Sparse-View Spectral CT Reconstruction Using Deep Learning
- URL: http://arxiv.org/abs/2011.14842v2
- Date: Fri, 26 Mar 2021 23:49:03 GMT
- Title: Sparse-View Spectral CT Reconstruction Using Deep Learning
- Authors: Wail Mustafa, Christian Kehl, Ulrik Lund Olsen, S{\o}ren Kimmer Schou
Gregersen, David Malmgren-Hansen, Jan Kehres, Anders Bjorholm Dahl
- Abstract summary: We propose an approach for fast reconstruction of sparse-view spectral CT data using a U-Net convolutional neural network architecture with multi-channel input and output.
Our method is fast at run-time and because the internal convolutions are shared between the channels, the computational load increases only at the first and last layers.
- Score: 0.283239609744735
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Spectral computed tomography (CT) is an emerging technology capable of
providing high chemical specificity, which is crucial for many applications
such as detecting threats in luggage. This type of application requires both
fast and high-quality image reconstruction and is often based on sparse-view
(few) projections. The conventional filtered back projection (FBP) method is
fast but it produces low-quality images dominated by noise and artifacts in
sparse-view CT. Iterative methods with, e.g., total variation regularizers can
circumvent that but they are computationally expensive, as the computational
load proportionally increases with the number of spectral channels. Instead, we
propose an approach for fast reconstruction of sparse-view spectral CT data
using a U-Net convolutional neural network architecture with multi-channel
input and output. The network is trained to output high-quality CT images from
FBP input image reconstructions. Our method is fast at run-time and because the
internal convolutions are shared between the channels, the computational load
increases only at the first and last layers, making it an efficient approach to
process spectral data with a large number of channels. We have validated our
approach using real CT scans. Our results show qualitatively and quantitatively
that our approach outperforms the state-of-the-art iterative methods.
Furthermore, the results indicate that the network can exploit the coupling of
the channels to enhance the overall quality and robustness.
Related papers
- UnWave-Net: Unrolled Wavelet Network for Compton Tomography Image Reconstruction [0.0]
Compton scatter tomography (CST) presents an interesting alternative to conventional CT.
Deep unrolling networks have demonstrated potential in CT image reconstruction.
UnWave-Net is a novel unrolled wavelet-based reconstruction network.
arXiv Detail & Related papers (2024-06-05T16:10:29Z) - WiTUnet: A U-Shaped Architecture Integrating CNN and Transformer for Improved Feature Alignment and Local Information Fusion [16.41082757280262]
Low-dose computed tomography (LDCT) has become the technology of choice for diagnostic medical imaging, given its lower radiation dose compared to standard CT.
In this paper, we introduce WiTUnet, a novel LDCT image denoising method that utilizes nested, dense skip pathways instead of traditional skip connections.
arXiv Detail & Related papers (2024-04-15T07:53:07Z) - TCCT-Net: Two-Stream Network Architecture for Fast and Efficient Engagement Estimation via Behavioral Feature Signals [58.865901821451295]
We present a novel two-stream feature fusion "Tensor-Convolution and Convolution-Transformer Network" (TCCT-Net) architecture.
To better learn the meaningful patterns in the temporal-spatial domain, we design a "CT" stream that integrates a hybrid convolutional-transformer.
In parallel, to efficiently extract rich patterns from the temporal-frequency domain, we introduce a "TC" stream that uses Continuous Wavelet Transform (CWT) to represent information in a 2D tensor form.
arXiv Detail & Related papers (2024-04-15T06:01:48Z) - Distance Weighted Trans Network for Image Completion [52.318730994423106]
We propose a new architecture that relies on Distance-based Weighted Transformer (DWT) to better understand the relationships between an image's components.
CNNs are used to augment the local texture information of coarse priors.
DWT blocks are used to recover certain coarse textures and coherent visual structures.
arXiv Detail & Related papers (2023-10-11T12:46:11Z) - A three-dimensional dual-domain deep network for high-pitch and sparse
helical CT reconstruction [13.470588027095264]
We propose a new GPU implementation of the Katsevich algorithm for helical CT reconstruction.
Our implementation divides the sinograms and reconstructs the CT images pitch by pitch.
By embedding our implementation into the network, we propose an end-to-end deep network for the high pitch helical CT reconstruction.
arXiv Detail & Related papers (2022-01-07T03:26:15Z) - The Application of Convolutional Neural Networks for Tomographic
Reconstruction of Hyperspectral Images [0.0]
A novel method, utilizing convolutional neural networks (CNNs), is proposed to reconstruct hyperspectral cubes from computed imaging spectrometer (CTIS) images.
CNNs deliver higher precision and shorter reconstruction time than a standard expectation algorithm.
arXiv Detail & Related papers (2021-08-30T18:11:08Z) - Fast and High-Quality Blind Multi-Spectral Image Pansharpening [48.68143888901669]
We propose a fast approach to blind pansharpening and achieve state-of-the-art image reconstruction quality.
To achieve fast blind pansharpening, we decouple the solution of the blur kernel and of the HRMS image.
Our algorithm outperforms state-of-the-art model-based counterparts in terms of both computational time and reconstruction quality.
arXiv Detail & Related papers (2021-03-17T23:12:14Z) - Learning Frequency-aware Dynamic Network for Efficient Super-Resolution [56.98668484450857]
This paper explores a novel frequency-aware dynamic network for dividing the input into multiple parts according to its coefficients in the discrete cosine transform (DCT) domain.
In practice, the high-frequency part will be processed using expensive operations and the lower-frequency part is assigned with cheap operations to relieve the computation burden.
Experiments conducted on benchmark SISR models and datasets show that the frequency-aware dynamic network can be employed for various SISR neural architectures.
arXiv Detail & Related papers (2021-03-15T12:54:26Z) - Deep Unfolded Recovery of Sub-Nyquist Sampled Ultrasound Image [94.42139459221784]
We propose a reconstruction method from sub-Nyquist samples in the time and spatial domain, that is based on unfolding the ISTA algorithm.
Our method allows reducing the number of array elements, sampling rate, and computational time while ensuring high quality imaging performance.
arXiv Detail & Related papers (2021-03-01T19:19:38Z) - Learning Spatial-Spectral Prior for Super-Resolution of Hyperspectral
Imagery [79.69449412334188]
In this paper, we investigate how to adapt state-of-the-art residual learning based single gray/RGB image super-resolution approaches.
We introduce a spatial-spectral prior network (SSPN) to fully exploit the spatial information and the correlation between the spectra of the hyperspectral data.
Experimental results on some hyperspectral images demonstrate that the proposed SSPSR method enhances the details of the recovered high-resolution hyperspectral images.
arXiv Detail & Related papers (2020-05-18T14:25:50Z) - Learned Spectral Computed Tomography [0.0]
We propose a Deep Learning imaging method for Spectral Photon-Counting Computed Tomography.
The method takes the form of a two-step learned primal-dual algorithm that is trained using case-specific data.
The proposed approach is characterised by fast reconstruction capability and high imaging performance, even in limited-data cases.
arXiv Detail & Related papers (2020-03-09T13:39:12Z)
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.