Support vector machine-based ultrasonic image segmentation method

Abstract

The invention discloses a support vector machine-based ultrasonic image segmentation method. The method comprises the following steps: respectively extracting sample points from the background of an image and a target of interest, estimating the variance features and the significance features of the pixel values of the ultrasonic image based on the gray values of the above sample points, and generating a sample training set; selecting a first-order linear polynomial as a kernel function, training samples by using the SVM train function in the MATLAB, and establishing a segmentation model basedon a support vector machine; segmenting a whole image according to a segmentation model for each sample on the whole image by utilizing the SVM predict function in the MATLAB, and extracting the target of interest. According to the method, the method is good in segmentation effect for low-contrast and low-resolution ultrasonic images. By adopting the method, details which cannot be distinguishedby naked eyes can be recognized and segmented. Therefore, the method is good in practicability for the diagnosis and the quantitative evaluation of medical ultrasonic images and industrial ultrasonicimages.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an image segmentation method applied in the medical field for tumor diagnosis. Background technique [0002] In medical ultrasound diagnosis and industrial ultrasound detection, the quantitative analysis of images plays an important role in clinical diagnosis and industrial quantitative evaluation. For low-resolution images, image quantitative analysis based on human eye analysis often brings great differences, and even leads to different conclusions. The basis of accurate image quantification is image segmentation, and correct segmentation is to carry out accurate quantitative analysis. premise. [0003] Image segmentation refers to a technique that divides an image into characteristic regions and extracts objects of interest. It is a basic problem in the field of image processing and computer vision. In medical image processing, image segmentation is often used to ex...

AI Technical Summary

Problems solved by technology

[0004] At present, the existing image segmentation methods are mainly divided into region-based segmentation methods and boundary-based segmentation methods. These image segmentation methods take a long time to process, and the segmentation results are greatly affected by human factors.

In common medical images such as X-ray images, magnetic resonance images, and ultrasound images, the image gray distribution is determined by the different parameters of human tissue characteristics. In general, the differences in human tissue characteristics are small, resulting in relatively large images. The grayscale difference between adjacent pixels is also very small, and it is sometimes difficult for the human eye to distinguish, and according to physiological research, the human perception system is more sensitive to the contrast of visual signals (such as color, intensity, texture), and smaller in the image. The contrast is difficult to distinguish, resulting in a very unsatisfactory segmentation effect

Images