Detection system based on phosphorylated tau protein content information in brain magnetic resonance image

Abstract

The invention discloses a detection system based on phosphorylated tau protein content information in a brain magnetic resonance image. The detection system is provided with an MRI image acquisition device, an image preprocessing device, a feature extraction device and a parameter inversion device. The parameter inversion device is used for inversion of an optimal feature subset to generate the phosphorylated tau protein content. A trained SVM model is solidified in the parameter inversion device. The SVM model is a mapping relation between the finally trained optimal feature subset and the phosphorylated tau protein content, and the finally trained optimal feature subset is obtained by selecting multiple feature parameters of multiple training sample images and the phosphorylated tau protein content of the PET image corresponding to each sample image acts as an evaluation criterion. The phosphorylated tau protein content can be quantitatively displayed only by the brain magnetic resonance image so that the detection system has advantages of being noninvasive, safe and high in degree of automation without radiation.

Description

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine

Login to view more

AI Technical Summary

Benefits of technology

In this patented method for creating an improved machine learning tool that predicts neurologically relevant changes from MRI scans without damaging them or causing damage during medical procedures. By training a specialized neural network called XGBoost with specific algorithms like Neural Network Theory (NLT) it learns how well different proteins are associated with certain structures within neurons while also showing their activity levels at other locations throughout the body. These models help researchers better identify diseases by analyzing data obtained from these experiments.

Problems solved by technology

The technical problem addressed by this patented method is that it requires expensive equipment like an X-ray machine or injection into patients during diagnoses due to their negative impact on healthcare providers who use these methods.

Images