Perfusion image judgment system and method based on opencv, intelligent terminal

Abstract

The invention belongs to the technical field of image processing, and discloses an OPENCV-based perfusion image judging system and method, and an intelligent terminal, which can segment pictures and remove patient information, time series information, and other noises that are meaningless to result judgment; The position of the brain area is segmented, and the left and right brain areas in a single picture are divided; the color system of the perfusion picture uses pixels to convert RGB->HSV; traverses the pixels and sets the pixels to black in the value of the image in the RGB color space Or white; the target color point is displayed with black pixels, and the non-target color point is displayed with white pigment points in the present invention; each element in the array is given a weight; a more suitable threshold parameter is obtained. The invention can realize the intelligent analysis of head nuclear magnetic perfusion images, intelligently distinguish the clinical stages of nuclear magnetic perfusion, and has guiding significance for the treatment of ischemic diseases; the severity of diseased brain tissue can be judged.

Description

Technical field [0001] The present invention belongs to the field of image processing, and more particularly to an OpenCV-based perfusion image determination system and method, intelligent terminal. Background technique [0002] At present, the closest prior art: Due to the aging of the population, the number of people suffering from the ischemic brain is increasing year by year, and patients with cerebral ischemia disease will be admitted to the hospital. The patient's head nuclear magnetic perfusion examination, grading the degree of ischemia's ischemic levels to formulate the treatment plan. At present, the domestic commonly used cerebral dilution staging refers to Gao Peiyi and other studies to divide the infarction, low perfusion state: I1: TTP prolong, MTT, RCBF and RCBV normal; I2: TTP and MTT extended, RCBF is normal, RCBV is normal or Mild increase; II1: TTP, MTT extension and RCBF decreased, RCBV is basically normal or mildly decreased; II2: TTP, MTT extended, RCBF and ...

AI Technical Summary

Problems solved by technology

Each clinical doctor may have a slight error in the discrimination of the image, resulting in an error in the classification of the image

[0004] To sum up, the problems existing in the existing technology are: the current recognition, interpretation, division and staging of perfusion images have errors in image discrimination, resulting in errors in image grading

1. There is no completely unified standard for the color distribution of perfusion images. Different radiologists have great differences in color matching when producing perfusion images. This is also the main reason for differences in judgments by clinicians.

2. There is no gold standard for judging the degree of ischemia in patients with perfusion images. That is to say, doctors can only estimate the degree of ischemia through the so-called "feeling". Different doctors have their own measurement standards in mind, which also leads to Important reasons for judging the difference

Images