Under-sampled magnetic resonance image reconstruction method based on reference images and data correction

Through the undersampling magnetic resonance image reconstruction method based on reference images and data correction, convolutional neural networks and mutual information values ​​are used to select the optimal reconstructed image, which solves the problem of insufficient utilization of reference image information in the existing technology, achieves fast convergence and high-precision image reconstruction, and is suitable for clinical diagnosis.

CN114998458BActive Publication Date: 2025-10-24XIAMEN UNIV OF TECH
1 Cites 0 Cited by

Patent Information

Application Number
CN202111434806.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-11-29
Publication Date
2025-10-24
Estimated Expiration
2041-11-29

AI Technical Summary

Technical Problem

Existing unsupervised magnetic resonance image reconstruction methods do not fully utilize reference image information and undersampled data, resulting in low reconstruction accuracy. Existing supervised methods require a large amount of paired image data and are difficult to apply in clinical scenarios.

Method used

An undersampling magnetic resonance image reconstruction method based on reference images and data correction is adopted. A convolutional neural network and mutual information value are used to select the optimal reconstructed image, and the reconstruction accuracy is improved through iterative k-space data correction.

Benefits of technology

Fast convergence and high-precision reconstruction of undersampled magnetic resonance images are achieved, which improves image quality and is suitable for clinical diagnosis.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The application provides an undersampling magnetic resonance image reconstruction method based on a reference image and data correction, comprising the following steps: acquiring a full sampling T1 weighted image as a reference image I ref ; acquiring a full sampling T2 weighted image I T2 , and converting it into undersampling k-space data y; initializing an image sequence I s and initializing a mutual information value sequence MI s ; using a convolutional neural network based on a residual module, establishing an undersampling magnetic resonance image reconstruction model based on the reference image I ref and the undersampling k-space data y; training the undersampling magnetic resonance image reconstruction model; recording the reconstructed image in the reconstruction process and the mutual information value thereof with the reference image; selecting the best reconstructed image based on the mutual information value; and performing iterative k-space data correction on the best reconstructed image to obtain a final reconstructed image. The application can improve the accuracy of the reconstructed image.
Need to check novelty before this filing date? Find Prior Art