A knowledge-guided active model method of skull segmentation on T1-weighted MR images

Shan, Zuyao Y., Hua, Chia-Ho, Ji, Qing, Parra, Carlos, Ying, Xiaofei, Krasin, Matthew J., Merchant, Thomas E., Kun, Larry E. and Reddick, Wilburn E. (2007). A knowledge-guided active model method of skull segmentation on T1-weighted MR images. In: , Medical Imaging 2007: Image Processing, Pts 1-3. Medical Imaging 2007 Conference, San Diego, United States, (65122R-1-65122R-6). 18-20 February, 2007.


Author Shan, Zuyao Y.
Hua, Chia-Ho
Ji, Qing
Parra, Carlos
Ying, Xiaofei
Krasin, Matthew J.
Merchant, Thomas E.
Kun, Larry E.
Reddick, Wilburn E.
Title of paper A knowledge-guided active model method of skull segmentation on T1-weighted MR images
Conference Paper Type Fully Published Paper
Conference name Medical Imaging 2007 Conference
DOI 10.1117/12.709801
Conference location San Diego, United States
Conference dates 18-20 February, 2007
Proceedings title Medical Imaging 2007: Image Processing, Pts 1-3
Journal name Proceedings of SPIE - International Society for Optical Engineering
Place published Bellingham, WA, United States
Publisher S P I E - International Society for Optical Engineering
Publication date 2007
Volume number 6512
Issue number Part 2
ISBN 978-0-8194-6630-3
ISSN 0277-786X; 1996-756X
Start page 65122R-1
End page 65122R-6
Total pages 6
Language eng
Abstract/Summary Skull is the anatomic landmark for patient set up of head radiation therapy. Skull is generally segmented from CT images because CT provides better definition of skull than MR imaging. In the mean time, radiation therapy is planned on MR images for soft tissue information. This study utilized a knowledge-guided active model (KAM) method to segmented skull on MR images in order to enable radiation therapy planning with MR images as the primary planning dataset. KAM utilized age-specific skull mesh models that segmented from CT images using a conditional region growing algorithm. Skull models were transformed to given MR images using an affine registration algorithm based on normalized mutual information. The transformed mesh models actively located skull boundaries by minimizing their total energy. The preliminary validation was performed on MR and CT images from five patients. The KAM segmented skulls were compared with those segmented from CT images. The average image similarity (kappa index) was 0.57. The initial validation showed that it was promising to segment skulls directly on MR images using KAM.
Keyword Registration
Segmentation
Mathematical morphology
Q-Index Code E1
Q-Index Status Provisional Code
Institutional Status Non-UQ

Document type: Conference Paper
Sub-type: Fully Published Paper
Collections: ERA 2012 Admin Only
Centre for Advanced Imaging Publications
 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in Thomson Reuters Web of Science Article
Scopus Citation Count Cited 0 times in Scopus Article
Google Scholar Search Google Scholar
Access Statistics: 31 Abstract Views  -  Detailed Statistics
Created: Mon, 05 Sep 2011, 18:02:31 EST by System User on behalf of Centre for Advanced Imaging