
Author(s):  
Dengwang Li ◽  
Hongsheng Li ◽  
Honglin Wan ◽  
Jinhu Chen ◽  
Guanzhong Gong ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document