---

An ITK Implementation of Physics-based Non-rigid Registration Method

 

Yixun Liu, Andriy Kot, Fotios Drakopoulos, Andriy Fedorov, Andinet Enquobahrie, Olivier Clatz and Nikos Chrisochoides.

 

Published in Insight Journal, 2012

 

Abstract

 

As part of the ITK v4 project efforts, we have developed ITK filters for physics-based non-rigid registration (PBNRR), which satisfies the following requirements: account for tissue properties in the registration, improve accuracy compared to rigid registration, and reduce execution time using GPU and multi-core accelerators. The implementation has three main components: (1) Feature Point Selection, (2) Block Matching (mapped to both multi-core and GPU processors), and (3) a Robust Finite Element Solver. The use of multi-core and GPU accelerators in ITK v4 provides substantial performance improvements. For example, in average for the non- rigid registration of brain MRIs, the performance of the Block Matching filter is about 12 times faster when 12 hyperthreaded multi-cores are used and about 540 times faster when the Quadro 6000 with 448 threads is used in Dell Workstation.