Medical image registration based on distinctive image features from scale-invariant (SIFT) key-points

2005 ◽  
Vol 1281 ◽  
pp. 1292 ◽  
Author(s):  
M. Moradi ◽  
P. Abolmaesumi
Keyword(s):  
Image Registration ◽  
Medical Image ◽  
Image Features ◽  
Medical Image Registration ◽  
Scale Invariant ◽  
Key Points

scholarly journals Nonrigid Registration of Lung CT Images Based on Tissue Features

2013 ◽  
Vol 2013 ◽  
pp. 1-7 ◽  
Author(s):  
Rui Zhang ◽  
Wu Zhou ◽  
Yanjie Li ◽  
Shaode Yu ◽  
Yaoqin Xie
Keyword(s):  
Image Registration ◽  
Medical Image ◽  
Feature Detection ◽  
Ct Images ◽  
Image Process ◽  
Scale Invariant ◽  
Nonrigid Image Registration ◽  
Breathing Motion ◽  
Key Points ◽  
High Gradients

Nonrigid image registration is a prerequisite for various medical image process and analysis applications. Much effort has been devoted to thoracic image registration due to breathing motion. Recently, scale-invariant feature transform (SIFT) has been used in medical image registration and obtained promising results. However, SIFT is apt to detect blob features. Blobs key points are generally detected in smooth areas which may contain few diagnostic points. In general, diagnostic points used in medical image are often vessel crossing points, vascular endpoints, and tissue boundary points, which provide abundant information about vessels and can reflect the motion of lungs accurately. These points generally have high gradients as opposed to blob key points and can be detected by Harris. In this work, we proposed a hybrid feature detection method which can detect tissue features of lungs effectively based on Harris and SIFT. In addition, a novel method which can remove mismatched landmarks is also proposed. A series of thoracic CT images are tested by using the proposed algorithm, and the quantitative and qualitative evaluations show that our method is statistically significantly better than conventional SIFT method especially in the case of large deformation of lungs during respiration.

Computing the Medical Image Registration Using Meta-Heuristics

2014 ◽  
Vol 643 ◽  
pp. 237-242 ◽  
Author(s):  
Tahari Abdou El Karim ◽  
Bendakmousse Abdeslam ◽  
Ait Aoudia Samy
Keyword(s):  
Image Processing ◽  
Genetic Algorithms ◽  
Simulated Annealing ◽  
Image Registration ◽  
Cost Function ◽  
Population Genetic ◽  
Medical Image ◽  
Medical Image Registration ◽  
Anatomical Structures

The image registration is a very important task in image processing. In the field of medical imaging, it is used to compare the anatomical structures of two or more images taken at different time to track for example the evolution of a disease. Intensity-based techniques are widely used in the multi-modal registration. To have the best registration, a cost function expressing the similarity between these images is maximized. The registration problem is reduced to the optimization of a cost function. We propose to use neighborhood meta-heuristics (tabu search, simulated annealing) and a meta-heuristic population (genetic algorithms). An evaluation step is necessary to estimate the quality of registration obtained. In this paper we present some results of medical image registration

Medical image registration using sparse coding of image patches

2016 ◽  
Vol 73 ◽  
pp. 56-70 ◽  
Author(s):  
Maryam Afzali ◽  
Aboozar Ghaffari ◽  
Emad Fatemizadeh ◽  
Hamid Soltanian-Zadeh
Keyword(s):  
Image Registration ◽  
Sparse Coding ◽  
Medical Image ◽  
Medical Image Registration ◽  
Image Patches

Multi-Modal Medical Image Registration of by Combining Improved Mean Shift and RPM

2012 ◽  
Vol 239-240 ◽  
pp. 1472-1475
Author(s):  
Dan Ai ◽  
Jing Li Shi ◽  
Jun Jun Cao ◽  
Hong Yan Zhong
Keyword(s):  
Image Registration ◽  
Medical Image ◽  
Mean Shift ◽  
Decisive Role ◽  
Experimental Results ◽  
Medical Image Registration ◽  
Image Content ◽  
Point Matching ◽  
Target Mode ◽  
Convergence Process

Landmark correspondence plays a decisive role in the landmark-based multi-modality image registration. We combine RPM (Robust Point Matching) and improved Mean Shift to estimate the correspondence of landmarks in images. We improve the target mode and bandwidth used in Mean Shift, and we also perform RPM to estimate the initial landmark correspondence. Next, we use improved Mean Shift to adjust corresponding relations between points. Our method is benefit to make corresponding relations between points more accurate and impels the convergence process of RPM to be related to the image content. Experimental results show that our method can achieve accurate registration of the multi-modal images.

Sign in / Sign up

Export Citation Format

Share Document