Abstract This paper proposes a probabilistic prior-based active contour model for segmenting human brain MR images. Our model is formulated with the maximum a posterior (MAP) principle and implemented under the level set framework. Probabilistic atlas for the structure of interest, e.g., cortical gray matter or caudate nucleus, can be seamlessly integrate into the level set evolution procedure to provide crucial guidance in accurately capturing the target. Unlike other region-based active contour models, our solution uses locally varying Gaussians to account for intensity inhomogeneity and local variations existing in many MR images are better handled. Experiments conducted on whole brain as well as caudate segmentation demonstrate the improvement made by our model.
A Local Probabilistic Prior-Based Active Contour Model for Brain MR Image Segmentation
Computer Vision – ACCV 2007 ; 21 ; 956-964
Lecture Notes in Computer Science ; 4843 , 21
2007-01-01
9 pages
Article/Chapter (Book)
Electronic Resource
English
Probabilistic Atlas , Active Contour , Intensity Inhomogeneity , Gradient Vector Flow , Active Contour Model Pattern Recognition , Algorithm Analysis and Problem Complexity , Computer Science , Artificial Intelligence (incl. Robotics) , Biometrics , Image Processing and Computer Vision , Computer Imaging, Vision, Pattern Recognition and Graphics
Transition region-based active contour model for image segmentation
British Library Online Contents | 2013
|A novel active contour model for image segmentation using local and global region-based information
British Library Online Contents | 2017
|A statistical active contour model for SAR image segmentation
British Library Online Contents | 1999
|Directional geodesic active contour for image segmentation
British Library Online Contents | 2007
|