A fast 3D region growing approach for CT angiography applications

Zhen Ye; Zhongmin Lin; Cheng-chang Lu

doi:10.1117/12.533741

12 May 2004 A fast 3D region growing approach for CT angiography applications

Zhen Ye, Zhongmin Lin, Cheng-chang Lu

Proceedings Volume 5370, Medical Imaging 2004: Image Processing; (2004) https://doi.org/10.1117/12.533741
Event: Medical Imaging 2004, 2004, San Diego, California, United States

Abstract

Region growing is one of the most popular methods for low-level image segmentation. Many researches on region growing have focused on the definition of the homogeneity criterion or growing and merging criterion. However, one disadvantage of conventional region growing is redundancy. It requires a large memory usage, and the computation-efficiency is very low especially for 3D images. To overcome this problem, a non-recursive single-pass 3D region growing algorithm named SymRG is implemented and successfully applied to 3D CT angiography (CTA) applications for vessel segmentation and bone removal. The method consists of three steps: segmenting one-dimensional regions of each row; doing region merging to adjacent rows to obtain the region segmentation of each slice; and doing region merging to adjacent slices to obtain the final region segmentation of 3D images. To improve the segmentation speed for very large volume 3D CTA images, this algorithm is applied repeatedly to newly updated local cubes. The next new cube can be estimated by checking isolated segmented regions on all 6 faces of the current local cube. This local non-recursive 3D region-growing algorithm is memory-efficient and computation-efficient. Clinical testings of this algorithm on Brain CTA show this technique could effectively remove whole skull, most of the bones on the skull base, and reveal the cerebral vascular structures clearly.

Citation Download Citation

Zhen Ye, Zhongmin Lin, and Cheng-chang Lu "A fast 3D region growing approach for CT angiography applications", Proc. SPIE 5370, Medical Imaging 2004: Image Processing, (12 May 2004); https://doi.org/10.1117/12.533741

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available