Technical Program

Paper Detail

Paper:	TH-PM-PS3.8
Session:	Cardiac and Vascular Imaging
Time:	Thursday, April 6, 15:20 - 16:40
Presentation:	Poster
Title:	Automatic Extraction and Matching of Neonatal Cerebral Vasculature
Authors:	Hui Xue; Hammersmith Hospital / Imperial College London
	Christina Malamateniou; Hammersmith Hospital / Imperial College London
	Joanna Allsop; Hammersmith Hospital / Imperial College London
	Latha Srinivasan; Hammersmith Hospital / Imperial College London
	Joseph Hajnal; Hammersmith Hospital / Imperial College London
	Daniel Rueckert; Hammersmith Hospital / Imperial College London
Abstract:	This paper presents a method for extracting and matching the neonatal cerebral vasculature from MRA-TOF images. The vasculature is first extracted using an automatic ridge traversal algorithm. Extracted vessel segments are then connected iteratively to compose a vessel tree that is automatically labeled. An indirect vasculature registration method is used to recover global deformation between two vessel trees and vessel matching is performed by comparing a cost function measuring average spatial distance between two vessel branches. The robustness and accuracy of vessel matching are improved by performing subtree registration using a robust bootstrap extension of the Iterative Closest Point (ICP) algorithm. Experiments show the effectiveness of the proposed methods for analysis arteries subject to change resulting from growth and development.

ISBI 2006 is sponsored by

and organized in cooperation with