Medical Imaging is a vital tool within the areas of diagnostic, planning, implementation and evaluation of surgical and radiotherapy procedures. For this reason, it is helpful to integrate the information from different medical images by aligning them according to their correlation or information in common, with the aim of getting the best spatial coincidence. The algorithm presented in this work has been developed within the context of the AR-PET project belonging to the National Atomic Energy Commission (CNEA in Spanish). The key in the process of developing the algorithm is mutual information and the Metropolis technique as a similarity measure and search method respectively. The 2D fusion imaging has been achieved by maximizing mutual information and carrying out rigid transformations of rotation and translation with satisfactory results with respect to their geometric alignment.
-
Notifications
You must be signed in to change notification settings - Fork 3
ahestevenz/ap-image-register
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
C++ class for 2D multimodal image registration
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published