Method for optimizing the sampling trajectory in molecular exchange magnetic resonance measurements, molecular exchange magnetic resonance measurement method and apparatus
The integrated network model optimizes sampling trajectories and parameter estimation using deep learning, addressing inefficiencies in existing methods to enhance molecular exchange magnetic resonance measurement accuracy and efficiency.
JP7875650B1Active Publication Date: 2026-06-18ZHEJIANG UNIV
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- ZHEJIANG UNIV
- Filing Date
- 2024-07-01
- Publication Date
- 2026-06-18
Smart Images

Figure 0007875650000001_ABST
Abstract
The present invention discloses a method for optimizing the sampling trajectory of a molecular exchange magnetic resonance (MEL) measurement. The method includes the steps of: (1) determining the number and corresponding range of physiological / physical parameters of a molecular exchange system and generating a simulated physiological / physical parameter dataset; (2) determining a molecular exchange magnetic resonance measurement method and setting the acquisition parameters; (3) constructing an end-to-end integrated network model including a sampling trajectory optimization network, a noise signal generation network, and a parameter estimation network; and (4) training the network using the simulated physiological / physical parameters as input, and obtaining the optimized sampling trajectory and the corresponding parameter estimation network once the network has converged and training is complete. The present invention further discloses a molecular exchange magnetic resonance measurement method and apparatus. The method for optimizing the sampling trajectory of a molecular exchange magnetic resonance measurement provided by the present invention improves the efficiency and accuracy of physiological / physical parameter estimation and can be applied to various molecular exchange magnetic resonance measurement methods.
Need to check novelty before this filing date? Find Prior Art