Title :
Robust image registration based on a Partition of Unity Finite Element Method
Author :
Somphone, O. ; Ebeid, S. Makram ; Cohen, L.D.
Author_Institution :
Medisys Res. Lab., Philips Healthcare, Suresnes
Abstract :
In this paper, we present a robust, hierarchical partition of unity finite element method (PUFEM) to compute the transformation between two images, which is represented by a non-rigid, locally polynomial displacement field. The partition of unity property offers an efficient optimization scheme by breaking down the global minimization of the mismatch energy into independent, local minimizations. Moreover, the regularization introduced by our approach enables us to control the range of the smoothness. Our method was applied to cardiac ultrasound image sequences to propagate the segmentation of anatomical structures of interest.
Keywords :
biomedical ultrasonics; cardiology; finite element analysis; image registration; image segmentation; medical image processing; anatomical structure-of-interest; cardiac ultrasound image sequences; image registration; image segmentation; partition-of-unity finite element method; Finite element methods; Image registration; Image segmentation; Image sequences; Mathematical model; Medical services; Optical propagation; Polynomials; Robustness; Ultrasonic imaging; Image registration; cardiac ultrasound; optical flow; partition of unity; robust estimation;
Conference_Titel :
Biomedical Imaging: From Nano to Macro, 2008. ISBI 2008. 5th IEEE International Symposium on
Conference_Location :
Paris
Print_ISBN :
978-1-4244-2002-5
Electronic_ISBN :
978-1-4244-2003-2
DOI :
10.1109/ISBI.2008.4541198