“School of Cognitive Sciences”

Back to Papers Home
Back to Papers of School of Cognitive Sciences

Paper   IPM / Cognitive Sciences / 7463
School of Cognitive Sciences
  Title:   Automatic Segmentation of Thalamus from Brain MRI Integration Fuzzy Clustering and Dynamic Contours
  Author(s): 
1.  L. Amini
2.  H. Soltanian Zadeh
3.  C. Lucas
4.  M. Gity
  Status:   Published
  Journal: IEEE Trans. Biomedicine Eng.
  No.:  5
  Vol.:  51
  Year:  2004
  Pages:   800 - 811
  Supported by:  IPM
  Abstract:
Thalamus is an important neuro-anatomic structure in the brain. In this paper, an automated method is presented to segment thalamus from magnetic resonance images (MRI). The method is based on a discrete dynamic contour model that consists of vertices and edges connecting adjacent vertices. The model starts from an initial contour and deforms by external and internal forces. Internal forces are calculated from local geometry of the model and external forces are estimated from desired image features such as edges. However, thalamus has low contrast and discontinues edges on MRI, making external force estimation a challenge. In this work, the problem is solved using a new algorithm based on fuzzy C-means (FCM) unsupervised clustering, Prewitt edge-finding filter, and morphological operators. In addition, manual definition of the initial contour for the model makes the final segmentation operator-dependent. To eliminate this dependency, new methods are developed for generating the initial contour automatically. The proposed approaches are evaluated and validated by comparing automatic and radiologists segmentation results and illustrating their agreement.


Download TeX format
back to top
scroll left or right