Automatic segmentation method of ultrasound images of gallbladder stones based on mspcnn

Abstract

The invention discloses an MSPCNN-based gallstone ultrasonic image full-automatic segmentation method, and the method comprises the steps: carrying out the segmentation of an ultrasonic image throughemploying an MSPCNN algorithm, and obtaining a gallstone coarse segmentation binary image; Segmenting the gall bladder coarse segmentation binary image by adopting a morphological algorithm to obtaina gall bladder accurate segmentation binary image and a calculus accurate segmentation binary image; And carrying out post-processing on the accurate gall bladder segmentation binary image and the accurate calculus segmentation binary image by adopting a local weighted linear regression algorithm, enabling the edge contour of the gall bladder calculus to be smooth, and finally obtaining a gall bladder region segmentation result and a calculus region segmentation result. The advantages of reducing the calculation complexity, reducing the segmentation steps and improving the image segmentation speed and precision are achieved.

Description

technical field [0001] The present invention relates to the field of image processing, in particular to an MSPCNN-based automatic segmentation method for ultrasound images of gallbladder stones. Background technique [0002] Cholelithiasis is a common gallbladder disease. For example, the incidence of gallstones in the natural population of B-type ultrasonography in Northwest my country is about 15%. In recent years, medical imaging technologies such as CT, MRI, and ultrasound have developed rapidly. Due to the low cost of ultrasound imaging examination, the advantages of strong real-time performance, no damage, and no electromagnetic radiation, ultrasound imaging examination is usually used as a means of initial diagnosis of gallstone disease. [0003] The purpose of ultrasonic image segmentation of gallbladder stones is to quickly and accurately segment the gallbladder area and stone area, so that doctors can obtain valuable and complete diagnostic information in the earl...

AI Technical Summary

Problems solved by technology

[0007] ②The parameters of the fully automatic segmentation algorithm are all adaptively obtained according to the image attribute values, which has been significantly improved compared with the semi-automatic segmentation based on the empirical value setting parameters. Improve the simplicity of the algorithm

[0009] ④The pulse-coupled neural network model (PCNN) introduced in the stone area segmentation step is an image processing tool that is more in line with the visual characteristics of the human eye. What is lacking is that the previous research is not deep enough, and its advantages have not been fully explored and displayed. There is still room for improvement in automatic segmentation speed and accuracy

Images