Magnetic particle imaging (MPI) is a medical
imaging technology with high resolution and high sensitivity,
which tracks the distribution of superparamagnetic iron oxide
nanoparticles (SPIONs) in the nonlinear response to dynamic
excitation at a field-free region. However, various noises distort
the signals resulting in a decline in imaging quality. Traditional
threshold-based methods cannot remove dynamic noise in
MPI signals. Therefore, a self-supervised denoising method is
proposed to denoise MPI signals in this study. The approach
adopted U-net as the backbone and modified the network
for MPI signals. The network is trained using two periods
of noisy signals and the shape prior knowledge of the MPI
signals is introduced for promoting the convergence of the self supervised net. The experiments show that the learning-based
method can still denoising the MPI signal without labeling
data and eventually improve image quality, and our approach
can achieve the best performance compared with other self supervised methods in MPI signal denoising.