Abstract: A training method and apparatus for angiography image processing and a method and apparatus for automatically processing a vessel image. The training method includes obtaining training data that includes original angiography image data and local segmentation result data of a side branch vessel. The local segmentation result data of the side branch vessel are local segmentation image data of the side branch vessel on a main branch vessel determined from an original angiography image. A neural network is trained according to the obtained training data to make the neural network perform local segmentation on the side branch vessel on the determined main branch vessel in the original angiography image. The training method can obtain the neural network for performing local segmentation on the side branch vessel, thereby realizing improvement of segmentation accuracy while improving segmentation efficiency, and avoiding missing segmentation and wrong segmentation of the side branch vessel.

Abstract: The present invention relates to a blood vessel image processing method, a blood vessel image processing apparatus, a computer storage medium, and an imaging device. The method includes: obtaining blood vessel geometric structure information of a blood vessel segment of interest; obtaining vital feature information of the blood vessel segment; establishing an association relationship between the blood vessel geometric structure information and the vital feature information; and displaying the blood vessel geometric structure information and the vital feature information in the same image in a mutual fusion manner by using the association relationship as a reference. In this way, work efficiency of users can be improved by the solution.

Abstract: A blood vessel cross-section function, a blood vessel pressure difference, and blood vessel stress may be established. A method for establishing a blood vessel cross-section function may include: obtaining image data in at least one cardiac cycle; selecting multiple feature times during the one cardiac cycle; generating spatial models of a target region blood vessel corresponding to each of the feature times according to the image data; establishing a first cross-section model of the target region blood vessel at each position along an axial direction of the target region blood vessel according to each of the spatial models; and establishing a corresponding first cross-section function according to each first cross-section model. Actual conditions of blood vessels may be reflected more accurately, and may provide an intermediate variable with less error for subsequent analysis operations, so that the later calculated value is closer to the actual value.