PGNet: Projection generative network for sparse-view reconstruction of projection-based magnetic particle imaging.

Researchers

Journal

Modalities

Models

Abstract

Magnetic particle imaging (MPI) is a novel tomographic imaging modality that scans the distribution of superparamagnetic iron oxide nanoparticles. However, it is time-consuming to scan multi-view two-dimensional (2D) projections for three-dimensional (3D) reconstruction in projection MPI, such as computed tomography (CT). An intuitive idea is to use the sparse view projections for reconstruction to improve the temporal resolution. Tremendous progress has been made towards addressing the sparse view problem in CT, because of the availability of large datasets. For the novel tomography of MPI, to the best of our knowledge, studies on the sparse view problem have not yet been reported.The acquisition of multi view projections for 3D MPI imaging is time-consuming. Our goal is to only acquire sparse view projections for reconstruction to improve the 3D imaging temporal resolution of projection MPI.We propose to address the sparse view problem in projection MPI by generating novel projections. The dataset we constructed consists of three parts: simulation dataset (including 3000 3D data), four phantoms data, and an in vivo mouse data. The simulation dataset is used to train and validate the network, and the phantoms and in vivo mouse data are used to test the network. When the number of novel generated projections meets the requirements of filtered back projection, the streaking artifacts will be absent from MPI tomographic imaging. Specifically, we propose a projection generation network (PGNet), that combines an attention mechanism, adversarial training strategy, and a fusion loss function and can generate novel projections based on sparse view real projections. To the best of our knowledge, we are the first to propose a deep learning method to attempt to overcome the sparse view problem in projection MPI.We compare our method with several sparse view methods on phantoms and in vivo mouse data and validate the advantages and effectiveness of our proposed PGNet. Our proposed PGNet enables the 3D imaging temporal resolution of projection MPI to be improved by 6.6 times, while significantly suppressing the streaking artifacts.We proposed a deep learning method operated in projection domain to address the sparse-view reconstruction of MPI, and the data scarcity problem in projection MPI reconstruction is alleviated by constructing a sparse-dense simulated projection dataset. By our proposed method, the number of acquisitions of real projections can be reduced. The advantage of our method is that it prevents the generation of streaking artifacts at the source. Our proposed sparse view reconstruction method has great potential for application to time-sensitive in vivo 3D MPI imaging. This article is protected by copyright. All rights reserved.This article is protected by copyright. All rights reserved.