“School of Cognitive”

Back to Papers Home
Back to Papers of School of Cognitive

Paper   IPM / Cognitive / 7437
School of Cognitive Sciences
  Title:   Automatic Landmark Extraction from Image Data Using Modified Growing Neural Gas Network
  Author(s): 
1.  E. Fatemizadeh
2.  C. Lucas
3.  H. Soltanian Zadeh
  Status:   Published
  Journal: IEEE Transaction on Information Technology and Biomedicine
  No.:  2
  Vol.:  7
  Year:  2003
  Supported by:  IPM
  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 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 The-Chin algorithm (a well-known approach for dominant points extraction or ordered curves). It is shown that the proposed algorithm has lower distortion error, ability of extraction landmarks from two corresponding curves simultaneously, and also generates the best match according to five medical experts.


Download TeX format
back to top
scroll left or right