Image reconstruction for positron emission tomography (PET) is challenging because of the ill-conditioned tomographic problem and low counting statistics. Kernel methods address this challenge by using kernel representation to incorporate image prior information in the forward model of iterative PET image reconstruction. Existing kernel methods construct the kernels commonly using an empirical process, which may lead to suboptimal performance. In this paper, we describe the equivalence between the kernel representation and a trainable neural network model. A deep kernel method is proposed by exploiting deep neural networks to enable an automated learning of an optimized kernel model. The proposed method is directly applicable to single subjects. The training process utilizes available image prior data to seek the best way to form a set of robust kernels optimally rather than empirically. The results from computer simulations and a real patient dataset demonstrate that the proposed deep kernel method can outperform existing kernel method and neural network method for dynamic PET image reconstruction.
翻译:红外线排放断层造影(PET)的图像重建具有挑战性,因为有不成熟的断层成像问题和低计数统计。内核方法应对这一挑战,使用内核表示法将图像先前信息纳入迭接的 PET 图像重建前模式。现有的内核方法通常使用经验过程来构造内核,这可能导致不理想的性能。在本文中,我们描述了内核表示法和可训练的神经网络模型之间的等值。我们建议了一种深内核方法,即利用深神经网络,以便能够自动学习优化的内核模型。拟议方法直接适用于单个主题。培训过程利用现有的先前数据,以最佳的方式而不是以实验方式寻找形成一套坚固的内核的最佳方法。计算机模拟的结果和真正的病人数据集表明,拟议的深内核方法可以超越动态的PET图像重建的现有内核方法和神经网络方法。