3 March 2017 Slice-to-volume parametric image registration models with applications to MRI-guided cardiac procedures
Author Affiliations +
Abstract
A mathematical formulation for intensity-based slice-to-volume registration is proposed. The approach is flexible and accommodates various regularization schemes, similarity measures, and optimizers. The framework is evaluated by registering 2D and 3D cardiac magnetic resonance (MR) images obtained in vivo, aimed at real- time MR-guided applications. Rigid-body and affine transformations are used to validate the parametric model. Target registration error (TRE), Jaccard, and Dice indices are used to evaluate the algorithm and demonstrate the accuracy of the registration scheme on both simulated and clinical data. Registration with the affine model appeared to be more robust than with the rigid model in controlled cases. By simply extending the rigid model to an affine model, alignment of the cardiac region generally improved, without the need for complex dissimilarity measures or regularizers.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
L.W. Lorraine Ma, L.W. Lorraine Ma, Mehran Ebrahimi, Mehran Ebrahimi, } "Slice-to-volume parametric image registration models with applications to MRI-guided cardiac procedures", Proc. SPIE 10135, Medical Imaging 2017: Image-Guided Procedures, Robotic Interventions, and Modeling, 1013520 (3 March 2017); doi: 10.1117/12.2254597; https://doi.org/10.1117/12.2254597
PROCEEDINGS
16 PAGES


SHARE
Back to Top