发表机构
Institute for the Protection of Terrestrial Infrastructures, German Aerospace Center (DLR); Hochschule Darmstadt; Data Science Institute, European University of Technology; Technische Hochschule Würzburg-Schweinfurt（德国航空航天中心陆地基础设施保护研究所; 达姆施塔特应用科学大学; 欧洲技术大学数据科学研究所; 维尔茨堡-施韦因富特应用技术大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出MPISuperRes-PnP算法，将超分辨率融入磁粒子成像的能量最小化重建任务，采用零样本预训练去噪器，无需MPI稀缺训练数据，在合成与真实数据上验证了通用性。
AI 中文摘要
磁粒子成像（Magnetic Particle Imaging, MPI）是一种新兴的医学成像模态，基于磁性纳米粒子对施加磁场的非线性响应，避免了电离辐射。测量得到的信号是接收线圈中由粒子响应感应出的电压，从该信号中重建粒子浓度构成了成像任务。即便采用最先进的基于测量的重建方法，其对应的空间网格仍非常粗糙，因此超分辨率（Super-Resolution, SR）技术至关重要。本研究提出一种受能量最小化启发的MPI超分辨率方法。针对MPI超分辨率已提出了多种方法，涵盖从相关系统矩阵的上采样到重建结果的插值等。本研究将超分辨率融入重建任务，采用能量最小化公式，遵循即插即用（Plug-and-Play）的能量最小化方法推导了一种分裂方案和MPI超分辨率方法，其中产生的高斯去噪任务采用预训练的学习型高斯去噪器以零样本方式处理。由此，本方法在无需训练的情况下结合了深度学习的优势，避免了对训练数据的需求。进一步，本研究对所提方法进行了定量和定性评估，超参数通过扩展参数搜索选择，找到的参数被应用于真实数据的重建。本研究在合成数据和真实数据（MPIData：EquilibriumModelWithAnisotropy及2D-OpenMPI数据）上验证了所提方法的适用性。该方法采用无需训练的深度学习去噪器，因此无需目前稀缺的MPI训练数据；该去噪器表现保守，未观察到幻觉伪影；所提超分辨率方法具有通用性，可应用于未来涉及不同正则化项或不同成像任务的MPI场景。
英文摘要
Magnetic Particle Imaging (MPI) is an emerging medical imaging modality. MPI is based on the non-linear response of magnetic nanoparticles to an applied magnetic field and avoids ionizing radiation. The measured signal is the voltage induced in receive coils by the particles' response. Reconstructing the particle concentration from the signal constitutes the imaging task. Even using state-of-the-art measurement-based reconstruction, the associated spatial grid is very coarse, hence super-resolution (SR) techniques are important. In this work, we propose an approach for SR in MPI inspired by energy minimization. Different methods have been proposed for SR in MPI, ranging from upscaling of the associated system matrix to interpolation of the reconstruction. Here we incorporate SR into the reconstruction task via an energy minimization formulation. Following the plug-and-play approach to energy minimization we derive a splitting scheme and a SR method for MPI where the arising Gaussian denoising task is treated with a pre-trained learned Gaussian denoiser in a zero-shot fashion. This way, we incorporate benefits of deep learning without training and avoid the need of training data. Further, we provide a quantitative and qualitative evaluation of the proposed method. Hyper-parameter are selected via an extended parameter search. The found parameters are applied for reconstruction on real data. We show the applicability of our method on synthetic and on real data (MPIData: EquilibriumModelWithAnisotropy and 2D-OpenMPI Data). The proposed method employs a deep-learning denoiser without training -- thus it does not require presently scarcely available MPI training data. The denoiser behaves conservatively, i.e., no hallucination artifacts were observed. The SR approach is generic such that it can be applied in future MPI contexts involving different regularizers or different imaging tasks.
Comments19 pages, 8 tables
