Publication
Deconvolution of direct reconstructions in 3D
Mathias Eulers; Christine Droigk; Marco Maass; Alfred Mertins
In: International Journal on Magnetic Particle Imaging, Vol. 11, No. 1 Suppl. 1, Pages 1-2, Infinite Science Publishing, 3/2025.
Abstract
A while ago a direct reconstruction method for multi-dimensional MPI was proposed, which is based on weighting frequency components of the measured voltage signals with Chebychev polynomials of second kind. The method works fast but leads to reconstructions of convolved spatial distributions of magnetic nanoparticles. In a previous work we were able to show that using a neural network model to deconvolve these reconstructions leads to high-quality images in the two-dimensional case. In this work, we take this approach one step further and demonstrate that this also applies to three-dimensional data. Therefore, in this work, we apply a neural network model on a simulated data set consisting of three-dimensional volumes containing blood vessel like structures. We show that the proposed network produces high-quality deconvolution results and outperforms conventional methods on the data set.