Fuzzy clustering medical image segmentation method based on medical tissue organ own characteristics

Abstract

The invention discloses a fuzzy clustering medical image segmentation method based on medical tissue organ own characteristics, and belongs to the image processing technology field. The fuzzy clustering medical image segmentation method comprises steps that gray scale characteristics of a predetermined medical image are extracted, and the characteristic information set of the medical image is acquired; the preprocessing of the medical image is carried out based on a filtering technology; the characteristic histogram of the filtered medical image is calculated; medical tissues and organs in the medical image are pre-segmented; the clustering centers and the membership degrees of the pixels of the medical tissues and organs are initialized, and the energy function of the medical image segmentation is defined; the energy function is minimized by an iteration process, and during the iteration process, a current segmentation result is corrected, and based on the corrected segmentation result, the clustering centers and the membership degrees of the pixels of the medical tissues and organs are updated; and the final medical image segmentation result is output. The medical image segmentation is well realized, and operation efficiency of a segmentation algorithm is improved.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a fuzzy clustering medical image segmentation method based on the characteristics of medical tissues and organs. Background technique [0002] Medical imaging instruments provide rich image information for medical diagnosis. Effective use of these medical image information can effectively help doctors to carry out computer-aided diagnosis, implement interventional treatment, formulate medical and surgical operation planning, dynamically simulate corresponding medical tissues and organs, analyze the structure and occurrence process of lesion parts, and improve the accuracy of disease diagnosis sex. [0003] When using the information provided by medical images, the first thing to do is to segment the medical images, divide the medical images into different medical tissues or organs, and analyze the shape, grayscale and other characteristics of different medical tissues a...

AI Technical Summary

Problems solved by technology

[0007] There are two obvious shortcomings when the traditional FCM method is applied to medical image segmentation: (1) The segmentation result is affected by the initialization of the cluster center, and the randomized cluster center initialization is easy to make the weighted distance function fall into a local minimum, and it is impossible to achieve the ideal value. (2) The calculation of the cluster center involves all pixels in the image. When applied to medical image segmentation, the intensity of a medical tissue is determined by all pixels in the medical image, which is obviously unreasonable. At the same time, since all pixels participate in the calculation, the operating efficiency of the segmentation algorithm is also reduced.

Images