Deep learning model and device for predicting blood flow features on flood flow vector paths

Abstract

The invention discloses a deep learning model for predicting flood flow features on flood flow paths. The deep learning model receives structural features of each point on the blood flow vector paths,physiological features of humans and personal features, and outputs the blood flow features of each point on the blood flow vector paths. The deep learning model comprises a support vector machine; and after the structure features of each point on the blood flow vector paths, the physiological features of humans and the personal features are input to the support vector machine, blood flow features of each point on the blood flow vector paths are obtained through calculation. The deep learning model integrates the structural features of blood vessels, physiological features and personal features of users, so that the blood flow features on the blood flow vector paths can be accurately predicted.

Description

technical field [0001] The invention belongs to the field of artificial intelligence, and in particular relates to a deep learning model for predicting blood flow characteristics on a blood flow vector path, and a device for predicting blood flow characteristics on a blood flow vector path. Background technique [0002] Blood flow characteristics have very important guiding significance in medicine. Fraction Flow Reverse (FFR) is a parameter for functional evaluation of coronary artery stenosis, which is defined as: in the case of coronary artery stenosis, the target measurement The ratio of the maximum blood flow that can be obtained by the myocardial region supplied by the blood vessel to the maximum blood flow that the same region can theoretically obtain under normal conditions. This ratio can be calculated from the ratio of the pressure distal to the patient's stenosis to the pressure at the aorta when the vessel is at maximal hyperemia induced by intravenous adenosine....

AI Technical Summary

Problems solved by technology

The deep learning model only takes image features, structural features, and functional features as input, and does not combine the physiological information of the human body and other information related to the living environment. Therefore, compared with the blood flow features obtained by invasive tests, using this There are some differences in the blood flow characteristics obtained by the deep learning model in the patent application

Images