18 March 2015 Comparison of optimization strategy and similarity metric in atlas-to-subject registration using statistical deformation model
Author Affiliations +
Abstract
A robust atlas-to-subject registration using a statistical deformation model (SDM) is presented. The SDM uses statistics of voxel-wise displacement learned from pre-computed deformation vectors of a training dataset. This allows an atlas instance to be directly translated into an intensity volume and compared with a patient’s intensity volume. Rigid and nonrigid transformation parameters were simultaneously optimized via the Covariance Matrix Adaptation – Evolutionary Strategy (CMA-ES), with image similarity used as the objective function. The algorithm was tested on CT volumes of the pelvis from 55 female subjects. A performance comparison of the CMA-ES and Nelder-Mead downhill simplex optimization algorithms with the mutual information and normalized cross correlation similarity metrics was conducted. Simulation studies using synthetic subjects were performed, as well as leave-one-out cross validation studies. Both studies suggested that mutual information and CMA-ES achieved the best performance. The leave-one-out test demonstrated 4.13 mm error with respect to the true displacement field, and 26,102 function evaluations in 180 seconds, on average.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Y. Otake, Y. Otake, R. J. Murphy, R. J. Murphy, R. B. Grupp, R. B. Grupp, Y. Sato, Y. Sato, R. H. Taylor, R. H. Taylor, M. Armand, M. Armand, } "Comparison of optimization strategy and similarity metric in atlas-to-subject registration using statistical deformation model", Proc. SPIE 9415, Medical Imaging 2015: Image-Guided Procedures, Robotic Interventions, and Modeling, 94150Q (18 March 2015); doi: 10.1117/12.2081754; https://doi.org/10.1117/12.2081754
PROCEEDINGS
6 PAGES


SHARE
Back to Top