Medical MR image segmentation method based on Hough transform and geometric active contour

Abstract

The present invention discloses a medical MR image segmentation method based on Hough transform and a geometric active contour and belongs to the technical field of image processing. According to the method, firstly, the prior shape knowledge that inner and outer contours of a left ventricle myocardium on a short axis image are of a round-like shaped is utilized, Hough transform is adopted to estimate an initial contour of a left ventricle and the reason of adopting Hough transform is that Hough transform has strong robustness, is not quite sensitive for the incompleteness of data or noise and can recognize partially deformed or partially shielded objects; the reason of using a K-means clustering algorithm is that as a square error based clustering method, the K-means clustering algorithm is simple and has a high clustering speed; and by using the method provided by the present invention, the inner and outer contours of the left ventricle can be segmented effectively, relative positions of evolving curves of the inner and outer contours of the left ventricle can be controlled and a function of shape constraint can be realized.

Description

Technical field: [0001] The invention relates to the technical field of image editing, in particular to a medical MR image segmentation method based on Hough transform and geometric active contour. Background technique: [0002] For the segmentation of left ventricular myocardium, the mainstream method is based on the edge-driven image segmentation method. Such as: parameter active contour model (also known as Snake model), level set (LevelSet) model, geometric active contour model and their improved models. However, mastoid muscle interference, local gradient maxima, weak edges, and artifacts often appear in MR images, which brings difficulties to edge-based image segmentation methods. Aiming at the problems caused by these phenomena, a lot of prior knowledge is introduced into the edge-based image segmentation model to improve the robustness of the model. The shape constraints and regional information based on prior knowledge are mostly used. Based on the geometric activ...

AI Technical Summary

Problems solved by technology

However, for images with uneven gray levels and noisy images, the performance of GVF will be affected, or only a suboptimal GVF field can be obtained, or the structure of the target may be smoothed

At this time, the evolution curve will enter another region from the weak boundary, causing boundary leakage or stopping evolution at the local maximum value of the gradient inside the region and the isolated edge, and cannot move to the real boundary.

Although the Paragios method adds the regional information obtained by fitting the histogram through the Gaussian mixture model, this method has a better fitting effect on the image with three ideal peaks, and the EM algorithm used to solve the Gaussian mixture model is not suitable for the initial The parameter estimates of have some dependence and may stagnate at some local maximum

In addition, due to the large number of items added and the complex evolution of the curve in Paragios’ method, special numerical calculation methods are required to ensure its numerical stability, which makes numerical calculation more complex.

Images