Method and system for infarction classification based on CTP brain perfusion image data
A technology of image data and classification method, applied in the field of medical image analysis, can solve problems such as affecting surgery
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0021] refer to figure 1 As shown, the present invention discloses a method for infarction classification based on CTP cerebral perfusion image data, comprising the following steps:
[0022] S1. Obtain cerebral perfusion image data, and extract infarct candidate regions. The extraction of infarct candidate regions is realized by deep learning neural network or parameter map thresholding method.
[0023] S2. Calculate the average CT value M of each sequence in the brain region where the infarction candidate area is located 1 And get the peak sequence ID, and get the average CT value M of each sequence in the brain area around the infarct candidate area 2 And get the peak sequence ID, and get the average CT value M of each sequence in the ventricle area 0 .
[0024] S3. Judging M 1 with M 0 The degree of proximity, if M 1 -M 0 is less than the preset first empirical threshold, it is determined that the infarct candidate area is an old infarction, if M 1 -M 0 If it is g...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 
