ADAPTIVE-NET: deep computed tomography reconstruction network with analytical domain transformation knowledge

Ge, Yongshuai; Su, Ting; Zhu, Jiongtao; Deng, Xiaolei; Zhang, Qiyang; Chen, Jianwei; Hu, Zhanli; Zheng, Hairong; Liang, Dong

doi:10.21037/qims.2019.12.12

Cited by 43 publications

(29 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although artifacts can be well controlled with the very standard MSE loss, the output images of DIR-DBTnet become slightly smoothed compared to the images obtained from the FBP method. As demonstrated in literatures, 25,30,31 more advanced loss functions, such as the MAE loss, the VGG perceptual loss and the WGAN loss, may encourage edge preservation and thus yield images with better spatial resolution.…”

Section: Discussionmentioning

confidence: 93%

“…To address this problem, we developed two user-defined GPU accelerated TensorFlow operators: ðÁÞand ðÁÞ. 25 In particular, they are implemented in C++ and registered with the Tensorflow system. Both of the ðÁÞ and ðÁÞ operators accept a group of system geometry parameters and finally calculate the forward projection and backprojection results in parallel on the GPU.…”

Section: The Dir-dbtnetmentioning

confidence: 99%

“…Because the DBT imaging uses the 3D cone‐beam geometry, the matrix

A

and

A^{T}

would consume a huge amount of computation resource if they are stored on RAM. To address this problem, we developed two user‐defined GPU accelerated TensorFlow operators:

F P (\cdot)

and

B P (\cdot)

25 . In particular, they are implemented in C++ and registered with the Tensorflow system.…”

Section: The Dir‐dbtnetmentioning

confidence: 99%

See 2 more Smart Citations

DIR‐DBTnet: Deep iterative reconstruction network for three‐dimensional digital breast tomosynthesis imaging

Deng

Yang

et al. 2021

Medical Physics

Self Cite

View full text Add to dashboard Cite

The goal of this study is to develop a three-dimensional (3D) iterative reconstruction framework based on the deep learning (DL) technique to improve the digital breast tomosynthesis (DBT) imaging performance. Methods: In this work, the DIR-DBTnet is developed for DBT image reconstruction by mapping the conventional iterative reconstruction (IR) algorithm to the deep neural network. By design, the DIR-DBTnet learns and optimizes the regularizer and the iteration parameters automatically during the network training with a large amount of simulated DBT data. Numerical, experimental, and clinical data are used to evaluate its performance. Quantitative metrics such as the artifact spread function (ASF), breast density, and the signal difference to noise ratio (SDNR) are measured to assess the image quality. Results: Results show that the proposed DIR-DBTnet is able to reduce the in-plane shadow artifacts and the out-of-plane signal leaking artifacts compared to the filtered backprojection (FBP) and the total variation (TV)-based IR methods. Quantitatively, the full width half maximum (FWHM) of the measured ASF from the clinical data is 27.1% and 23.0% smaller than those obtained with the FBP and TV methods, while the SDNR is increased by 194.5% and 21.8%, respectively. In addition, the breast density obtained from the DIR-DBTnet network is more accurate and consistent with the ground truth. Conclusions: In conclusion, a deep iterative reconstruction network, DIR-DBTnet, has been proposed for 3D DBT image reconstruction. Both qualitative and quantitative analyses of the numerical, experimental, and clinical results demonstrate that the DIR-DBTnet has superior DBT imaging performance than the conventional algorithms.

show abstract

Section: Discussionmentioning

confidence: 93%

Section: The Dir-dbtnetmentioning

confidence: 99%

“…Because the DBT imaging uses the 3D cone‐beam geometry, the matrix

A

and

A^{T}

would consume a huge amount of computation resource if they are stored on RAM. To address this problem, we developed two user‐defined GPU accelerated TensorFlow operators:

F P (\cdot)

and

B P (\cdot)

25 . In particular, they are implemented in C++ and registered with the Tensorflow system.…”

Section: The Dir‐dbtnetmentioning

confidence: 99%

See 1 more Smart Citation

DIR‐DBTnet: Deep iterative reconstruction network for three‐dimensional digital breast tomosynthesis imaging

Deng

Yang

et al. 2021

Medical Physics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Deep learning is playing an increasingly important role in PT image reconstruction (32,33). Deep learning networks improve tomographic image degradation caused by insufficient contrast agent, low radiation dose, or sparseview measurements, such as few-view or limited-angle measurements .…”

Section: Introductionmentioning

confidence: 99%

Two-stage deep learning network-based few-view image reconstruction for parallel-beam projection tomography

