A medical image processing method and device based on artificial butterfly optimization algorithm

Abstract

The present invention provides a medical image processing method and device based on the artificial butterfly optimization algorithm. The method includes: obtaining the input medical image I(i,j) to be processed, dividing the image into n windows, and analyzing the n windows. For each window of , median filtering is used to remove noise, and a noise-free image I is obtained. F (i, j); Construct a kernel function based on the multi-kernel local discriminant analysis MKLFDA method, from the noise-free image I F Extract the feature matrix of the image from (i,j), and reduce the dimensionality of the feature matrix into a one-dimensional vector form; use the artificial butterfly optimization algorithm to extract the feature matrix from the noise-free image I F Extract important features from the one-dimensional vector form of (i, j); input the extracted important features into the trained correlation vector machine RVM to obtain the classification and recognition results of the medical images to be processed. According to the solution of the present invention, the accuracy of ultrasound image recognition can be improved, and the efficiency of ultrasound image classification and image recognition can be improved.

Description

technical field [0001] The invention relates to the technical field of medical imaging, in particular to a medical image processing method and device based on an artificial butterfly optimization algorithm. Background technique [0002] In recent years, medical imaging technology has developed rapidly. Ultrasound imaging is an important branch of medical imaging. It plays an important role in quantitative analysis, real-time diagnosis and surgical planning, and can provide a basis for analysis and diagnosis of medical workers. [0003] However, the incidence of speckle noise in ultrasound images is higher than that in CT and MRI, which will affect the accuracy of ultrasound image recognition. And in order to accurately identify the region of interest in the ultrasound image and improve the recognition accuracy, it is necessary to read the object in the ultrasound image multiple times. Furthermore, in order to identify the region of interest in the ultrasound image, a large ...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the above-mentioned technical problems, the present invention proposes a medical image processing method and device based on the artificial butterfly optimization algorithm, which is used to solve the problem of high noise in ultrasonic images in the prior art, multiple reading of objects in ultrasonic images, and problems when recognizing images. A large number of irrelevant and redundant features are extracted, which affects the efficiency of ultrasound image classification and image recognition.

Images