Paper Info
Title
Automatic landmark extraction from image data using modified growing neural gas network
Abstract
A new method for automatic landmark extraction from MR brain images is presented. In this method, landmark extraction is accomplished by modifying growing neural gas (GNG), which is a neural-network-based cluster-seeking algorithm. Using modified GNG (MGNG) corresponding dominant points of contours extracted from two corresponding images are found. These contours are borders of segmented anatomical regions from brain images. The presented method is compared to: 1) the node splitting-merging Kohonen model and 2) the Teh-Chin algorithm (a well-known approach for dominant points extraction of ordered curves). It is shown that the proposed algorithm has lower distortion error, ability of extracting landmarks from two corresponding curves simultaneously, and also generates the best match according to five medical experts.
Year
DOI
Venue
2003
10.1109/TITB.2003.808501
IEEE Transactions on Information Technology in Biomedicine
Keywords
Field
DocType
biomedical MRI,brain,medical image processing,neural nets,MR brain images,Teh-Chin algorithm,automatic landmark extraction,brain images,dominant points,modified growing neural gas,multimodality,neural-network-based cluster-seeking algorithm,node splitting-merging Kohonen model,registration,segmented anatomical regions
Computer vision,Image warping,Medical imaging,Computer science,Self-organizing map,Artificial intelligence,Artificial neural network,Cluster analysis,Landmark,Distortion,Neural gas
Journal
Volume
Issue
ISSN
7
2
1089-7771
Citations 
PageRank 
References 
16
0.76
29
Authors
3
Name
Order
Citations
PageRank
Emad Fatemizadeh1160.76
Caro Lucas2171.16
Hamid Soltanian-Zadeh324422.92