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).

翻译：基于深度学习的PET图像重建方法近年来取得了令人瞩目的成果。然而，这些方法大多遵循监督学习范式，高度依赖于高质量训练标签的可用性。尤其值得注意的是，PET扫描所需的长采集时间及高辐射暴露使得获取此类标签变得不切实际。本文提出了一种基于学习下降算法的双域无监督PET图像重建方法，该方法无需图像标签，即可从正弦图中重建出高质量的PET图像。具体而言，我们针对PET图像重建问题，采用可学习的l2,1范数展开近端梯度法。该训练过程是无监督的，同时利用了基于深度图像先验的测量域损失和基于旋转等变性质的图像域损失。实验结果表明，与最大似然期望最大化（MLEM）、全变分正则化期望最大化（EM-TV）以及基于深度图像先验的方法（DIP）相比，所提方法具有更优越的性能。