A Data-Driven Reconstruction Technique based on Newton's Method for
Emission Tomography
- URL: http://arxiv.org/abs/2110.11396v1
- Date: Tue, 19 Oct 2021 14:54:34 GMT
- Title: A Data-Driven Reconstruction Technique based on Newton's Method for
Emission Tomography
- Authors: Loizos Koutsantonis, Tiago Carneiro, Emmanuel Kieffer, Frederic Pinel,
Pascal Bouvry
- Abstract summary: DNR-Net is capable of providing high-quality image reconstructions using data from SPECT phantom simulations.
The DNR-Net produces reconstructions comparable to the ones produced by OSEM while featuring higher contrast and less noise.
- Score: 1.2209547858269227
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: In this work, we present the Deep Newton Reconstruction Network (DNR-Net), a
hybrid data-driven reconstruction technique for emission tomography inspired by
Newton's method, a well-known iterative optimization algorithm. The DNR-Net
employs prior information about the tomographic problem provided by the
projection operator while utilizing deep learning approaches to a) imitate
Newton's method by approximating the Newton descent direction and b) provide
data-driven regularisation. We demonstrate that DNR-Net is capable of providing
high-quality image reconstructions using data from SPECT phantom simulations by
applying it to reconstruct images from noisy sinograms, each one containing 24
projections. The Structural Similarity Index (SSIM) and the Contrast-to-Noise
ratio (CNR) were used to quantify the image quality. We also compare our
results to those obtained by the OSEM method. According to the quantitative
results, the DNR-Net produces reconstructions comparable to the ones produced
by OSEM while featuring higher contrast and less noise.
Related papers
- DensePANet: An improved generative adversarial network for photoacoustic tomography image reconstruction from sparse data [1.4665304971699265]
We propose an end-to-end method called DensePANet to solve the problem of PAT image reconstruction from sparse data.
The proposed model employs a novel modification of UNet in its generator, called FD-UNet++, which considerably improves the reconstruction performance.
arXiv Detail & Related papers (2024-04-19T09:52:32Z) - Multi-stage image denoising with the wavelet transform [125.2251438120701]
Deep convolutional neural networks (CNNs) are used for image denoising via automatically mining accurate structure information.
We propose a multi-stage image denoising CNN with the wavelet transform (MWDCNN) via three stages, i.e., a dynamic convolutional block (DCB), two cascaded wavelet transform and enhancement blocks (WEBs) and residual block (RB)
arXiv Detail & Related papers (2022-09-26T03:28:23Z) - Self-Supervised Coordinate Projection Network for Sparse-View Computed
Tomography [31.774432128324385]
We propose a Self-supervised COordinate Projection nEtwork (SCOPE) to reconstruct the artifacts-free CT image from a single SV sinogram.
Compared with recent related works that solve similar problems using implicit neural representation network (INR), our essential contribution is an effective and simple re-projection strategy.
arXiv Detail & Related papers (2022-09-12T06:14:04Z) - SAR Despeckling using a Denoising Diffusion Probabilistic Model [52.25981472415249]
The presence of speckle degrades the image quality and adversely affects the performance of SAR image understanding applications.
We introduce SAR-DDPM, a denoising diffusion probabilistic model for SAR despeckling.
The proposed method achieves significant improvements in both quantitative and qualitative results over the state-of-the-art despeckling methods.
arXiv Detail & Related papers (2022-06-09T14:00:26Z) - SPECT Angle Interpolation Based on Deep Learning Methodologies [0.0]
A novel method for SPECT angle based on deep learning methodologies is presented.
Projection data from software phantoms were used to train the proposed model.
For evaluation of the efficacy of the method, phantoms based on Shepp Logan, with various noise levels added were used.
The resulting interpolated sinograms are reconstructed using Ordered Subset Expectation Maximization (OSEM) and compared to the reconstructions of the original sinograms.
arXiv Detail & Related papers (2021-08-09T09:19:51Z) - 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) - Deep Gaussian Scale Mixture Prior for Spectral Compressive Imaging [48.34565372026196]
We propose a novel HSI reconstruction method based on the a Posterior (MAP) estimation framework.
We also propose to estimate the local means of the GSM models by the deep convolutional neural network (DCNN)
arXiv Detail & Related papers (2021-03-12T08:57:06Z) - SPECT Imaging Reconstruction Method Based on Deep Convolutional Neural
Network [0.0]
"CNN Reconstruction - CNNR" is a novel method for tomographic reconstruction in the field of SPECT imaging.
Deep Learning methodologies and deep convolutional neural networks are employed in the new reconstruction method.
arXiv Detail & Related papers (2020-10-19T13:11:32Z) - Deep Variational Network Toward Blind Image Restoration [60.45350399661175]
Blind image restoration is a common yet challenging problem in computer vision.
We propose a novel blind image restoration method, aiming to integrate both the advantages of them.
Experiments on two typical blind IR tasks, namely image denoising and super-resolution, demonstrate that the proposed method achieves superior performance over current state-of-the-arts.
arXiv Detail & Related papers (2020-08-25T03:30:53Z) - Attention Based Real Image Restoration [48.933507352496726]
Deep convolutional neural networks perform better on images containing synthetic degradations.
This paper proposes a novel single-stage blind real image restoration network (R$2$Net)
arXiv Detail & Related papers (2020-04-26T04:21:49Z) - Noise2Inverse: Self-supervised deep convolutional denoising for
tomography [0.0]
Noise2Inverse is a deep CNN-based denoising method for linear image reconstruction algorithms.
We develop a theoretical framework which shows that such training indeed obtains a denoising CNN.
On simulated CT datasets, Noise2Inverse demonstrates an improvement in peak signal-to-noise ratio and structural similarity index.
arXiv Detail & Related papers (2020-01-31T12:50:24Z)
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.