Fast Analysis Of 1H Magnetic Resonance Spectroscopic Imaging Data: An Artificial Neural Network Based Approach.
Bhat H, Sajja B, Narayana P, Datta S
University of Houston
A radial basis function neural network (RBFNN) based method for fast quantification of phased, as opposed to magnitude, MRSI data is presented. Simulations show this method to be robust in the presence of noise and phase distortions. The metabolite area ratios for normal subjects determined using RBFNN very favorably compare with the published values. The computational time on a typical PC was around 15-20 seconds, compared to 30-40 minutes, for line fitting methods. This method could be applied for real time analysis of MRSI data under parallel computing environment.