Coronary artery projection image generation method and device and computer readable medium

Abstract

The invention discloses a coronary artery projection image generation method and device and a computer readable medium. One embodiment of the method comprises the following steps: acquiring a coronaryartery computed tomography angiography (CTA) sequence image; carrying out segmentation processing on the coronary artery CTA sequence image to generate two connected region images; identifying the two connected region images to generate a left coronary artery three-dimensional segmentation image and a right coronary artery three-dimensional segmentation image; and performing image projection processing on the left coronary artery three-dimensional segmented image and the right coronary artery three-dimensional segmented image to generate a left coronary artery tree two-dimensional image and aright coronary artery tree two-dimensional image. According to the invention, the left coronary artery CTA sequence image can be processed by the artificial intelligence model to generate the left coronary artery three-dimensional segmentation image and the right coronary artery three-dimensional segmentation image; therefore, maximum density projection is generated for the left coronary artery tree and the right coronary artery tree, interference of other tissues or blood vessel branches on coronary arteries is eliminated, and doctors can observe related problems of disease diagnosis such asblood vessel bifurcation, calcification or stenosis.

Description

Technical field [0001] The invention belongs to the field of medical imaging, and in particular relates to a method, a device and a computer readable medium for generating coronary projection images. Background technique [0002] Automated coronary artery reconstruction has important clinical value and practical significance for doctors. Maximum intensity projection (Maximal Intensity Projection, abbreviated MIP), is a widely used computer tomography angiography (ComputerAided Translation, abbreviated CAT) and magnetic resonance imaging (Magnetic Resonance Imaging, abbreviated MRI) image post-processing technology. MIP uses perspective to obtain two-dimensional images, which are generated by calculating the maximum density pixels encountered along each ray along the scanned object. When the fiber bundle passes through the original image of a piece of tissue, the pixels with the highest density in the image are retained and projected onto a two-dimensional plane to form a MIP rec...

AI Technical Summary

Problems solved by technology

This process takes a long time to manually identify the left and right coronary trees, and the start and end points are also prone to errors. It is easy to cut off small coronary vessels during the post-processing cutting process, resulting in missing branch vessels or lesions, resulting in images that are not diagnostically usable.

Images