School of Computer and Information Technology, Beijing Jiaotong University, Beijing, 100069, People's Republic of China.
Beijing Key Laboratory of Molecular Imaging, Beijing, 100190, People's Republic of China.
Phys Med Biol. 2022 Jun 10;67(12). doi: 10.1088/1361-6560/ac6e24.
Magnetic particle imaging (MPI) is a new medical, non-destructive, imaging method for visualizing the spatial distribution of superparamagnetic iron oxide nanoparticles. In MPI, spatial resolution is an important indicator of efficiency; traditional techniques for improving the spatial resolution may result in higher costs, lower sensitivity, or reduced contrast.Therefore, we propose a deep-learning approach to improve the spatial resolution of MPI by fusing a dual-sampling convolutional neural network (FDS-MPI). An end-to-end model is established to generate high-spatial-resolution images from low-spatial-resolution images, avoiding the aforementioned shortcomings.We evaluate the performance of the proposed FDS-MPI model through simulation and phantom experiments. The results demonstrate that the FDS-MPI model can improve the spatial resolution by a factor of two.This significant improvement in MPI could facilitate the preclinical application of medical imaging modalities in the future.
磁共振粒子成像（MPI）是一种新的医学、无损成像方法，用于可视化超顺磁氧化铁纳米粒子的空间分布。在 MPI 中，空间分辨率是效率的一个重要指标；传统提高空间分辨率的技术可能会导致更高的成本、更低的灵敏度或降低对比度。因此，我们提出了一种基于深度学习的方法，通过融合双采样卷积神经网络（FDS-MPI）来提高 MPI 的空间分辨率。建立了一个端到端的模型，从低空间分辨率图像生成高空间分辨率图像，避免了上述缺点。我们通过模拟和体模实验评估了所提出的 FDS-MPI 模型的性能。结果表明，FDS-MPI 模型可以将空间分辨率提高两倍。MPI 的这一显著改进将有助于未来医学成像模式在临床前的应用。
