Comparisons of Glutamate in the Brains of Alzheimer's Disease Mice Under Chemical Exchange Saturation Transfer Imaging Based on Machine Learning Analysis

Chemical exchange saturation transfer (CEST) is one of the molecular magnetic resonance imaging (MRI) techniques that indirectly measures low-concentration metabolite or free protein signals that are difficult to detect by conventional MRI techniques. We applied CEST to Alzheimer's disease (AD) and analyzed both region of interest (ROI) and pixel dimensions. Through the analysis of the ROI dimension, we found that the content of glutamate in the brains of AD mice was higher than that of normal mice of the same age. In the pixel-dimensional analysis, we obtained a map of the distribution of glutamate in the mouse brain. According to the experimental data of this study, we designed an algorithm framework based on data migration and used Resnet neural network to classify the glutamate distribution images of AD mice, with an accuracy rate of 75.6%. We evaluate the possibility of glutamate imaging as a biomarker for AD detection for the first time, with important implications for the detection and treatment of AD.

Automated summary

This study utilized CEST technology to investigate Alzheimer's disease and found differences in glutamate content in the brains of AD mice through ROI and pixel-dimensional analysis. Additionally, by using a neural network for classification, we preliminarily evaluated the potential of glutamate imaging as a biomarker for AD detection.