Seminar 2006 10 25 Capillary Segmentation
From CISSTwiki
CISST ERC Seminar
Capillary Active Contours and the Model of Interaction for Biomedical Image Segmentation
Date: Wednesday, October 25, 2006
Time: 12:00pm, Lunch will be served before the seminar.
Place: Maryland Hall 110
Speaker: Dr. Pingkun Yan
Title: Capillary Active Contours and the Model of Interaction for Biomedical Image Segmentation
Presentation slideshow: Power Point, 11MB ( info )
Abstract:
Segmentation is a fundamental operation of biomedical image analysis, which remains to be an open-end problem. Two novel biomedical image segmentation methods are presented in this talk. The first part of this talk presents a novel method for segmentation of blood vessels from volumetric magnetic resonance angiography (MRA).
The main difficulty of MRA image segmentation exists in getting the complex structure of vasculature and the thin blood vessels.
To solve these problems, a new capillary active contour is derived for MRA segmentation with the inspiration from capillary action. In this approach, the capillary action is modeled as an energy minimization process and then implemented using the level set method.
The second part of the talk describes a new model of interaction between neighboring structures. Instead of dealing with a single structure each time, the proposed model segments multiple neighboring structures simultaneously to gain more robust image segmentation. The interaction between these structures consists of repulsion, competition, and attraction.
The performance of the interaction model is demonstrated by the segmentation of MR images and high-throughput RNAi cell images.
Bio:
Dr. Pingkun Yan is Research Associate with the Computer Vision Lab in the School of Computer Science at the University of Central Florida (UCF), Orlando, FL. He received his Ph.D. degree in Electrical and Computer Engineering from the National University of Singapore (NUS), in 2006. Before that, he received his B.Eng. degree in Electronics Engineering from the University of Science and Technology of China (USTC), Hefei, Anhui, China, in 2001.
He joined the Computer Vision Lab in 2005. His research interests include biomedical image analysis, computer vision, information technology, and image processing. Dr. Yan is a recipient of the MICCAI 2005 Student Award for the best presentation on image segmentation and analysis at the 8th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2005.