A method, device and medium for blood vessel segmentation on medical images

Abstract

The present disclosure relates to a method, device and medium for blood vessel segmentation on medical images. The method may include acquiring a medical image including several parts to be segmented into blood vessels, the blood vessels in each part having different structural properties. The processor may be used to divide the medical image into sub-medical images of each part according to the parts. Based on the sub-medical images of each part, the processor can use the corresponding blood vessel segmentation model of each part to determine the corresponding blood vessel segmentation result. The processor may be used to fuse the blood vessel segmentation results of the sub-medical images of various parts to obtain the blood vessel segmentation results of the medical image. The method and device differentiate and adapt the blood vessel segmentation model for each part to segment the blood vessels of each part respectively, so that the whole blood vessel segmentation process is fast, effective and highly accurate.

Description

technical field [0001] The invention relates to the technical field of medical image processing, in particular to a method and a device for blood vessel segmentation on medical images. Background technique [0002] With the development of medical imaging equipment, doctors can use medical images for disease screening and diagnosis, surgical planning and prognosis assessment, for example, using computed tomography angiography (Computed Tomography Angiography, CTA) or magnetic resonance angiography (Magnetic Resonance Angiography) , MRA) can image blood vessels, vascular variations, and vascular lesions in various parts of the body. Medical vascular image analysis plays an important role in the clinical field, and vascular image segmentation is an extremely important part of vascular image analysis. Early blood vessel segmentation methods were mainly based on feature selection and image analysis for angiographic images to obtain vessel segmentation results, but they were easi...

AI Technical Summary

Problems solved by technology

Although the blood vessel segmentation method based on the deep neural network is effective, a single model is generally used

Due to the complexity of blood vessel images, there may be some problems in its segmentation results

Specifically, there may be an under-segmentation problem, and blood vessels with larger and smaller radii are easily missed and segmented, resulting in breakage; there may be an over-segmentation problem, and non-vascular areas similar to blood vessels in the image are segmented, resulting in adhesion noise

Images