Segmentation method for vascular medical image

Abstract

The invention discloses a segmentation method for a vascular medical image. The method comprises the steps that the similarity of pixel points in an area is obtained by calculating the Euclidean distance between each pixel point in the area and an assumed pixel point gray value at the corresponding position, and gray similarity information Gi. Ck is used for replacing fi (x) commonly used in a traditional variational level set image segmentation model to serve as a data fidelity item of an image; maintaining the level set function as a signed distance function; adding a regular term penalty function to enable the level set function to be close to the symbolic distance function; and combining the data item, the length item, the regular item and the boundary stop item to obtain an improved variational active contour model of the energy functional. A data fidelity term is constructed by introducing similarity and gray similarity information of pixel points in a region, then evolution of an edge stop function control curve is added, and finally an improved variational active contour model is obtained in combination with a regular term.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a segmentation method for vascular medical images. Background technique [0002] Medical imaging is an emerging technology driven by engineering development in recent years. It has attracted great attention in the field of clinical medicine due to its advantages of simplicity, convenience, and high specificity. And with the advancement of science and technology and the rapid update of related images, imaging medicine has made innovations and breakthroughs in the medical field, and has been widely recognized by the medical community. Now it has become an important pillar of clinical medical work. Therefore, research on medical image processing has become a frontier topic in the field of medical imaging. [0003] In the past few decades, the clinical application of various new medical imaging technologies has enabled the rapid development of medical diagnosis and ...

AI Technical Summary

Problems solved by technology

Since each part of the human vascular system has its own characteristics, general vascular images have large differences such as uneven intensity and weak boundaries between tissues in the image; and due to the different information of different tissues, it is difficult to achieve better results. split effect

These defects often bring a lot of trouble to the doctor's accurate diagnosis and seriously affect the doctor's diagnosis efficiency of the disease.

Images