ABSORB: Atlas building by Self-Organized Registration and Bundling

• Published in: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition pp. 2785 - 2790
• Main Authors: Hongjun Jia, Guorong Wu, Qian Wang, Dinggang Shen
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2010
• Subjects: Biomedical imaging; Buildings; Computer science; Cost function; Image analysis; Image registration; Optimization methods; Radiology; Registers; Robustness

A novel groupwise registration framework, called Atlas Building by Self-Organized Registration and Bundling (ABSORB), is proposed in this paper. In this framework, the global structure of relative subject image distribution is preserved during the registration by constraining each subject to deform...