Blood vessel calcification image segmentation method and system and readable storage medium

Abstract

The invention provides a blood vessel calcification image segmentation method and system and a readable storage medium, and the method comprises the steps: firstly segmenting a to-be-segmented blood vessel image through employing a pre-trained neural network model, and obtaining an initial blood vessel segmentation image which only comprises a blood flowing region in a blood vessel and does not comprise a blood vessel calcification region; performing morphological dilation on the initial blood vessel segmentation image to obtain a blood vessel region mask image, expanding a blood vessel wall region on the periphery of a blood flowing region in a blood vessel, and performing multiplication operation on the blood vessel region mask image and the to-be-segmented blood vessel image to obtain a blood vessel segmentation image, wherein the blood vessel segmentation image contains a blood vessel calcification region at the moment; and determining a calcification threshold value according to the blood vessel segmentation image, and determining the blood vessel calcification region in the blood vessel segmentation image according to the calcification threshold value to obtain a blood vessel calcification segmentation image. The method not only can improve the precision of the whole segmentation algorithm, but also can effectively reduce the tedious operation of man-machine interaction.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a method, system and readable storage medium for segmenting vascular calcification images. Background technique [0002] Vascular disease, especially cardiovascular disease, has become one of the major diseases that threaten the safety of human life. During the operation, doctors use vascular imaging technology to assist in the diagnosis of various vascular diseases, such as calcification, aortic dissection, aneurysm, and cardiovascular and cerebrovascular stenosis. [0003] Vascular imaging techniques include computed tomography angiography (CTA), magnetic resonance angiography (MRA), and the like. Vascular imaging obtains a three-dimensional image, which includes not only vascular tissue but also other tissues around blood vessels (bone, fat, muscle, lung tissue, etc.), which cannot provide accurate diagnosis to doctors. Therefore, extracting the entire vascu...

AI Technical Summary

Problems solved by technology

[0006] (1) It takes a lot of time and effort to segment blood vessels manually or semi-automatically;

[0007] (2) In terms of blood vessel segmentation results, it is necessary to obtain vascular calcification through human-computer interaction segmentation, which is not intelligent enough

Images