SIFT and shape information incorporated into fluid model for non-rigid registration of ultrasound images

Authors:
Xuesong Lu;Su Zhang;Wei Yang;Yazhu Chen
Affiliations:
College of Biomedical Engineering, South-Central University for Nationalities, Wuhan 430074, PR China and Biomedical Instrument Institute, Shanghai Jiao Tong University, Shanghai 200240, PR China;Biomedical Instrument Institute, Shanghai Jiao Tong University, Shanghai 200240, PR China;Biomedical Instrument Institute, Shanghai Jiao Tong University, Shanghai 200240, PR China and School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, PR China;Biomedical Instrument Institute, Shanghai Jiao Tong University, Shanghai 200240, PR China
Venue:
Computer Methods and Programs in Biomedicine
Year:
2010

Citing 10
Cited 0

Principal Warps: Thin-Plate Splines and the Decomposition of Deformations

IEEE Transactions on Pattern Analysis and Machine Intelligence
Multiresolution elastic matching

Computer Vision, Graphics, and Image Processing
Using Points and Surfaces to Improve Voxel-Based Non-rigid Registration

MICCAI '02 Proceedings of the 5th International Conference on Medical Image Computing and Computer-Assisted Intervention-Part II
Fast Fluid Registration of Medical Images

VBC '96 Proceedings of the 4th International Conference on Visualization in Biomedical Computing
Image Denoising and Decomposition with Total Variation Minimization and Oscillatory Functions

Journal of Mathematical Imaging and Vision
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
A Performance Evaluation of Local Descriptors

IEEE Transactions on Pattern Analysis and Machine Intelligence
Nonrigid registration of brain MRI using NURBS

Pattern Recognition Letters
SIFT and shape context for feature-based nonlinear registration of thoracic CT images

CVAMIA'06 Proceedings of the Second ECCV international conference on Computer Vision Approaches to Medical Image Analysis
Deformable templates using large deformation kinematics

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Non-rigid registration of ultrasound images takes an important role in image-guided radiotherapy and surgery. Intensity-based method is popular in non-rigid registration, but it is sensitive to intensity variations and has problems with matching small structure features for the existence of speckles in ultrasound images. In this paper, we develop a new algorithm integrating the intensity and feature of ultrasound images. Both global shape information and local keypoint information extracted by scale invariant feature transform (SIFT) are incorporated into intensity similarity measure as the body force of viscous fluid model in a Bayesian framework. Experiments were performed on synthetic and clinical ultrasound images of breast and kidney. It is shown that shape and keypoint information significantly improves fluid model for non-rigid registration, especially for alignment of small structure features in accuracy.