Deep learning model and system predicting blood flow characteristic in blood vessel path of blood vessel tree

Abstract

The invention discloses a deep learning model and system predicting a blood flow characteristic in a blood vessel path of a blood vessel tree. The deep learning model comprises a neural network arranged for different points in the blood vessel path, receives at least one, as input, selected from image, structure and function characteristics of the points in the blood vessel path, and predicts the blood flow characteristic, as output, of the points of a point sequence in the blood vessel path,; and the deep learning model is established via a recursive neural network or by combining a multilayer neural network with a recursive neural network sequentially. The deep learning model can predict the blood flow characteristic (as a blood flow reservation fraction) in the whole blood vessel path, and the computing efficiency is improved greatly.

Description

technical field [0001] The present invention relates to the field of artificial intelligence, in particular to a deep learning model for predicting blood flow characteristics on a vascular path of a vascular tree, its establishment method, its establishment device, a prediction device using it, and a method for predicting a vascular tree A system of blood flow characteristics along a vascular path. Background technique [0002] In human physiology and fluid dynamics, especially in hemodynamics that require precise data, obtain the blood flow characteristics of a large amount of blood at different points in the corresponding vascular path, such as Fractional Flow Reserve (FFR), etc. , has extremely important significance, but at present, the traditional machine learning method is used to obtain the blood flow characteristics at different points in the vascular path based on artificial intelligence methods, such as the blood flow reserve fraction, and only the characteristics ...

AI Technical Summary

Problems solved by technology

[0007] However, the existing algorithms including this paper almost only predict the FFR value of a single point on the vascular path, which belongs to a local optimization method. These point-based machine learning models do not take into account the blood flow characteristics in the blood vessel. Sequence relationship, unable to use the sequence information provided by the whole blood vessel to globally optimize the whole blood vessel and predict the FFR value on the whole blood vessel path, resulting in inaccurate prediction results

However, there is no research on the modeling and prediction of blood flow characteristics using deep sequence learning methods.

Images