Dynamic PET Image Reconstruction via Non-negative INR Factorization

• URL: http://arxiv.org/abs/2503.08025v1
• Date: Tue, 11 Mar 2025 04:13:30 GMT
• Title: Dynamic PET Image Reconstruction via Non-negative INR Factorization
• Authors: Chaozhi Zhang, Wenxiang Ding, Roy Y. He, Xiaoqun Zhang, Qiaoqiao Ding,
• Abstract summary: We introduce an unsupervised learning approach, Non-negative Implicit Neural Representation Factorization (textttNINRF), based on low rank matrix factorization of unknown images.<n>Experiments on dynamic PET reconstruction with Poisson noise demonstrate the effectiveness of the proposed method.
• Score: 2.6408529601818422
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The reconstruction of dynamic positron emission tomography (PET) images from noisy projection data is a significant but challenging problem. In this paper, we introduce an unsupervised learning approach, Non-negative Implicit Neural Representation Factorization (\texttt{NINRF}), based on low rank matrix factorization of unknown images and employing neural networks to represent both coefficients and bases. Mathematically, we demonstrate that if a sequence of dynamic PET images satisfies a generalized non-negative low-rank property, it can be decomposed into a set of non-negative continuous functions varying in the temporal-spatial domain. This bridges the well-established non-negative matrix factorization (NMF) with continuous functions and we propose using implicit neural representations (INRs) to connect matrix with continuous functions. The neural network parameters are obtained by minimizing the KL divergence, with additional sparsity regularization on coefficients and bases. Extensive experiments on dynamic PET reconstruction with Poisson noise demonstrate the effectiveness of the proposed method compared to other methods, while giving continuous representations for object's detailed geometric features and regional concentration variation.

Related papers

• Implicit neural representations for end-to-end PET reconstruction [3.7066816275267627]
  Implicit neural representations (INRs) have demonstrated strong capabilities in various medical imaging tasks. We propose an unsupervised PET image reconstruction method based on the implicit SIREN neural network architecture. Our method incorporates a forward projection model and a loss function adapted to perform PET image reconstruction directly from sinograms.
  arXiv  Detail & Related papers  (2025-03-26T08:30:53Z)
• Deep-Unrolling Multidimensional Harmonic Retrieval Algorithms on Neuromorphic Hardware [78.17783007774295]
  This paper explores the potential of conversion-based neuromorphic algorithms for highly accurate and energy-efficient single-snapshot multidimensional harmonic retrieval.<n>A novel method for converting the complex-valued convolutional layers and activations into spiking neural networks (SNNs) is developed.<n>The converted SNNs achieve almost five-fold power efficiency at moderate performance loss compared to the original CNNs.
  arXiv  Detail & Related papers  (2024-12-05T09:41:33Z)
• Haar Nuclear Norms with Applications to Remote Sensing Imagery Restoration [53.68392692185276]
  This paper proposes a novel low-rank regularization term, named the Haar nuclear norm (HNN), for efficient and effective remote sensing image restoration.<n>It leverages the low-rank properties of wavelet coefficients derived from the 2-D frontal slice-wise Haar discrete wavelet transform.<n> Experimental evaluations conducted on hyperspectral image inpainting, multi-temporal image cloud removal, and hyperspectral image denoising have revealed the HNN's potential.
  arXiv  Detail & Related papers  (2024-07-11T13:46:47Z)
• Inferring stochastic low-rank recurrent neural networks from neural data [5.179844449042386]
  A central aim in computational neuroscience is to relate the activity of large neurons to an underlying dynamical system.<n>Low-rank recurrent neural networks (RNNs) exhibit such interpretability by having tractable dynamics.<n>Here, we propose to fit low-rank RNNs with variational sequential Monte Carlo methods.
  arXiv  Detail & Related papers  (2024-06-24T15:57:49Z)
• Enhancing Dynamic CT Image Reconstruction with Neural Fields and Optical Flow [0.0]
  We show the benefits of introducing explicit motion regularizers for dynamic inverse problems based on partial differential equations.<n>We also compare neural fields against a grid-based solver and show that the former outperforms the latter in terms of PSNR.
  arXiv  Detail & Related papers  (2024-06-03T13:07:29Z)
• Ray-driven Spectral CT Reconstruction Based on Neural Base-Material Fields [10.684377265644045]
  In spectral CT reconstruction, the basis materials decomposition involves solving a large-scale nonlinear system of integral equations. This paper proposes a model that parameterizes the attenuation coefficients of the object using a neural field representation. It introduces a lightweight discretization method for line integrals based on a ray-driven neural field.
  arXiv  Detail & Related papers  (2024-04-10T13:10:52Z)
• A novel image space formalism of Fourier domain interpolation neural networks for noise propagation analysis [0.0]
  We develop an image space formalism of convolutional neural networks (CNNs) for the Fourier domain in MRI reconstructions. Inferences conducted in the image domain are quasi-identical to inferences in the k-space. The noise resilience is well characterized, as in the case of classical Parallel Imaging.
  arXiv  Detail & Related papers  (2024-02-27T11:01:58Z)
• Non Commutative Convolutional Signal Models in Neural Networks: Stability to Small Deformations [111.27636893711055]
  We study the filtering and stability properties of non commutative convolutional filters. Our results have direct implications for group neural networks, multigraph neural networks and quaternion neural networks.
  arXiv  Detail & Related papers  (2023-10-05T20:27:22Z)
• Convolutional Filtering and Neural Networks with Non Commutative Algebras [153.20329791008095]
  We study the generalization of non commutative convolutional neural networks. We show that non commutative convolutional architectures can be stable to deformations on the space of operators.
  arXiv  Detail & Related papers  (2021-08-23T04:22:58Z)
• Limited-angle tomographic reconstruction of dense layered objects by dynamical machine learning [68.9515120904028]
  Limited-angle tomography of strongly scattering quasi-transparent objects is a challenging, highly ill-posed problem. Regularizing priors are necessary to reduce artifacts by improving the condition of such problems. We devised a recurrent neural network (RNN) architecture with a novel split-convolutional gated recurrent unit (SC-GRU) as the building block.
  arXiv  Detail & Related papers  (2020-07-21T11:48:22Z)
• Provably Efficient Neural Estimation of Structural Equation Model: An Adversarial Approach [144.21892195917758]
  We study estimation in a class of generalized Structural equation models (SEMs) We formulate the linear operator equation as a min-max game, where both players are parameterized by neural networks (NNs), and learn the parameters of these neural networks using a gradient descent. For the first time we provide a tractable estimation procedure for SEMs based on NNs with provable convergence and without the need for sample splitting.
  arXiv  Detail & Related papers  (2020-07-02T17:55:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.