Fast magnetic particle imaging reconstruction method based on undersampling

Abstract

The invention discloses a fast magnetic particle imaging reconstruction method based on undersampling. The method comprises the steps of obtaining MPI undersampling voltage signals, obtaining full-sampling MPI images, conducting nonlinear normalization on the signals and the images, training a neural network and predicting magnetic particle concentration distribution. According to the method, the voltage signals are directly mapped to the image domain, reconstruction can be carried out within several milliseconds, wide evaluation on a large number of data sets shows that the method can reconstruct the full-sampling high-resolution MPI image from the under-sampling voltage signals, and the method has good anti-noise capacity and anti-artifact capacity; the method has good generalization ability, the reconstructed image quality is higher, the reconstruction speed is higher, the imaging potential of a magnetic particle imaging system is improved, and the problem that MPI equipment introduces a large amount of noise due to too long acquisition time is solved.

Description

technical field [0001] The invention belongs to the technical field of magnetic particle imaging (Magnetic Particle Image, MPI) image reconstruction, and in particular relates to a fast magnetic particle imaging reconstruction method based on undersampling. Background technique [0002] MPI is a new and cutting-edge tomographic imaging method for imaging the concentration distribution of biocompatible superparamagnetic nanoparticles, with high sensitivity, high resolution, and no radiation. In general, the ideal angiographic approach is to see only the tracer and not the tissue, and in MPI, the tissue is transparent to low-frequency magnetic fields. Therefore, MPI can detect nanoparticle contrast agents without any background and zero depth attenuation. MPI benefits from high temporal resolution and potentially high spatial resolution, which makes it suitable for a variety of in vivo applications such as blood flow imaging, long-term monitoring using circulating tracers, fl...

AI Technical Summary

Problems solved by technology

In MPI imaging, the speed index is an important index. If the acquisition time is too slow, the imaging system will generate more noise, and the thermal effect of the system will also generate thermal noise, which will reduce the sensitivity of the reconstructed MPI image. In addition, if it is an animal experiment, Animal breathing and slight movement will cause image artifacts and blurring, which will reduce the resolution of the reconstructed MPI image

Images