Classification method for brain resting state functional magnetic resonance imaging

Abstract

The invention discloses a brain resting state functional magnetic resonance imaging graph classification method, which adopts a mode of combining a traditional machine learning method and a deep learning method to analyze a neuroimaging result of a user. The problem that in the prior art, a resting state functional magnetic resonance imaging graph analysis method cannot have high classification performance and low training data volume at the same time is solved.

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

This technology helps identify people who are sleepy or have difficulty staying still during an MRI scan without getting tired again later when they return from another session for examination. By analyzing these images with different parts of their body that correspond to specific areas called “rest-related” functions (R) , this system can improve accuracy while reducing overfitting.

Problems solved by technology

This patented technical solution described by the inventors relates to improving the accuracy and efficiency of analyzing sleep state magnetoencephalography (Sleep Magnetism Imager). Current analyzes either involve manual or automatic processing steps such as image segmentation, annotation, etc., making them time-consuming processes. Additionally, current approaches often result in overlapping areas between different types of neurons due to their close proximity during an eye movement process.

Images