Patent · US Active

System for reconstructing magnetic particle image based on pre-trained model

US12136146B1 · kind B1 · utility

0Cited by
0References
8Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJun 24, 2024
Grant dateNov 5, 2024
Priority date
Expiry dateJun 24, 2044

Classification

  • Technology area (CPC Y)Emerging Cross-Sectional Technologies
  • CPC primaryY02A90/30
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A system for reconstructing a magnetic particle image based on a pre-trained model aims to address the influence by point spread function and reduce the computational and time costs, which results in low reconstruction accuracy, or high acquisition time and computational costs for high-precision images. The system is implemented by: generating a simulation system matrix; pre-training a pre-constructed neural network model, and fine-tuning a pre-trained neural network model by performing a downstream task; and inputting real data corresponding to the downstream task into the pre-trained neural network model after fine-tuning, thereby playing an auxiliary role to acquire a high-quality reconstructed MPI image. The system fits the relationship between different harmonics, which helps enhance frequency-domain information. The system has certain universality and can be generalized to a plurality of downstream tasks related to MPI image reconstruction, thereby acquiring high-quality reconstructed images through simple model fine-tuning.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.