Normalized mutual information based registration using k-means clustering and shading correction

In this paper the influence of intensity clustering and shading correction on mutual information based image registration is studied. Instead of the generally used equidistant re-binning, we use k-means clustering in order to achieve a more natural binning of the intensity distribution. Secondly, im...

Full description

Saved in:
Bibliographic Details
Published in:Medical image analysis 2006-06, Vol.10 (3), p.432-439
Main Authors: Knops, Z.F., Maintz, J.B.A., Viergever, M.A., Pluim, J.P.W.
Format: Article
Language:English
Subjects:
Algorithms
Artificial Intelligence
Brain - anatomy & histology
Cluster Analysis
Humans
Image Enhancement - methods
Image Interpretation, Computer-Assisted - methods
Image registration
Imaging, Three-Dimensional - methods
Information Storage and Retrieval - methods
Information Theory
k-Means clustering
Normalized mutual information
Pattern Recognition, Automated - methods
Reproducibility of Results
Robustness
Sensitivity and Specificity
Shading correction
Subtraction Technique
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper the influence of intensity clustering and shading correction on mutual information based image registration is studied. Instead of the generally used equidistant re-binning, we use k-means clustering in order to achieve a more natural binning of the intensity distribution. Secondly, image inhomogeneities occurring notably in MR images can have adverse effects on the registration. We use a shading correction method in order to reduce these effects. The method is validated on clinical MR, CT and PET images, as well as synthetic MR images. It is shown that by employing clustering with inhomogeneity correction the number of misregistrations is reduced without loss of accuracy thus increasing robustness as compared to the standard non-inhomogeneity corrected and equidistant binning based registration.
ISSN:1361-8415
1361-8423
DOI:10.1016/j.media.2005.03.009