K-UNN: k-Space Interpolation With Untrained Neural Network
- URL: http://arxiv.org/abs/2208.05827v1
- Date: Thu, 11 Aug 2022 13:53:48 GMT
- Title: K-UNN: k-Space Interpolation With Untrained Neural Network
- Authors: Zhuo-Xu Cui, Sen Jia, Qingyong Zhu, Congcong Liu, Zhilang Qiu,
Yuanyuan Liu, Jing Cheng, Haifeng Wang, Yanjie Zhu and Dong Liang
- Abstract summary: Untrained neural networks (UNNs) have shown satisfactory performances for MR image reconstruction on random sampling trajectories.
We propose a safeguarded k-space method for MRI using a specially designed UNN with a tripled architecture driven by three physical priors of the MR images.
- Score: 28.129181950669686
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Recently, untrained neural networks (UNNs) have shown satisfactory
performances for MR image reconstruction on random sampling trajectories
without using additional full-sampled training data. However, the existing
UNN-based approach does not fully use the MR image physical priors, resulting
in poor performance in some common scenarios (e.g., partial Fourier, regular
sampling, etc.) and the lack of theoretical guarantees for reconstruction
accuracy. To bridge this gap, we propose a safeguarded k-space interpolation
method for MRI using a specially designed UNN with a tripled architecture
driven by three physical priors of the MR images (or k-space data), including
sparsity, coil sensitivity smoothness, and phase smoothness. We also prove that
the proposed method guarantees tight bounds for interpolated k-space data
accuracy. Finally, ablation experiments show that the proposed method can more
accurately characterize the physical priors of MR images than existing
traditional methods. Additionally, under a series of commonly used sampling
trajectories, experiments also show that the proposed method consistently
outperforms traditional parallel imaging methods and existing UNNs, and even
outperforms the state-of-the-art supervised-trained k-space deep learning
methods in some cases.
Related papers
- Joint Edge Optimization Deep Unfolding Network for Accelerated MRI Reconstruction [3.9681863841849623]
We build a joint edge optimization model that not only incorporates individual regularizers specific to both the MR image and the edges, but also enforces a co-regularizer to effectively establish a stronger correlation between them.
Specifically, the edge information is defined through a non-edge probability map to guide the image reconstruction during the optimization process.
Meanwhile, the regularizers pertaining to images and edges are incorporated into a deep unfolding network to automatically learn their respective inherent a-priori information.
arXiv Detail & Related papers (2024-05-09T05:51:33Z) - Self-Supervised k-Space Regularization for Motion-Resolved Abdominal MRI Using Neural Implicit k-Space Representation [3.829690053412406]
We introduce the concept of parallel imaging-inspired self-consistency (PISCO)
We incorporate self-supervised k-space regularization enforcing a consistent neighborhood relationship.
At no additional data cost, the proposed regularization significantly improves neural implicit k-space reconstructions on simulated data.
arXiv Detail & Related papers (2024-04-12T09:31:11Z) - Exploiting Diffusion Prior for Generalizable Dense Prediction [85.4563592053464]
Recent advanced Text-to-Image (T2I) diffusion models are sometimes too imaginative for existing off-the-shelf dense predictors to estimate.
We introduce DMP, a pipeline utilizing pre-trained T2I models as a prior for dense prediction tasks.
Despite limited-domain training data, the approach yields faithful estimations for arbitrary images, surpassing existing state-of-the-art algorithms.
arXiv Detail & Related papers (2023-11-30T18:59:44Z) - Modality-Agnostic Variational Compression of Implicit Neural
Representations [96.35492043867104]
We introduce a modality-agnostic neural compression algorithm based on a functional view of data and parameterised as an Implicit Neural Representation (INR)
Bridging the gap between latent coding and sparsity, we obtain compact latent representations non-linearly mapped to a soft gating mechanism.
After obtaining a dataset of such latent representations, we directly optimise the rate/distortion trade-off in a modality-agnostic space using neural compression.
arXiv Detail & Related papers (2023-01-23T15:22:42Z) - A scan-specific unsupervised method for parallel MRI reconstruction via
implicit neural representation [9.388253054229155]
implicit neural representation (INR) has emerged as a new deep learning paradigm for learning the internal continuity of an object.
The proposed method outperforms existing methods by suppressing the aliasing artifacts and noise.
The high-quality results and scanning specificity make the proposed method hold the potential for further accelerating the data acquisition of parallel MRI.
arXiv Detail & Related papers (2022-10-19T10:16:03Z) - Learning Optimal K-space Acquisition and Reconstruction using
Physics-Informed Neural Networks [46.751292014516025]
Deep neural networks have been applied to reconstruct undersampled k-space data and have shown improved reconstruction performance.
This work proposes a novel framework to learn k-space sampling trajectories by considering it as an Ordinary Differential Equation (ODE) problem.
Experiments were conducted on different in-viv datasets (textite.g., brain and knee images) acquired with different sequences.
arXiv Detail & Related papers (2022-04-05T20:28:42Z) - NUQ: Nonparametric Uncertainty Quantification for Deterministic Neural
Networks [151.03112356092575]
We show the principled way to measure the uncertainty of predictions for a classifier based on Nadaraya-Watson's nonparametric estimate of the conditional label distribution.
We demonstrate the strong performance of the method in uncertainty estimation tasks on a variety of real-world image datasets.
arXiv Detail & Related papers (2022-02-07T12:30:45Z) - PARCEL: Physics-based unsupervised contrastive representation learning
for parallel MR imaging [9.16860702327751]
This paper proposes a physics based unsupervised contrastive representation learning (PARCEL) method to speed up parallel MR imaging.
Specifically, PARCEL has three key ingredients to achieve direct deep learning from the undersampled k-space data.
A specially designed co-training loss is designed to guide the two networks to capture the inherent features and representations of the MR image.
arXiv Detail & Related papers (2022-02-03T10:09:19Z) - Probabilistic 3D surface reconstruction from sparse MRI information [58.14653650521129]
We present a novel probabilistic deep learning approach for concurrent 3D surface reconstruction from sparse 2D MR image data and aleatoric uncertainty prediction.
Our method is capable of reconstructing large surface meshes from three quasi-orthogonal MR imaging slices from limited training sets.
arXiv Detail & Related papers (2020-10-05T14:18:52Z) - Residual-driven Fuzzy C-Means Clustering for Image Segmentation [152.609322951917]
We elaborate on residual-driven Fuzzy C-Means (FCM) for image segmentation.
Built on this framework, we present a weighted $ell_2$-norm fidelity term by weighting mixed noise distribution.
The results demonstrate the superior effectiveness and efficiency of the proposed algorithm over existing FCM-related algorithms.
arXiv Detail & Related papers (2020-04-15T15:46:09Z)
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.