MR image resolution enhancement using a multi-layer neural network
Hong Yan, J. Mao, B. Chen · 2003
A magnetic resonance image may contain truncation artifacts if there are not enough high-frequency data when the conventional Fourier transform method is used for reconstruction. The authors propose a method for reducing the artifacts using a multilayer neural network. The network consists of one linear output layer and at least one nonlinear hidden layer. In this method the missing high-frequency components are predicted based on known low-frequency components and are used to improve the resolution of the image. The method is tested with simulated data with good results.>