13 March 2010 Fuzzy affinity induced curve evolution
Author Affiliations +
Proceedings Volume 7623, Medical Imaging 2010: Image Processing; 76234A (2010); doi: 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.
© (2010) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ying Zhuge, Jayaram K. Udupa, Robert W. Miller, "Fuzzy affinity induced curve evolution", Proc. SPIE 7623, Medical Imaging 2010: Image Processing, 76234A (13 March 2010); doi: 10.1117/12.843793; https://doi.org/10.1117/12.843793
PROCEEDINGS
8 PAGES


SHARE
KEYWORDS
Image segmentation

Fuzzy logic

Magnetic resonance imaging

Brain

Gaussian filters

Lung

Tissues

Back to Top