Brain image feature extraction method based on edge connecting function connection

The invention discloses a brain image feature extraction method based on edge connecting function connection, and belongs to the field of brain function magnetic resonance image mode recognition, and the method specifically comprises the following steps: S1, including resting state function magnetic...

Full description

Saved in:
Bibliographic Details
Main Authors GONG QIYONG, SUN ANG, JIA ZHIYUN, ZHANG JUNRAN, LYU SU, HUANG XIAOQI
Format Patent
LanguageChinese
English
Published 06.09.2022
Subjects
CALCULATING
COMPUTING
COUNTING
DIAGNOSIS
HUMAN NECESSITIES
HYGIENE
IDENTIFICATION
MEDICAL OR VETERINARY SCIENCE
PHYSICS
SURGERY
Online AccessGet full text

Cover

More Information
Summary:The invention discloses a brain image feature extraction method based on edge connecting function connection, and belongs to the field of brain function magnetic resonance image mode recognition, and the method specifically comprises the following steps: S1, including resting state function magnetic resonance data of a subject, and carrying out image preprocessing and brain region time sequence extraction operation on the resting state function magnetic resonance data; obtaining an average time sequence of each brain region; s2, constructing an edge connecting function to connect the initial feature vector; s3, performing 102-104 times of non-put-back random sampling on the initial feature set, wherein the number of single sampling is flexibly adjusted according to nFC dimension; s4, feature selection and fusion; s5, the reconstructed feature vectors serve as final features of subject classification and are sent to a classifier; according to the method, the classification accuracy of identifying mental diseas
Bibliography:Application Number: CN202210621663