X-ray cone-beam computed tomography geometric artefact reduction based on a data-driven strategy

Xiao, Kai; Han, Yu; Xu, Yifu; Li, Lei; Xi, Xiaoqi; Bu, Haibing; Yan, Bin

doi:10.1364/ao.58.004771

Cited by 10 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we demonstrate the artifact removal performance of DRAR by presenting quantitative and visual results. We present the comparison of DRAR with other deep learning-based methods including ERAR and EDAR, as mentioned in this paper, as well as MFCNN [ 24 ], UNet [ 22 ], and DnCNN [ 36 ] (a method for image denoising) from previous work. It is worth noting that while DnCNN is specifically designed for image denoising, the artifacts in ICT images can also be considered as noises, and so we also compare DnCNN with DRAR.…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…Thanks to the powerful learning and feature representation capability of convolutional neural networks (CNNs), the learning-based AR methods [ 22 , 23 , 24 , 25 , 26 ] have achieved far better performance than previous methods. Kida et al [ 22 ] designed a deep convolutional neural network (DCNN) based on UNet for the correction of scattering artifacts and truncation artifacts to improve CBCT image quality.…”

Section: Introductionmentioning

confidence: 99%

“…Harms et al [ 23 ] proposed a residual block concept into a cycle-consistent adversarial network (cycle-GAN) framework (res-cycle GAN) for the correction of scattering pseudopacities. Xiao et al [ 24 ] proposed a geometric artifact correction method based on a fully convolutional neural network. Zhu et al [ 25 ] also proposed a GAN framework, using the U-Net structure as the generator to extract the CT image features with geometric artifacts.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Dilated Residual Network for Turbine Blade ICT Image Artifact Removal

Han

Zeng

et al. 2023

Sensors

View full text Add to dashboard Cite

Artifacts are divergent strip artifacts or dark stripe artifacts in Industrial Computed Tomography (ICT) images due to large differences in density among the components of scanned objects, which can significantly distort the actual structure of scanned objects in ICT images. The presence of artifacts can seriously affect the practical application effectiveness of ICT in defect detection and dimensional measurement. In this paper, a series of convolution neural network models are designed and implemented based on preparing the ICT image artifact removal datasets. Our findings indicate that the RF (receptive field) and the spatial resolution of network can significantly impact the effectiveness of artifact removal. Therefore, we propose a dilated residual network for turbine blade ICT image artifact removal (DRAR), which enhances the RF of the network while maintaining spatial resolution with only a slight increase in computational load. Extensive experiments demonstrate that the DRAR achieves exceptional performance in artifact removal.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Dilated Residual Network for Turbine Blade ICT Image Artifact Removal

Han

Zeng

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Kustner et al [13] and Latif et al [14] propose a conditional generative adversarial network (cGAN) to synthesize motion free MRI reconstructions from a motion degenerated one. The same approach was presented for X-ray imaging by Xiao et al [15].…”

Section: A Non-rigid Motion Compensationmentioning

confidence: 88%

Appearance Learning for Image-Based Motion Estimation in Tomography

Preuhs

Manhart

Roser

et al. 2020

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

In tomographic imaging, anatomical structures are reconstructed by applying a pseudo-inverse forward model to acquired signals. Geometric information within this process is usually depending on the system setting only, i. e., the scanner position or readout direction. Patient motion therefore corrupts the geometry alignment in the reconstruction process resulting in motion artifacts. We propose an appearance learning approach recognizing the structures of rigid motion independently from the scanned object. To this end, we train a siamese triplet network to predict the reprojection error (RPE) for the complete acquisition as well as an approximate distribution of the RPE along the single views from the reconstructed volume in a multi-task learning approach. The RPE measures the motioninduced geometric deviations independent of the object based on virtual marker positions, which are available during training. We train our network using 27 patients and deploy a 21-4-2 split for training, validation and testing. In average, we achieve a residual mean RPE of 0.013 mm with an inter-patient standard deviation of 0.022 mm. This is twice the accuracy compared to previously published results. In a motion estimation benchmark the proposed approach achieves superior results in comparison with two state-of-the-art measures in nine out of twelve experiments. The clinical applicability of the proposed method is demonstrated on a motion-affected clinical dataset.

show abstract

“…34 In other approaches, deep learning has also been used to reduce cone-angle artifact in circular cone-beam CT 35 and to generate an image-based geometry correction. 36…”

Section: Iterative Reconstruction and Deep-learningmentioning

confidence: 99%

Flat-panel conebeam CT in the clinic: history and current state

et al. 2021

View full text Add to dashboard Cite

. Research into conebeam CT concepts began as soon as the first clinical single-slice CT scanner was conceived. Early implementations of conebeam CT in the 1980s focused on high-contrast applications where concurrent high resolution ( ), for visualization of small contrast-filled vessels, bones, or teeth, was an imaging requirement that could not be met by the contemporaneous CT scanners. However, the use of nonlinear imagers, e.g., x-ray image intensifiers, limited the clinical utility of the earliest diagnostic conebeam CT systems. The development of consumer-electronics large-area displays provided a technical foundation that was leveraged in the 1990s to first produce large-area digital x-ray detectors for use in radiography and then compact flat panels suitable for high-resolution and high-frame-rate conebeam CT. In this review, we show the concurrent evolution of digital flat panel (DFP) technology and clinical conebeam CT. We give a brief summary of conebeam CT reconstruction, followed by a brief review of the correction approaches for DFP-specific artifacts. The historical development and current status of flat-panel conebeam CT in four clinical areas—breast, fixed C-arm, image-guided radiation therapy, and extremity/head—is presented. Advances in DFP technology over the past two decades have led to improved visualization of high-contrast, high-resolution clinical tasks, and image quality now approaches the soft-tissue contrast resolution that is the standard in clinical CT. Future technical developments in DFPs will enable an even broader range of clinical applications; research in the arena of flat-panel CT shows no signs of slowing down.

show abstract

X-ray cone-beam computed tomography geometric artefact reduction based on a data-driven strategy

Cited by 10 publications

References 24 publications

A Dilated Residual Network for Turbine Blade ICT Image Artifact Removal

A Dilated Residual Network for Turbine Blade ICT Image Artifact Removal

Appearance Learning for Image-Based Motion Estimation in Tomography

Flat-panel conebeam CT in the clinic: history and current state

Contact Info

Product

Resources

About