Abstract
A new method for the estimation of the intensity distributions of the images prior to normalized mutual information (NMI) based registration is presented. Our method is based on the K-means clustering algorithm as opposed to the generally used equidistant binning method. K-means clustering is a binning method with a variable size for each bin which is adjusted to achieve a natural clustering. Registering clinical MR-CT and MR-PET images with K-means clustering based intensity distribution estimation shows that a significant reduction in computational time without loss of accuracy as compared to the standard equidistant binning based registration is possible. Further inspection shows a reduction in the NMI variance and a reduction in local maxima for K-means clustering based NMI registration as opposed to equidistant binning based NMI registration.
Original language | English |
---|---|
Title of host publication | Proceedings of SPIE - The International Society for Optical Engineering |
Editors | M. Sonka, J.M. Fitzpatrick |
Pages | 1072-1080 |
Number of pages | 9 |
Volume | 5032 II |
DOIs | |
Publication status | Published - 2003 |
Externally published | Yes |
Event | 2003 Medical Imaging : Image Processing - San Diego, United States Duration: 17 Feb 2003 → 20 Feb 2003 |
Conference
Conference | 2003 Medical Imaging : Image Processing |
---|---|
Country/Territory | United States |
City | San Diego |
Period | 17/02/03 → 20/02/03 |