Multispectral MR images segmentation using SOM network

The precise segmentation of magnetic resonance images (MRI) is an important subject in both medical and computer science communities. With MRI's property of multi-spectrum, we use the information from its PD-,T1-, and T2-weighted images, mapping them into a multi-dimensional intensity space and getting its vector gradient. Through the improvement of the step function, an unsupervised self-organizing map (SOM) neural network is trained dynamically. To improve the effectiveness of segmentation, we develop a semi-supervised training scheme at the edge of image in multi-dimensional intensity space.

[1]  Teuvo Kohonen,et al.  The self-organizing map , 1990 .

[2]  J.A.F. Costa,et al.  A new tree-structured self-organizing map for data analysis , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[3]  Antônio Carlos Roque da Silva Filho,et al.  Segmentation of digitized mammograms using self-organizing maps in a breast cancer computer aided diagnosis system , 2002, VII Brazilian Symposium on Neural Networks, 2002. SBRN 2002. Proceedings..

[4]  Suchendra M. Bhandarkar,et al.  Segmentation of multispectral MR images using a hierarchical self-organizing map , 2001, Proceedings 14th IEEE Symposium on Computer-Based Medical Systems. CBMS 2001.

[5]  J.A.F. Costa,et al.  Automatic data classification by a hierarchy of self-organizing maps , 1999, IEEE SMC'99 Conference Proceedings. 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.99CH37028).

[6]  JANDER M OREIRA,et al.  Neural-based color image segmentation and classification using self-organizing maps , 1996 .

[7]  Volkan Atalay,et al.  Unsupervised segmentation of gray level Markov model textures with hierarchical self organizing maps , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[8]  Alain Hillion,et al.  An information fusion method for multispectral image classification postprocessing , 1998, IEEE Trans. Geosci. Remote. Sens..

[9]  Javad Alirezaie,et al.  Multi-spectral magnetic resonance image segmentation using LVQ neural networks , 1995, 1995 IEEE International Conference on Systems, Man and Cybernetics. Intelligent Systems for the 21st Century.