A method and system for reconstructing magnetic resonance imaging parameters of incoherent motion within a voxel

Abstract

The invention discloses a method and system for reconstructing magnetic resonance imaging parameters of incoherent motion within a voxel. The method includes: setting D parameter, f parameter, D* parameter and S(0) parameter in the geometric figure generated in the simulation area, and judging whether the total area of ​​all geometric figures covers the simulation area; if covered, generating D parameter map, f Parameter map, D* parameter map and S(0) parameter map; generate a magnetic resonance diffusion weighted image corresponding to each b value, train the neural network model, and obtain a trained neural network model; perform Fu on the k-space data Liye transformation and normalization processing, input the normalized MR diffusion weighted image into the trained neural network model, and obtain the reconstructed IVIM parameter image. By adopting the method and system of the present invention, the problem of graininess in the reconstruction result caused by point-by-point fitting is solved, the image is smoother, and the influence of small b value on the IVIM double-exponential model is taken into account, thereby improving the reconstruction effect.

Description

Technical field[0001]The present invention relates to the field of magnetic resonance imaging, and in particular, in particular, an in-voxel intangible motion magnetic resonance imaging parameter reconstruction method and system.Background technique[0002]Magnetic Resonance Imaging, MRI) is widely used in clinical diagnosis due to its advantages such as high resolution, no electric radiation and multi-orientation, multi-parameter imaging. Magnetic resonance diffusion, DWI, mainly depends on the sport of water molecules rather than the organizational spin proton density, T1Value or T2Value, therefore it is possible to detect the molecular diffusion movement of the living tissue. Commonly used diffusion weighted imaging sequences are EPI-DWI sequences that mainly add a diffusion gradient based on the echo plane imaging (EPI) sequence, and the diffusion gradient speeds up the speed of proton scattering, so that the collected image is diffused in molecules. The weaker area shows a high s...

AI Technical Summary

Problems solved by technology

[0004] Although the IVIM model has successfully solved the limitations of the traditional single-exponential model, the model has a high degree of freedom and requires point-by-point nonlinear fitting for each pixel of the entire set of images, which makes the reconstruction of the D and f parameter maps It takes a lot of time, and the reconstructed parameter map will show obvious graininess, which will affect clinical diagnosis

At the same time, in the traditional point-by-point nonlinear fitting method, in order to alleviate the problem of high degrees of freedom in the double-exponential model of incoherent motion within the voxel, only large b values ​​(b≥200) are used for fitting the D and f parameter maps The original data (b represents the gradient factor), ignoring the impact of the small b value (b<200) data, resulting in the result cannot fully match the double exponential model, which may affect the diagnosis result

Images