Abstract
A novel hybrid neural network trained by the genetic algorithms is presented. Genetic algorithms are used to improve the neural net's classification performance while minimizing the number of nodes. Each node of the network forms a closed region in the input space. The closed regions, which are formed by the nodes, intersect each other. The performance of the proposed hybrid neural network is compared with the multilayer perceptron, and the restricted Coulomb energy network for the segmentation of MR and CT head images. Experimental results show that the proposed neural network gives the best classification performance with a small number of nodes in short training times.
Similar content being viewed by others
References
Qian, W., Li, L. H. and Clarke, L. P.: Image feature extraction for mass detection in digital mammography-Influence of wavelet analysis, Medical Physics, 26(3) (1999), 402-408.
Tian, B., Shaikh, M. A., Azimisadjadi, M. R., Vonderhaar, T. H. and Reinke, D. L.: A study of cloud classification with neural networks using spectral and textural features, IEEE Trans. on Neural Networks, 10(1) (1999), 138-151.
Haering, N. and Lobo, N. D.: Features and classification methods to locate deciduous trees in images, Computer Vision and Image Understanding, 75(1-2) (1999), 133-149.
Ölmez, T. and Yazgan, E.: Abnormal tissue detection in computer tomography images using artificial neural networks, Proc. of the Annual Int. Conf. of the IEEE-EMBS, Paris, 1992, vol. 14, pp. 998-999.
Randen, T. and Husoy, J. H.: Filtering for texture classification-A comparative study, IEEE Trans. on Pattern Analysis and Machine Intelligence, 21(4) (1999), pp. 291-310.
Dokur, Z. and Ölmez, T.: Classification of magnetic resonance images using a novel neural network, IEEE-EMBS Asia Pacific Conference on Biomedical Engineering, 2000, Hangzhou China.
Reza, N. and Ying, S.: Classification of digital angiograms using artificial neural networks, 13th Ann. Int. Conf. of the IEEE-EMBS, 1991, vol. 13, no. 3, pp. 1440-1441.
Vinitski, S., Mohamed, F., Gonzalez, C., Knobler, R., Andrews, D., lwanaga, T. and Madi, S.: Fast tissue segmentation based on a 3D and 4D feature map: Comparison study, 19th Annual Int. Conf. of the IEEE-EMBS, 1997, pp. 505-508.
Qian, L. S., Xiang, L., Cheng, L. K. and Liang, L. S.: Tissue classification of multi-spectral MR images of brain, 20th Annual Int. Conf. of the IEEE-EMBS, 1998, pp. 634-636.
Özkan, M., Dawart, B. M. and Maciunas, R. J.: Neural network based segmentation of multi-modal medical images: A comparative and prospective study, IEEE Trans. on Medical Imaging, 12(3) (1993), 534-544.
Miller, A. S., Blott, B. H. and Hames, T. K.: Review of neural network applications in medical imaging and signal processing, Medical & Biological Engineering & Computing, 30 (1992), 449-464.
Reilly, D. L., Cooper, L. N. and Elboum, C.: A neural model for category learning, Biological Cybernetics, 45 (1982), 35-41.
Ölmez, T., Yazgan, E. and Ersoy, O. K.: Optimized competitive feature vector network, Electronics Letters, 30(24) (1994), 2052-2053.
Schaffer, J. D., Whitley, D. and Eshelman, L. J.: Combination of genetic algorithms and neural networks: A survey of the state of the art, Proc. Int. Wks on Combination of Genetic Algorithms and Neural Networks (COGANN-92), 1992, pp. 1-37.
Makhoul, J., Jaraudi, A. E. and Schwartz, R.: Formation of disconnected regions with a single hidden layer, IJCNN Int. Joint Conference on Neural Networks, vol. 1, 1989, pp. 455-460.
Dokur, Z., Ölmez, T. and Yazgan, E.: Comparison of discrete wavelet and Fourier transforms for ECG beat classification, Electronics Letters, 35(18) (1999), 1502-1504.
Goldberg, D. E.: Genetic Algorithms in Search, Optimization and Machine Learning, Addison Wesley Longman, Inc., Massachusetts, 1989.
Holland, J. H.: Genetic Algorithms, Scientific American, July (1992), 44-50.
Shareef, N., Wang, D. L.: and Yagel, R.: Segmentation of medical images using legion, IEEE Trans. on Medical Imaging, 18(1) (1999), 74-91.
Ölmez, T., and Dokur, Z.: ECG beat classification by a novel hybrid neural network and wavelet transform, IEEE-EMBS Asia Pacific Conference on Biomedical Engineering, 2000, Hangzhou China.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Dokur, Z. Segmentation of MR and CT Images Using a Hybrid Neural Network Trained by Genetic Algorithms. Neural Processing Letters 16, 211–225 (2002). https://doi.org/10.1023/A:1021769530941
Issue Date:
DOI: https://doi.org/10.1023/A:1021769530941