Blood vessel segmentation method and device and computer readable medium

Abstract

The invention discloses a blood vessel segmentation method and device and a computer readable medium, and belongs to the technical field of image processing. The method comprises the steps: using a blood vessel CT image as a training sample, and carrying out image feature extraction on the training sample to obtain a blood vessel feature map; respectively carrying out position feature extraction and semantic feature extraction on the blood vessel feature map to obtain a position feature vector and a semantic feature vector of the blood vessel; based on the position feature vector and the semantic feature vector, performing model training to obtain a blood vessel segmentation model; and performing prediction processing on a to-be-detected blood vessel CT image by using the blood vessel segmentation model to generate a blood vessel segmentation result. Therefore, problems of blood vessel fracture and / or vein adhesion and the like in a blood vessel segmentation result can be soved, the accuracy of blood vessel segmentation is improved, and the problem of long-distance dependence of a blood vessel image in the prior art is solved.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a blood vessel segmentation method, device and computer-readable medium. Background technique [0002] At present, angiography technology has been widely used in clinical diagnosis and treatment. The vascular segmentation algorithm can realize automatic vascular reconstruction (such as head and neck vessels, coronary arteries, etc.), which greatly improves the work pressure of technicians while reducing the pressure on technicians. the operating efficiency of the hospital. In actual scenarios, some external factors (such as artifacts, noise, shooting techniques, etc.) will affect the quality of vascular imaging, and it is difficult to distinguish arterial vessels from venous vessels from a local perspective. [0003] In the prior art, the coronary vessel segmentation algorithm is usually based on the UNet structure to directly predict the coronary vessel segment...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the above-mentioned problems in the prior art, the embodiments of the present invention provide a blood vessel segmentation method, device and computer readable medium, which can accurately segment blood vessels and solve the problem of long-distance dependence of blood vessel images in the prior art

Images