Dynamic function connection local linear embedded feature extraction and brain state classification method and system

Abstract

The invention discloses a dynamic function connection local linear embedded feature extraction and brain state classification method and system. The dynamic function connection local linear embedded feature extraction method comprises the following steps: collecting functional magnetic resonance imaging data in a resting state; after preprocessing, extracting an average time sequence signal of each brain region through a brain template; calculating and constructing a dynamic function connection matrix by using a sliding time window, and taking the dynamic function connection matrix as to-be-processed high-dimensional brain dynamic description original data; and carrying out manifold learning on the dynamic function connection matrix by using a local linear embedding algorithm to obtain a low-dimensional manifold subspace model, and extracting a feature part in the low-dimensional manifold subspace model to obtain a dynamic function connection local linear embedding feature. For the dynamic function connection local linear embedded feature extraction method, the feature extraction method is rapid in calculation and ideal in data processing effect, can construct significant crowd feature description, does not depend on the absolute value of the amplitude of an imaging signal, is migratable between different MRI machines, is excellent in classification and discrimination performance, and can conveniently utilize a machine learning model to realize brain state classification.

Description

technical field [0001] The present invention relates to brain state classification technology based on functional magnetic resonance imaging (fMRI) data, in particular to a brain state classification method and system based on local linear embedding of dynamic functional connections. Background technique [0002] The principle of functional magnetic resonance imaging is to measure hemodynamic changes caused by neuronal activity through magnetic resonance imaging. For example, when certain sense organs are stimulated, certain specific brain functional areas of the cerebral cortex are activated, and these activated brain areas send out neural signals, which are obtained by using MRI to obtain a series of images. When people perform various complex tasks such as movement, sensation, and advanced cognition, certain neural signals in the brain will be aroused. This physiological brain activity will cause changes in local cerebral blood flow, cerebral blood volume, and energy meta...

AI Technical Summary

Problems solved by technology

In reality, most brain activity patterns are nonlinear, and the biggest drawback of using linear methods is that they cannot effectively discover nonlinear structural features in the data.

Images