Segmentation of Magnetic Resonance Brain Images using Analog Constraint Satisfaction Neural Networks

The Grey-White Decision Network (GWDN) is presented as an analog constraint satisfaction neural network that segments magnetic resonance brain images. Constraints on signal intensity, neighborhood interactions and edge in uences are combined to assign labels of grey matter, white matter or \other" to each pixel. An improved version of this novel segmentation network that is provably stable is described. Results of the network are presented along with a comparison of these results to a collection of 1 

• Type: Conference
• Year: 1993
• Where: DAGM
• Authors: Andrew J. Worth, David N. Kennedy
• Keywords: DAGM 1993, Grey-White Decision Network, Image Processing, Magnetic Resonance Brain, Satisfaction Neural Network