Vascular imaging based calculation method of fractional flow reserve

Abstract

The invention relates to a vascular imaging based calculation method of fractional flow reserve. An artificial intelligence model 1 is utilized to automatically divide target blood vessel into multiple blood vessel segments having similar morphological features; the artificial intelligence model is also used to calculate the pressure drop of each blood vessel segments, so that the pressure distribution and FFR of the whole blood vessel can be obtained, and the use of pressure wires and the injection of vasodilators can be avoided; and the evaluation and rehearsal of vascular function recoveryafter virtual interventional surgery (such as stent placing) is performed by utilizing the pressure drop distribution information of the whole blood vessel.

Description

technical field [0001] The invention relates to medical images, in particular to a method for calculating blood flow reserve fraction based on vascular images. Background technique [0002] Myocardial hypoperfusion is an important cause of coronary heart disease. Fractional Flow Reserve (FFR) is defined as the ratio of the maximum blood flow that a diseased vessel can provide to the maximum blood flow that the vessel can provide when it is completely normal. It is one of the most important interventional diagnostic methods for the degree of vascular ischemia. The common measurement method of FFR is to measure the ratio of the distal pressure of the lesion stenosis and the proximal arterial pressure under the state of maximum hyperemia through a pressure-intervening guide wire or a microcatheter. Generally speaking, the distal pressure of vascular lesion stenosis is not only related to the degree of stenosis and lesion, but also related to the more distal capillary microcir...

AI Technical Summary

Problems solved by technology

For now, its technical barriers mainly lie in the inability to calculate accurate FFR from image data

[0004] The current FFR measurement requires an interventional guide wire to be inserted into the patient's blood vessel, and the microvascular circulation is maximally congested by injecting vasodilator drugs in the patient's body. Increased measurement complexity and time

The currently published methods of measuring FFR through computational methods are mostly based on computational fluid dynamics, which take a long time to calculate and are not real-time; the methods based on non-computational fluid dynamics are based on empirical formulas or certain analytical expressions, with significant empiricism Composition; a certain empirical formula may only be applicable to blood vessels of a specific shape, but not to other shapes of blood vessels, and the error is relatively large in the face of complex blood vessels and lesions in practical applications

In addition, the current FFR calculation method based on artificial intelligence does not fully respect the physical model of fluid mechanics, and there is no method suitable for intravascular imaging such as IVUS and OCT

Images