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. |