Limited View Tomographic Reconstruction Using a Cascaded Residual Dense Spatial-Channel Attention Network With Projection Data Fidelity Layer

Zhou, Bo; Zhou, S. Kevin; Duncan, James S.; Liu, Chi

doi:10.1109/tmi.2021.3066318

Cited by 45 publications

(23 citation statements)

References 43 publications

(65 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another approach is to consider transformer-based architectures that are better suited than convolutional DNNs due to their non-local nature. As shown in [97], such transformer-based DNNs have excellent performance for reconstruction in limited angle tomography. A downside of transformer DNNs is that they are very demanding to train and require massive amounts of training data, so this approach will scale poorly.…”

Section: Joint Sinogram Inpainting and Reconstructionmentioning

confidence: 97%

“…Finally, we also mention [97] that develops an approach with a transformer-based DNN architecture instead of convolutional DNNs. Streak artefacts in limited-angle tomography are non-local.…”

Section: Joint Sinogram Inpainting and Reconstructionmentioning

confidence: 99%

“…Some of the issues related to memory footprint could perhaps be addressed by using more domain adapted transformer architectures, like Fourier Image Transformer [14]. Furthermore, there are still no guarantees that [97] extrapolates the missing data in a microlocally consistent manner.…”

Section: Joint Sinogram Inpainting and Reconstructionmentioning

confidence: 99%

See 2 more Smart Citations

Deep Microlocal Reconstruction for Limited-Angle Tomography

Andrade-Loarca¹,

Kutyniok²,

Öktem³

et al. 2021

Preprint

View full text Add to dashboard Cite

We present a deep learning-based algorithm to jointly solve a reconstruction problem and a wavefront set extraction problem in tomographic imaging. The algorithm is based on a recently developed digital wavefront set extractor as well as the well-known microlocal canonical relation for the Radon transform. We use the wavefront set information about x-ray data to improve the reconstruction by requiring that the underlying neural networks simultaneously extract the correct ground truth wavefront set and ground truth image. As a necessary theoretical step, we identify the digital microlocal canonical relations for deep convolutional residual neural networks. We find strong numerical evidence for the effectiveness of this approach.

show abstract

Section: Joint Sinogram Inpainting and Reconstructionmentioning

confidence: 97%

Section: Joint Sinogram Inpainting and Reconstructionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Microlocal Reconstruction for Limited-Angle Tomography

Andrade-Loarca¹,

Kutyniok²,

Öktem³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Lee et al [28] complemented the missing projection information based on a U-Net. Zhou et al [29] proposed a cascading attention network of residual dense spatial channels capable of generating high-quality reconstruction results.…”

Section: Introductionmentioning

confidence: 99%

ADMM-SVNet: An ADMM-Based Sparse-View CT Reconstruction Network

Wang

Chen

2022

Photonics

View full text Add to dashboard Cite

In clinical medical applications, sparse-view computed tomography (CT) imaging is an effective method for reducing radiation doses. The iterative reconstruction method is usually adopted for sparse-view CT. In the process of optimizing the iterative model, the approach of directly solving the quadratic penalty function of the objective function can be expected to perform poorly. Compared with the direct solution method, the alternating direction method of multipliers (ADMM) algorithm can avoid the ill-posed problem associated with the quadratic penalty function. However, the regularization items, sparsity transform, and parameters in the traditional ADMM iterative model need to be manually adjusted. In this paper, we propose a data-driven ADMM reconstruction method that can automatically optimize the above terms that are difficult to choose within an iterative framework. The main contribution of this paper is that a modified U-net represents the sparse transformation, and the prior information and related parameters are automatically trained by the network. Based on a comparison with other state-of-the-art reconstruction algorithms, the qualitative and quantitative results show the effectiveness of our method for sparse-view CT image reconstruction. The experimental results show that the proposed method performs well in streak artifact elimination and detail structure preservation. The proposed network can deal with a wide range of noise levels and has exceptional performance in low-dose reconstruction tasks.

show abstract

“…Although these conventional image post-processing methods may substantially improve the image quality, over-smoothing is often observed in ultra-low-dose data. Recently, deep learning techniques have achieved promising performance in medical imaging applications, such as reconstruction [23]- [27], segmentation [28]- [30], registration [31] and denoising [32]. As the statistical characteristics of noise in medical imaging Fig.…”

Section: Introductionmentioning

confidence: 99%

MDPET: A Unified Motion Correction and Denoising Adversarial Network for Low-Dose Gated PET

Zhou

Tsai

Chen

et al. 2021

IEEE Trans. Med. Imaging

Self Cite

View full text Add to dashboard Cite

In positron emission tomography (PET), gating is commonly utilized to reduce respiratory motion blurring and to facilitate motion correction methods. In application where low-dose gated PET is useful, reducing injection dose causes increased noise levels in gated images that could corrupt motion estimation and subsequent corrections, leading to inferior image quality. To address these issues, we propose MDPET, a unified motion correction and denoising adversarial network for generating motion-compensated low-noise images from low-dose gated PET data. Specifically, we proposed a Temporal Siamese Pyramid Network (TSP-Net) with basic units made up of 1.) Siamese Pyramid Network (SP-Net), and 2.) a recurrent layer for motion estimation among the gates. The denoising network is unified with our motion estimation network to simultaneously correct the motion and predict a motioncompensated denoised PET reconstruction. The experimental results on human data demonstrated that our MDPET can generate accurate motion estimation directly from low-dose gated images and produce high-quality motion-compensated low-noise reconstructions. Comparative studies with previous methods also show that our MDPET is able to generate superior motion estimation and denoising performance. Our code is available at https://github.com/bbbbbbzhou/MDPET.

show abstract

Limited View Tomographic Reconstruction Using a Cascaded Residual Dense Spatial-Channel Attention Network With Projection Data Fidelity Layer

Cited by 45 publications

References 43 publications

Deep Microlocal Reconstruction for Limited-Angle Tomography

Deep Microlocal Reconstruction for Limited-Angle Tomography

ADMM-SVNet: An ADMM-Based Sparse-View CT Reconstruction Network

MDPET: A Unified Motion Correction and Denoising Adversarial Network for Low-Dose Gated PET

Contact Info

Product

Resources

About