Method for segmenting ultrasonic images on basis of shape correlation active contour models

Abstract

The invention discloses a method for segmenting ultrasonic images on the basis of shape correlation active contour models. The method includes steps of 1, mining information of correlation between shape change of lesion regions in the continuous ultrasonic images and building low-rank shape correlation models; 2, building the active contour models on the basis of low-rank constraint; 3, creating augmented-Lagrange-based optimization algorithms for quickly computing segmentation results. The method has the advantage that the problem of inaccurate segmentation results of the traditional segmenting method on the basis of supervised statistical learning under the conditions of insufficient training sets, edge blur of lesion regions in existing ultrasonic images and deformation of the lesion regions in the existing ultrasonic images can be solved.

Description

technical field [0001] The invention belongs to the field of ultrasonic image processing in computer-aided therapy, in particular to an ultrasonic image segmentation method based on a shape-dependent active contour model, which is an ultrasonic image sequence segmentation method for soft tissues. Background technique [0002] An accurate and efficient ultrasound image segmentation method is of great significance for improving the efficiency of computer-assisted therapy. There are currently two main challenges: [0003] (1) Compared with CT and MRI images, ultrasound images generally have the characteristics of low signal-to-noise ratio and uneven distribution of image gray levels, which cause blurred target edge contours; [0004] (2) Another potential challenge is the deformation of the soft tissue caused by extrusion, which is reflected in the ultrasonic image that the shape of the target area changes greatly; [0005] For these reasons, some traditional segmentation met...

AI Technical Summary

Problems solved by technology

[0003] (1) Compared with CT and MRI images, ultrasound images generally have the characteristics of low signal-to-noise ratio and uneven distribution of image gray levels, which cause blurred target edge contours;

[0004] (2) Another potential challenge is the deformation of the soft tissue caused by extrusion, which is reflected in the ultrasonic image that the shape of the target area changes greatly;

[0005] These reasons have caused some traditional segmentation methods to fail to obtain ideal results in the above situations.

Images