STPDnet: Spatial-temporal convolutional primal dual network for dynamic PET image reconstruction
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).
Code (0)
등록된 구현이 없습니다.
Tasks
Image ReconstructionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A Deep Primal-Dual Network for Guided Depth Super-Resolution
In this paper we present a novel method to increase the spatial resolution of depth images. We combine a deep fully convolutional network with a non-local variational method in a deep primal-dual network. The joint netwo…
Rolling Shutter CorrectionSuper-ResolutionInverted Inference and Recursive Bootstrapping: A Primal-Dual Theory of Structured Cognition
This paper introduces a unifying framework that links the Context-Content Uncertainty Principle (CCUP) with optimal transport (OT) via primal-dual inference. We propose that cognitive representations are not static encod…
AllHippocampusPDNet: Semantic Segmentation integrated with a Primal-Dual Network for Document binarization
Binarization of digital documents is the task of classifying each pixel in an image of the document as belonging to the background (parchment/paper) or foreground (text/ink). Historical documents are often subjected to d…
BinarizationSemantic SegmentationDual-Primal Graph Convolutional Networks
In recent years, there has been a surge of interest in developing deep learning methods for non-Euclidean structured data such as graphs. In this paper, we propose Dual-Primal Graph CNN, a graph convolutional architectur…
Graph AttentionRecommendation SystemsSpatial Residual Layer and Dense Connection Block Enhanced Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition
Recent research has shown that modeling the dynamic joint features of the human body by a graph convolutional network (GCN) is a groundbreaking approach for skeleton-based action recognition, especially for the recogniti…
Action RecognitionSkeleton Based Action Recognition