AUTOMATED QUANTIFICATION OF HUMAN BRAIN-METABOLITES BY ARTIFICIAL NEURAL-NETWORK ANALYSIS FROM IN-VIVO SINGLE-VOXEL H-1-NMR SPECTRA

A real-time automated way of quantifying metabolites from in vivo NMR spectra using an artificial neural network (ANN) analysis is presented . The spectral training and test sets for ANN containing peaks at the chemical shift ranges resembling long echo time proton NMR spectra fro m human brain were simulated. The performance of the ANN constructed w as compared with an established lineshape fitting (LF) analysis using both simulated and experimental spectral data as inputs. The correspon dence between the ANN and LF analyses showed correlation coefficients of order of 0.915-0.997 for spectra with large variations in both sign al-to-noise and peak areas. Water suppressed H-1 NMR spectra from 24 h ealthy subjects were collected and choline-containing compounds (Cho), total creatine (Cr), and N-acetyl aspartate (NAA) were quantified wit h both methods. The ANN quantified these spectra with an accuracy simi lar to LF analysis (correlation coefficients of 0.915-0.951), These re sults show that LF and ANN are equally good quantifiers; however, the ANN analyses are more easily automated than LF analyses. (C) 1998 Acad emic Press.