Brain perfusion state classification method and device, equipment and storage medium

• Main Authors: LIU DONG, LYU HAN, YIN HONGXIA, CAI LINKUN, QIAO PENGGANG, MA XIA, LI JING, ZHAO ERWEI, ZHAO PENGFEI, WANG ZHENCHANG, ZHANG TINGTING, LI JIA, LUO DEHONG, LIU YAWEN, REN PENGLING, ZHENG WEI
• Format: Patent
• Language: Chinese; English
• Published: 07.04.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DIAGNOSIS; HUMAN NECESSITIES; HYGIENE; IDENTIFICATION; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; MEDICAL OR VETERINARY SCIENCE; PHYSICS; SURGERY

The invention provides a brain perfusion state classification method and device, equipment and a storage medium, and the method comprises the steps: dividing an obtained neck blood flow data sequence into a plurality of sub-segments, and enabling the number of neck blood flow data contained in each sub-segment to be the same; extracting associated features between adjacent sub-segments in the plurality of sub-segments and respective local features of the plurality of sub-segments; determining a statistical feature matrix of the neck blood flow data sequence according to the associated features and the local features; determining a physiological feature matrix of the neck blood flow data sequence according to physiological feature parameters reflected by the neck blood flow data sequence; and inputting the statistical feature matrix and the physiological feature matrix into a trained classification model to obtain brain perfusion state categories corresponding to a plurality of brain regions. According to the