Method for segmenting and marking multi-branch tubular structure in three-dimensional image

Abstract

The invention provides a method for segmenting and marking a multi-branch tubular structure in a three-dimensional image, and belongs to the field of medical image processing. According to the method,a multi-branch tubular structure is regarded as a set of a plurality of single-branch tubular structures, and for the single-branch tubular structures, a center line is obtained through key point detection and neural network fine adjustment methods; then a cross section image of the tubular structure is acquired along the center line based on the center line, and finally a segmentation result ofthe tubular structure is acquired by using a segmentation network. The specific multi-branch tubular structure existing in the image can be segmented and automatically marked, and especially for someimages with lesions, such as aortic dissection, aortic aneurysm and coronary artery stenosis images, a good segmentation result is achieved.

Description

technical field [0001] The invention belongs to the field of medical image processing, in particular to a method for segmenting and marking multi-branched tubular structures in a three-dimensional image. Background technique [0002] Computed tomography angiography is a mainstream method of medical imaging. Doctors can obtain three-dimensional tomographic images of specific parts of the human body through computer-aided tomography. In these three-dimensional images, important functional tissues such as arteries, veins, and trachea are mostly multi-branched tubular structures. By observing and analyzing these tubular structures, doctors can have a more intuitive and intuitive understanding of the patient's physical condition without surgery. fully understand. Take the aorta as an example. The aorta is the main artery that transports blood to all parts of the body. There are many important branches in the chest cavity and abdominal cavity, which are responsible for delivering...

AI Technical Summary

Problems solved by technology

However, the existing algorithms are limited to the two-dimensional structural information on the two-dimensional plane, and the segmentation algorithm combined with the 3D structural information is still blank.

Images