Heart MR image interpolation method and system based on causal relationship

Abstract

The invention provides a heart MR image interpolation method and system based on a causal relationship. The heart MR image interpolation method comprises the following steps: acquiring a heart MR image to be processed and preprocessing the heart MR image; performing key point extraction on the preprocessed current frame of heart MR image, and obtaining a key point coordinate sequence based on a time sequence; according to the obtained key point coordinate sequence, obtaining an interactive causal relationship between each pair of key points in combination with a graph neural network; obtaining coordinates of the key points in the next frame of image according to the obtained interaction causal relationship; and according to the coordinates of the key points in the next frame of image, obtaining a missing image in the heart MR sequence. The problem of image missing in the heart nuclear magnetic resonance image is effectively solved, and the robustness of image interpolation is improved.

Description

technical field [0001] The present disclosure relates to the technical field of image processing, in particular to a method and system for cardiac MR image interpolation based on causality. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art. [0003] Causal inference is the process of identifying causal relationships, learning directly from observations without modeling the underlying causal structure, which often distinguishes algorithmic models from human intelligent behavior. The reasoning process uses the generative model learned from human behavior teaching to find feasible trajectory solutions for a given user type, establishes a causal model based on key environmental information, and infers potential counterfactuals from the taught trajectory. Causal relationship. [0004] Heart disease is a huge hazard to human health. In the past 20 years...

AI Technical Summary

Problems solved by technology

[0005] The inventor found that cardiac MR imaging is also affected by many factors, resulting in problems such as blurred, incomplete or even missing images

Problems such as cardiac pulsation and blood movement in blood vessels, inhomogeneity of magnetic field (including gradient field), and radio frequency related interference will directly or indirectly affect image quality and cause artifacts. In addition, adjacent tissues or patients with different characteristics implants may cause localized signal loss in some images, resulting in images that may show incomplete LV coverage

Further, these poor quality images or missing images will have a certain impact on the diagnosis process and results, as well as on both medical staff and patients

Images