Aortic valve semi-automatic segmentation method based on CTA dynamic image

Abstract

The invention discloses an aortic valve semi-automatic segmentation method based on a CTA dynamic image, and the method comprises the steps: obtaining CT angiography image data under electrocardio gating, carrying out the division of 20 time phases, and carrying out the following steps for an image of each time phase point: step A, segmenting Valsalva sinus according to the upper and lower boundaries of the root of an aorta; and step B, segmenting the aortic valve from the Valsalva sinus. According to the method, the feature extraction range in the CTA image is expanded, so that more completeanatomical details are presented, and the working efficiency and safety during an operation are further improved.

Description

technical field [0001] The invention relates to the technical field of medical image processing, in particular to a semi-automatic segmentation method of an aortic valve based on a CTA dynamic image. Background technique [0002] The aortic valve is located at the root of the aorta and constitutes the physical boundary between the aorta and the left ventricle. It is in the morphological center of the heart and is also the hemodynamic center. Preventing aortic blood from returning to the left ventricle during diastole and allowing blood to flow from the left ventricle to the aorta during systole plays an important role in maintaining normal blood supply to the heart. [0003] The heart is a key organ of the human cardiovascular system. Its internal tissue structure is relatively complex, and the heart is constantly contracting. However, most of the image data of the heart are orthogonal two-dimensional plane images, and each plane is taken at a certain moment. For a certain ...

AI Technical Summary

Problems solved by technology

However, the CTA imaging after the above CT scan is a regular transverse coronal and sagittal plane imaging, which is difficult to show the irregular membranous structure of the aortic valve, and the anatomical parameters it provides are limited to the static measurement of the aortic valve ring, and the dynamic measurement The difficulty lies in the fact that the heart is in constant motion, and the positions of its anatomical landmarks will also change in space, while conventional CTA images cannot automatically track these important anatomical landmarks

In the actual operation process, the anatomical and morphological information adjacent to the aortic root has not been presented; in addition, the quantitative evaluation of some common complications after TAVR, such as valve detachment and paravalvular leakage conduction block, is of great importance to the aortic. Lobe segmentation requires more details and data support

Images