基于迭代细化与K空间后验修正的多模态MRI重建方法
By employing a multimodal MRI reconstruction method with iterative refinement and K-space posterior correction, the problems of cross-modal image registration and lack of frequency distribution correction were solved, achieving high-quality MRI image reconstruction, especially significantly improving image sharpness and artifact suppression at high speed ratios.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- NANJING UNIV OF INFORMATION SCI & TECH
- Filing Date
- 2026-05-06
- Publication Date
- 2026-07-17
AI Technical Summary
Existing multimodal MRI reconstruction methods suffer from spatial position shifts and lack of correction for K-space frequency distribution in cross-modal image registration, resulting in poor reconstruction quality, especially with severe image blurring and artifacts at high speed ratios.
A multimodal MRI reconstruction method based on iterative refinement and K-space posterior correction is adopted. The cross-modal structure is dynamically aligned through an image domain iterative refinement network, and high-frequency details are restored by combining the K-space posterior correction module. The feature weighted combination is performed by an adaptive fusion module to form a high-quality reconstruction result.
It effectively reduced the negative impact of spatial displacement on reconstruction quality, restored high-frequency details, achieved clear and accurate multimodal MRI image reconstruction, and improved reconstruction fidelity and artifact suppression.
Smart Images
Figure CN122156492B_ABST