Fuzzy clustering medical image segmentation method having real-time performance

Abstract

The invention discloses a fuzzy clustering medical image segmentation method having real-time performance, and belongs to the medical 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; by adopting the characteristic information and the neighborhood information of the medical image, the medical image is preprocessed based on a filtering technology; the characteristic histogram of the filtered medical image is calculated; corresponding characteristic intervals are calculated in the characteristic histogram; clustering centers of corresponding tissues or organs in the filtered medical image are initialized, and membership degrees of pixels are calculated; by adopting an iteration process, during a process of minimizing the weighting functions of the pixels and the clustering centers, the membership degrees of the pixels and the clustering centers are updated; defuzzification is carried out based on a maximum membership degree rule, and the segmentation of the medical image is realized, and the corresponding tissues or the corresponding organs are extracted. The segmentation of the medical image is well realized, and the real-time requirement of the segmentation of the medical image is satisfied.

Description

technical field [0001] The invention relates to the technical field of medical image processing, in particular to a real-time fuzzy clustering medical image segmentation method. Background technique [0002] The rapid development of medical imaging equipment provides X-ray, computerized tomography (CT), magnetic resonance imaging (MRI), positron emission tomography (PET), digital subtraction angiography (DSA) for medical diagnosis. and digital GI and other rich image information. Effective use of this information can effectively help doctors to carry out computer-aided diagnosis, assist interventional therapy, formulate medical and surgical operation planning, dynamically simulate corresponding medical tissues or organs and analyze the structure and occurrence process of lesion parts, and improve the accuracy of disease diagnosis . [0003] In order to effectively utilize the information provided by medical images, it is necessary to segment medical images into different m...

AI Technical Summary

Problems solved by technology

[0007] There are several obvious shortcomings when the traditional FCM method is applied to medical image segmentation: (1) The segmentation result is affected by the initialization cluster center, and sometimes the segmentation result is concentrated in the detail part of the medical image, ignoring the segmentation of the main part; ( 2) The efficiency of segmentation is relatively low. When the medical image contains more pixels, the segmentation efficiency is low and cannot meet the requirements of real-time segmentation

Images