Cross-domain knowledge transfer based parallel-cascaded multi-scale attention network for limited view reconstruction in projection magnetic particle imaging. (May 2023)

• Record Type: Journal Article
• Authors: Wu, Xiangjun; Gao, Pengli; Zhang, Peng; Shang, Yaxin; He, Bingxi; Zhang, Liwen; Jiang, Jingying; Hui, Hui; Tian, Jie
• Is Part Of: Computers in biology and medicine. Volume 158(2023)
• Publication Date: 2023-05
• Subjects: Magnetic particle imaging -- Projection reconstruction -- Limited view reconstruction -- Transfer learning; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2023.106809
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Projection magnetic particle imaging (MPI) can significantly improve the temporal resolution of three-dimensional (3D) imaging compared to that using traditional point by point scanning. However, the dense view of projections required for tomographic reconstruction limits the scope of temporal resolution optimization. The solution to this problem in computed tomography (CT) is using limited view projections (sparse view or limited angle) for reconstruction, which can be divided into: completing the limited view sinogram and image post-processing for streaking artifacts caused by insufficient projections. Benefiting from large-scale CT datasets, both categories of deep learning-based methods have achieved tremendous progress; yet, there is a data scarcity limitation in MPI. We propose a cross-domain knowledge transfer learning strategy that can transfer the prior knowledge of the limited view learned by the model in CT to MPI, which can help reduce the network requirements for real MPI data. In addition, the size of the imaging target affects the scale of the streaking artifacts caused by insufficient projections. Therefore, we propose a parallel-cascaded multi-scale attention module that allows the network to adaptively identify streaking artifacts at different scales. The proposed method was evaluated on real phantom and in vivo mouse data, and it significantly outperformed several advanced limited view methods. The streaking artifacts caused by an insufficient number of projections can be overcome using the proposed method. Highlights: A cross domain framework is proposed to solve the limited view problems in projection MPI. The proposed CDKT learning strategy can effectively transfer the prior knowledge of limited view from CT into MPI. The proposed PCMSA module enables the network to adaptively identify streaking artifacts at different scales.