Wang¹,

Wang²,

Xie³

et al. 2022

Quant Imaging Med Surg

View full text Add to dashboard Cite

Background: Projection tomography (PT) is a very important and valuable method for fast volumetric imaging with isotropic spatial resolution. Sparse-view or limited-angle reconstruction-based PT can greatly reduce data acquisition time, lower radiation doses, and simplify sample fixation modes. However, few techniques can currently achieve image reconstruction based on few-view projection data, which is especially important for in vivo PT in living organisms.Methods: A 2-stage deep learning network (TSDLN)-based framework was proposed for parallel-beam PT reconstructions using few-view projections. The framework is composed of a reconstruction network (R-net) and a correction network (C-net). The R-net is a generative adversarial network (GAN) used to complete image information with direct back-projection (BP) of a sparse signal, bringing the reconstructed image close to reconstruction results obtained from fully projected data. The C-net is a U-net array that denoises the compensation result to obtain a high-quality reconstructed image. Results:The accuracy and feasibility of the proposed TSDLN-based framework in few-view projectionbased reconstruction were first evaluated with simulations, using images from the DeepLesion public dataset. The framework exhibited better reconstruction performance than traditional analytic reconstruction algorithms and iterative algorithms, especially in cases using sparse-view projection images. For example, with as few as two projections, the TSDLN-based framework reconstructed high-quality images very close to the original image, with structural similarities greater than 0.8. By using previously acquired optical PT (OPT) data in the TSDLN-based framework trained on computed tomography (CT) data, we further exemplified the migration capabilities of the TSDLN-based framework. The results showed that when the number of projections was reduced to 5, the contours and distribution information of the samples in question could still be seen in the reconstructed images. Conclusions:The simulations and experimental results showed that the TSDLN-based framework has strong reconstruction abilities using few-view projection images, and has great potential in the application of in vivo PT.

show abstract

“…Applications of deep neural networks (DNNs) in medical image processing tasks have achieved impressive results, demonstrating their tremendous potential and providing new ideas for future research studies. Many specialists have used sinogram domain data, image domain data, or a combination of both to enhance the quality of LECT images (13,(17)(18)(19)(20)(21)(22). For DECT images, Ma et al (23) introduced a convolutional neural network (CNN) as a method of synthesizing pseudo-HECT images from LECT images.…”

Section: Introductionmentioning

confidence: 99%

The synthesis of high-energy CT images from low-energy CT images using an improved cycle generative adversarial network

Zhou¹,

Liu²,

Wang³

et al. 2022

Quant Imaging Med Surg

Self Cite

View full text Add to dashboard Cite

Background: The dose of radiation a patient receives when undergoing dual-energy computed tomography (CT) is of significant concern to the medical community, and balancing the tradeoffs between the level of radiation used and the quality of CT images is challenging. This paper proposes a method of synthesizing high-energy CT (HECT) images from low-energy CT (LECT) images using a neural network that achieves an alternative to HECT scanning by employing an LECT scan, which greatly reduces the radiation dose a patient receives.Methods: In the training phase, the proposed structure cyclically generates HECT and LECT images to improve the accuracy of extracting edge and texture features. Specifically, we combine multiple connection methods with channel attention (CA) and pixel attention (PA) mechanisms to improve the network's mapping ability of image features. In the prediction phase, we use a model consisting of only the network component that synthesizes HECT images from LECT images.Results: Our proposed method was conducted on clinical hip CT image data sets from Guizhou Provincial People's Hospital. In a comparison with other available methods [a generative adversarial network (GAN), a residual encoder-to-decoder network with a visual geometry group (VGG) pretrained model (RED-VGG), a Wasserstein GAN (WGAN), and CycleGAN] in terms of metrics of peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), normalized mean square error (NMSE), and a visual effect evaluation, the proposed method was found to perform better on each of these evaluation criteria. Compared with the results produced by CycleGAN, the proposed method improved the PSNR by 2.44%, the SSIM by 1.71%, and the NMSE by 15.2%. Furthermore, the differences in the statistical indicators are statistically significant, proving the strength of the proposed method. Conclusions:The proposed method synthesizes high-energy CT images from low-energy CT images, which significantly reduces both the cost of treatment and the radiation dose received by patients. Based on both image quality score metrics and visual effects comparisons, the results of the proposed method are superior to those obtained by other methods. 2 Zhou et al. Synthesis of high-energy CT images

show abstract

ADAPTIVE-NET: deep computed tomography reconstruction network with analytical domain transformation knowledge

Cited by 43 publications

References 27 publications

DIR‐DBTnet: Deep iterative reconstruction network for three‐dimensional digital breast tomosynthesis imaging

DIR‐DBTnet: Deep iterative reconstruction network for three‐dimensional digital breast tomosynthesis imaging

Two-stage deep learning network-based few-view image reconstruction for parallel-beam projection tomography

The synthesis of high-energy CT images from low-energy CT images using an improved cycle generative adversarial network

Contact Info

Product

Resources

About