STATISTICS FOR INVESTIGATION OF MULTIMODAL MR-IMAGING DATA AND AN APPLICATION TO MULTIPLE-SCLEROSIS PATIENTS

Magnetic resonance spectroscopy can image axonal damage specifically b ased on changes in N-acetyl aspartate (NAA), a neuronal marker, We hav e developed statistical methods for multimodal analysis of MR spectros copic images. These methods, which are extensions of mixed-effect mode ls, have allowed us to quantify differences in images from different s ubgroups of patients with multiple sclerosis CMS) and to determine the dependence of chemical pathology on clinical disability, duration of disease and lesions on T-2-weighted MRI. Statistical power was improve d by using all reliable resonance intensities in the spectroscopic ima ges while taking into consideration the intra-subject correlations, We studied 17 normal subjects, 14 patients with relapsing remitting (RR) MS and 21 patients with chronic progressive (CP) MS, The ratio of res onance intensities of N-acetylaspartate over creatine (Cr) was found t o be significantly lower than normal in normal appearing white matter (NAWM) of both RR and CP patients (19.6% in RR, 28.8% in CP), NAA/Cr w as decreased even more in MS plaques than in NAWM (44.2% in RR, 17.7% in CP), NAA/Cr was correlated with clinical disability (p < 0.02) and disease duration (p < 0.1). Our results suggest that, in this setting, MRS reflects accumulated neuronal loss or damage and can be used as a measure of disease severity, The methods developed provide opportunit ies to evaluate the relationship between inflammation, demyelination, axonal loss and clinical disability in future studies. (C) 1996 by Joh n Wiley & Sons, Ltd.