Fuzzy classification of metabolic brain diseases utilizing MR Spectroscopy signals

Abstract

A suspected metabolic brain disorder presents a difficult challenge to the physician and the patient. We have developed a fully automated system in order to classify the Magnetic Resonance Spectroscopy (MRS) signals. Novel fuzzy rules and a fuzzy classifier have been designed in this study to categorize metabolic brain diseases in children. The sensitivity and positive predictivity of 75% plusmn 43 in detecting five metabolic brain diseases have been achieved.