DATA TRUNCATION ARTIFACT REDUCTION IN MR-IMAGING USING A MULTILAYER NEURAL-NETWORK - COMMENTS

A recent paper by Yan and Mao(1) provided the results of using a neural network based nonlinear prediction algorithm to extrapolate truncated magnetic resonance data. The extrapolation is intended to reduce the truncation artifacts that result when reconstructing an image from a limited k-space magnetic resonance data set using the discrete Fourier transform. When attempting to quantitatively compare their method with our existing constrained modeling algorithm, we discovered a systematic error in their analysis. With the error corrected, it was found that their approach worked significantly better than they have reported and was more stable in the presence of noise.