2010 Summer Project Week Fiducial Deformable Registration
- MGH: Nadya Shusharina, Greg Sharp
We are developing methods for deformable image registration with landmark information. The goal is to improve the registration if misaligned areas are found.
Our approach for using the landmarks is to manually mark the distinct anatomical features by point landmarks after the automatic registration is done. Matching of landmarks is performed by two different methods. In one the optimization procedure is applied to the cost function containing an intensity-based data term and a landmark term, sum of squares of distances between fixed and moving landmarks. In another, an initial deformation field obtained from automatic registration is corrected by the field built on RBFs around the landmarks.
Our plan for the project week is to first try out <bar>,...
The code for the two methods of landmark matching has been implemented to our in house open source Plastimatch software. The methods have been validated on synthetic images and on lung CT scans obtained from NBIA data base. Statistical analysis for method validation has been performed on 4D CT scans obtained from http://www.dir-lab.com
This work will be delivered to the NA-MIC Kit as a (please select the appropriate options by noting YES against them below)
- ITK Module
- Slicer Module
- Extension -- commandline
- Extension -- loadable
- Other (YES) -- stand alone utility
- G. C. Sharp, R. Li, J. Wolfgang, G. TY Chen, M. Peroni, M. F. Spadea, S. Mori, J. Zhang, J. Shackleford, N. Kandasamy, Plastimatch - an open source software suite for radiotherapy image processing, In the proceedings of the 16th International Conference on the Use of Computers in Radiotherapy (ICCR 2010), Amsterdam, The Netherlands.
- Plastimatch. http://plastimatch.org