Craniocerebral CT angiography image processing method and device, medium and electronic device

Abstract

The invention relates to a craniocerebral CT angiography image processing method and device, a medium and an electronic device. The method comprises the following steps: performing three-dimensional contour extraction on brain tissues in a target craniocerebral CT angiography image to obtain a three-dimensional brain tissue image; inputting the three-dimensional brain tissue image into a pre-constructed segmented model to obtain an initial segmented blood supply area image; acquiring a hidden space including the anatomical features of the segmented blood supply area; and correcting the initial segmented blood supply area image according to the hidden space. In this way, the multiple segmented blood supply areas can be automatically obtained only by inputting the three-dimensional brain tissue image corresponding to the target craniocerebral CT angiography image into the segmentation model, and the segmentation efficiency is remarkably improved. Besides, the hidden space including the anatomical features of the segmented blood supply area is fused into the correction process of the segmentation result, so that the problem that the segmentation result is unreasonable in the aspect of the anatomical structure due to the fact that the segmentation model cannot learn the anatomical features of the segmented blood supply area in the training stage can be avoided, and the segmentation precision is guaranteed.

Description

technical field [0001] The present disclosure relates to the technical field of image processing, and in particular, relates to a processing method, device, medium and electronic equipment for brain CT angiography images. Background technique [0002] CT angiography (Computed Tomography angiography, CTA) image refers to the image obtained by CT scanning under the condition of injecting contrast agent into human blood vessels, and the blood vessels are more obvious. Compared with computed tomography without contrast agent, CTA can clearly display the vertebral artery, basilar artery, posterior cerebral artery and its main branches, and can provide an important basis for diagnosis of occlusive vascular lesions. The relationship with blood vessels is of great value. [0003] Among them, brain CTA images usually include multiple segmental blood supply areas. Doctors can determine the status of brain regions by analyzing the CTA image features of each segmental blood supply area...

AI Technical Summary

Problems solved by technology

At this stage, the segmental blood supply areas are mainly distinguished by the naked eye. Usually, only experienced doctors can quickly and accurately identify the segmental blood supply areas with the naked eye, while inexperienced doctors need to spend a lot of time to distinguish the segmental blood supply areas, and the accuracy is relatively low. Difficult to guarantee, in this way, it will not be possible to quickly and accurately determine the state of the brain region

Images