Physical model driven magnetic resonance four-dimensional dynamic imaging method and device
Through the magnetic resonance four-dimensional dynamic imaging method driven by the physical model, the target training model and the physical drive module are used to generate a high-fidelity four-dimensional dynamic imaging sequence, solving the problems of missing and incoherent information of the dynamic change process in the prior art, and achieving accurate evaluation of complex dynamic moving parts.
Patent Information
- Application Number
- CN202411713880.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-27
- Publication Date
- 2025-02-28
AI Technical Summary
The existing four-dimensional magnetic resonance imaging technology has problems of missing information and incoherence when capturing the dynamic changes of complex dynamic moving parts, which is difficult to meet the clinical needs for accurate and complete dynamic image data.
The magnetic resonance four-dimensional dynamic imaging method driven by physical model is adopted. By acquiring magnetic resonance K-space data, three-dimensional static images are extracted, and dynamic changing modes are analyzed using the target training model, and future images are predicted based on this mode. Combined with the physical driving module to impose constraints in the K-space domain, the data is corrected to generate a high-fidelity four-dimensional dynamic imaging sequence.
This method can comprehensively capture the characteristics of different motion states at the imaging site, avoid inaccurate dynamic information, improve the accuracy of evaluating joint functions and lesions in complex dynamic motion areas, and provide more reliable image information.
Smart Images

Figure CN119535319A_ABST
Abstract
Citation Information
Cited By
No-prior hinge type object state generation and joint estimation method
CN122176689A