Momentum-Net for Low-Dose CT Image Reconstruction
- URL: http://arxiv.org/abs/2002.12018v4
- Date: Wed, 9 Sep 2020 02:02:16 GMT
- Title: Momentum-Net for Low-Dose CT Image Reconstruction
- Authors: Siqi Ye, Yong Long, Il Yong Chun
- Abstract summary: This paper applies the recent fast iterative neural network framework, Momentum-Net, using appropriate models to low-dose X-ray computed tomography (LDCT) image reconstruction.
We show that the proposed Momentum-Net architecture significantly improves image reconstruction accuracy, compared to a state-of-the-art noniterative image denoising deep neural network (NN), WavResNet (in LDCT)
We also investigated the spectral normalization technique that applies to image refining NN learning to satisfy the nonexpansive NN property; results show that this does not improve the image reconstruction performance of Momentum-Net
- Score: 13.084578404699172
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This paper applies the recent fast iterative neural network framework,
Momentum-Net, using appropriate models to low-dose X-ray computed tomography
(LDCT) image reconstruction. At each layer of the proposed Momentum-Net, the
model-based image reconstruction module solves the majorized penalized weighted
least-square problem, and the image refining module uses a four-layer
convolutional neural network (CNN). Experimental results with the NIH AAPM-Mayo
Clinic Low Dose CT Grand Challenge dataset show that the proposed Momentum-Net
architecture significantly improves image reconstruction accuracy, compared to
a state-of-the-art noniterative image denoising deep neural network (NN),
WavResNet (in LDCT). We also investigated the spectral normalization technique
that applies to image refining NN learning to satisfy the nonexpansive NN
property; however, experimental results show that this does not improve the
image reconstruction performance of Momentum-Net.
Related papers
- 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.
A novel method for converting the complex-valued convolutional layers and activations into spiking neural networks (SNNs) is developed.
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.
It leverages the low-rank properties of wavelet coefficients derived from the 2-D frontal slice-wise Haar discrete wavelet transform.
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) - Application of Spherical Convolutional Neural Networks to Image Reconstruction and Denoising in Nuclear Medicine [0.31923933006157473]
equivariant neural networks are efficient and high-performance frameworks for image reconstruction and denoising in nuclear medicine.
We implemented and evaluated equivariant spherical CNNs for 2- and 3-dimensional medical imaging problems.
Our results demonstrate superior quality and computational efficiency of SCNNs in both image reconstruction and denoising benchmark problems.
arXiv Detail & Related papers (2023-07-06T21:18:47Z) - InDuDoNet+: A Model-Driven Interpretable Dual Domain Network for Metal
Artifact Reduction in CT Images [53.4351366246531]
We construct a novel interpretable dual domain network, termed InDuDoNet+, into which CT imaging process is finely embedded.
We analyze the CT values among different tissues, and merge the prior observations into a prior network for our InDuDoNet+, which significantly improve its generalization performance.
arXiv Detail & Related papers (2021-12-23T15:52:37Z) - Adaptive Gradient Balancing for UndersampledMRI Reconstruction and
Image-to-Image Translation [60.663499381212425]
We enhance the image quality by using a Wasserstein Generative Adversarial Network combined with a novel Adaptive Gradient Balancing technique.
In MRI, our method minimizes artifacts, while maintaining a high-quality reconstruction that produces sharper images than other techniques.
arXiv Detail & Related papers (2021-04-05T13:05:22Z) - DAN-Net: Dual-Domain Adaptive-Scaling Non-local Network for CT Metal
Artifact Reduction [15.225899631788973]
Metal implants can heavily attenuate X-rays in computed tomography (CT) scans, leading to severe artifacts in reconstructed images.
Several network models have been proposed for metal artifact reduction (MAR) in CT.
We present a novel Dual-domain Adaptive-scaling Non-local network (DAN-Net) for MAR.
arXiv Detail & Related papers (2021-02-16T08:09:16Z) - An Improved Iterative Neural Network for High-Quality Image-Domain
Material Decomposition in Dual-Energy CT [16.84451472788859]
Image-domain methods directly decompose material images from high- and low-energy attenuation images.
Various data-driven methods have been proposed to obtain high-quality material images.
Iterative neural network (NN) methods combine regression NNs and model-based image reconstruction.
arXiv Detail & Related papers (2020-12-02T16:27:38Z) - EDCNN: Edge enhancement-based Densely Connected Network with Compound
Loss for Low-Dose CT Denoising [27.86840312836051]
We propose the Edge enhancement based Densely connected Convolutional Neural Network (EDCNN)
We construct a model with dense connections to fuse the extracted edge information and realize end-to-end image denoising.
Compared with the existing low-dose CT image denoising algorithms, our proposed model has a better performance in preserving details and suppressing noise.
arXiv Detail & Related papers (2020-10-30T23:12:09Z) - Perceptually Optimizing Deep Image Compression [53.705543593594285]
Mean squared error (MSE) and $ell_p$ norms have largely dominated the measurement of loss in neural networks.
We propose a different proxy approach to optimize image analysis networks against quantitative perceptual models.
arXiv Detail & Related papers (2020-07-03T14:33:28Z) - Iterative Network for Image Super-Resolution [69.07361550998318]
Single image super-resolution (SISR) has been greatly revitalized by the recent development of convolutional neural networks (CNN)
This paper provides a new insight on conventional SISR algorithm, and proposes a substantially different approach relying on the iterative optimization.
A novel iterative super-resolution network (ISRN) is proposed on top of the iterative optimization.
arXiv Detail & Related papers (2020-05-20T11:11:47Z) - Geometric Approaches to Increase the Expressivity of Deep Neural
Networks for MR Reconstruction [41.62169556793355]
Deep learning approaches have been extensively investigated to reconstruct images from accelerated magnetic resonance image (MRI) acquisition.
It is not clear how to choose a suitable network architecture to balance the trade-off between network complexity and performance.
This paper proposes a systematic geometric approach using bootstrapping and subnetwork aggregation to increase the expressivity of the underlying neural network.
arXiv Detail & Related papers (2020-03-17T14:18:37Z)
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.