Development of fuzzy neural tool for medical signal processing and imaging

The author proposes the use of fuzzy neural networks to improve the resolution of medical images and the segmentation of medical images. The backpropagation neural network is used to obtain an optimized membership function. The author works out the algorithms to implement the fuzzy neural networks for both types of application. Preliminary results are given. An advantage of using fuzzy neural networks compared with conventional neural networks is the reduction of the number of elements in each neural network layer. Thus, computation time can be reduced. Another advantage of using neural networks is the solution of the ill-posed problem in the universe scattering problem such as the divergence problem.<>