Medical Diagnostic Image Fusion Based on Feature Mapping Wavelet Neural Networks
Authors:
- M. LiangMLM. Liang
- W.C. SunWSW.C. Sun
- 31 March 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 51-54
Abstract
In recent years, many solutions to medical diagnostic image fusion have been proposed; however, it is difficult to simulate the surgical ability of image fusion when algorithms of image processing are merely piled up. On the basis of the review of researches on psychophysics and physiology of human vision, this paper presents an effective multi-resolution image fusion methodology, which is self-organizing feature mapping wavelet neural network (SOFMWNN), to simulate the processes of images recognition and understanding implemented in the human vision system. As an example, the fusion process is applied in the clinical case: the study of some particular disease by MR/SPECT fusion. Results are presented and evaluated, and a preliminary clinical validation is achieved. The effectiveness of the proposed model is demonstrated via results comparison with several other image fusion methods.Keywords
This publication has 9 references indexed in Scilit:
- Image registration methods: a surveyImage and Vision Computing, 2003
- From neural to wavelet network2003
- Wavelet networks as an alternative to neural networks2002
- Image fusion based on median filters and SOFM neural networks:Signal Processing, 2001
- Review article Multisensor image fusion in remote sensing: Concepts, methods and applicationsInternational Journal of Remote Sensing, 1998
- An introduction to multisensor data fusionProceedings of the IEEE, 1997
- Multisensor Image Fusion Using the Wavelet TransformGraphical Models and Image Processing, 1995
- Wavelet networksIEEE Transactions on Neural Networks, 1992
- Multifrequency channel decompositions of images and wavelet modelsIEEE Transactions on Acoustics, Speech, and Signal Processing, 1989