DULDA: Dual-domain Unsupervised Learned Descent Algorithm for PET image reconstruction
DULDA: Dual-domain Unsupervised Learned Descent Algorithm for PET image reconstruction
复制标题
DOI：
10.48550/arxiv.2303.04661
复制
发表时间：
2023-03
期刊：
影响因子：
--
通讯作者：
Rui Hu;Yunmei Chen;Kyungsang Kim;M. Rockenbach;Quanzheng Li;Huafeng Liu
中科院分区：
文献类型：
--
作者：
Rui Hu;Yunmei Chen;Kyungsang Kim;M. Rockenbach;Quanzheng Li;Huafeng Liu
基于深度学习的PET图像重建方法最近取得了令人鼓舞的成果。然而，这些方法中的大多数都遵循监督学习范式，这在很大程度上依赖于高质量训练标签的可用性。特别是，所需的长扫描时间和与PET扫描相关的高辐射暴露使得获得这种标签不切实际。本文提出了一种基于学习的decent算法的双域无监督PET图像重建方法，该方法不需要对图像进行标记，即可从正弦图中重建出高质量的PET图像。具体来说，我们展开的近端梯度方法与可学习的l2，1范数的PET图像重建问题。训练是无监督的，使用基于深度图像先验的测量域损失以及基于旋转等方差特性的图像域损失。实验结果表明，与最大似然期望最大化（MLEM）、全变差正则化EM（EM-TV）和基于深度图像先验的方法（DIP）相比，该方法具有上级性能.
Deep learning based PET image reconstruction methods have achieved promising results recently. However, most of these methods follow a supervised learning paradigm, which rely heavily on the availability of high-quality training labels. In particular, the long scanning time required and high radiation exposure associated with PET scans make obtaining this labels impractical. In this paper, we propose a dual-domain unsupervised PET image reconstruction method based on learned decent algorithm, which reconstructs high-quality PET images from sinograms without the need for image labels. Specifically, we unroll the proximal gradient method with a learnable l2,1 norm for PET image reconstruction problem. The training is unsupervised, using measurement domain loss based on deep image prior as well as image domain loss based on rotation equivariance property. The experimental results domonstrate the superior performance of proposed method compared with maximum likelihood expectation maximazation (MLEM), total-variation regularized EM (EM-TV) and deep image prior based method (DIP).