A Cerebrovascular Segmentation Method Based on Multi-view Cascaded Deep Learning Network

Abstract

The present application discloses a method for cerebrovascular segmentation based on a multi-view cascaded deep learning network. The method includes acquiring MRA images and MRV images corresponding to the target part; determining several slice images based on the MRA images and MRV images; The trained first segmentation network model determines the reference segmentation map corresponding to each slice image; based on the MRA image, the MRV image, the obtained reference segmentation map and the trained second segmentation network model, determine the MRA The image corresponds to the segmented image. In this application, the first network segmentation model acquires the reference segmentation images corresponding to each section image as context information together with the MRA image and the MRV image as the input information of the second segmentation network model, so that the blood vessels in the MRA image can be learned from multiple perspectives Information, so that the accuracy of the second segmentation network model to determine the segmented image can be improved, thereby improving the accuracy of cerebrovascular segmentation.

Description

technical field [0001] This application relates to the field of medical imaging technology, in particular to a method for cerebrovascular segmentation based on a multi-view cascaded deep learning network. Background technique [0002] In neurosurgery, three-dimensional cerebrovascular images can assist doctors to see the relationship between saccular aneurysms and blood vessels in the skull, which is important for assisting clinicians in preoperative avoidance in epilepsy stereotactic EEG technology The path planning of electrode implantation in blood vessels is of great help. Magnetic resonance angiography (MRA), as an important means of computer-aided diagnosis and interventional therapy of cardiovascular and cerebrovascular diseases, neurosurgery navigation and postoperative observation, can be used to provide three-dimensional cerebrovascular images. However, due to differences in angiographic imaging principles and the characteristics of brain tissue itself, MRA cerebr...

AI Technical Summary

Problems solved by technology

However, due to differences in angiographic imaging principles and the characteristics of brain tissue itself, MRA cerebral angiographic images will be affected by noise, local volume effects, field offset effects, etc. during the acquisition process, resulting in low accuracy of blood vessel segmentation.

Images