STPDnet: Spatial-Temporal Convolutional Primal Dual Network for Dynamic Pet Image Reconstruction
STPDnet: Spatial-Temporal Convolutional Primal Dual Network for Dynamic Pet Image Reconstruction
复制标题
DOI：
10.1109/isbi53787.2023.10230335
复制
发表时间：
2023-03
期刊：
影响因子：
--
通讯作者：
Rui Hu;Jianan Cui;Chengjin Yu;Yunmei Chen;Huafeng Liu
中科院分区：
文献类型：
--
作者：
Rui Hu;Jianan Cui;Chengjin Yu;Yunmei Chen;Huafeng Liu
动态正电子发射断层扫描(DPET)图像重建是极具挑战性的，因为每一帧接收的计数有限。提出了一种用于动态PET图像重建的时空卷积原始对偶网络(STPDnet)。空间和时间相关性都由3D卷积运算符编码。PET的物理投影被嵌入到网络的迭代学习过程中，提供了物理约束并增强了可解释性。对真实大鼠扫描数据的实验表明，该方法在时间域和空间域均能达到较好的降噪效果，并且优于最大似然期望最大化(MLEM)、空时核方法(KEM-ST)、DeepPET和学习原始对偶(LPD)。
Dynamic positron emission tomography (dPET) image reconstruction is extremely challenging due to the limited counts received in individual frame. In this paper, we propose a spatial-temporal convolutional primal dual network (STPDnet) for dynamic PET image reconstruction. Both spatial and temporal correlations are encoded by 3D convolution operators. The physical projection of PET is embedded in the iterative learning process of the network, which provides the physical constraints and enhances interpretability. The experiments of real rat scan data have shown that the proposed method can achieve substantial noise reduction in both temporal and spatial domains and outperform the maximum likelihood expectation maximization (MLEM), spatial-temporal kernel method (KEM-ST), DeepPET and Learned Primal Dual (LPD).