Hybrid Kinetics Embedding Framework for Dynamic PET Reconstruction
arxiv(2024)
摘要
In dynamic positron emission tomography (PET) reconstruction, the importance
of leveraging the temporal dependence of the data has been well appreciated.
Current deep-learning solutions can be categorized in two groups in the way the
temporal dynamics is modeled: data-driven approaches use spatiotemporal neural
networks to learn the temporal dynamics of tracer kinetics from data, which
relies heavily on data supervision; physics-based approaches leverage a
priori tracer kinetic models to focus on inferring their parameters, which
relies heavily on the accuracy of the prior kinetic model. In this paper, we
marry the strengths of these two approaches in a hybrid kinetics embedding
(HyKE-Net) framework for dynamic PET reconstruction. We first introduce a novel
hybrid model of tracer kinetics consisting of a physics-based function
augmented by a neural component to account for its gap to data-generating
tracer kinetics, both identifiable from data. We then embed this hybrid model
at the latent space of an encoding-decoding framework to enable both supervised
and unsupervised identification of the hybrid kinetics and thereby dynamic PET
reconstruction. Through both phantom and real-data experiments, we demonstrate
the benefits of HyKE-Net – especially in unsupervised reconstructions – over
existing physics-based and data-driven baselines as well as its ablated
formulations where the embedded tracer kinetics are purely physics-based,
purely neural, or hybrid but with a non-adaptable neural component.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要