Fuzzy affinity induced curve evolution

Ying Zhuge; Jayaram K. Udupa; Robert W. Miller

doi:10.1117/12.843793

12 March 2010 Fuzzy affinity induced curve evolution

Ying Zhuge, Jayaram K. Udupa, Robert W. Miller

Proceedings Volume 7623, Medical Imaging 2010: Image Processing; 76234A (2010) https://doi.org/10.1117/12.843793
Event: SPIE Medical Imaging, 2010, San Diego, California, United States

Abstract

In this paper, we present a fuzzy affinity induced curve evolution method for image segmentation without the need for solving PDEs, thereby making level set implementations vastly more efficient. We make use of fuzzy affinity that has been employed in fuzzy connectedness methods as a speed function for curve evolution. The fuzzy affinity consists of two components, namely homogeneity-based affinity and object-feature-based affinity, which take account both boundary gradient and object region information. Ball scale - a local morphometric structure - has been used for image noise suppression. We use a similar strategy for curve evolution as the method in,1 but simplify the voxel switching mechanism where only one linked list is used to implicitly represent the evolving curve. We have presented several studies to evaluate the performance of the method based on brain MR and lung CT images. These studies demonstrate high accuracy and efficiency of the proposed method.

Citation Download Citation

Ying Zhuge, Jayaram K. Udupa, and Robert W. Miller "Fuzzy affinity induced curve evolution", Proc. SPIE 7623, Medical Imaging 2010: Image Processing, 76234A (12 March 2010); https://doi.org/10.1117/12.843793

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