DuDoNet: Dual Domain Network for CT Metal Artifact Reduction

Lin, Wei-An; Liao, Haofu; Cheng, Perry; Sun, Xiaohang; Zhang, Jingdan; Luo, Jiebo; Chellappa, Rama; Zhou, S. Kevin

doi:10.1109/cvpr.2019.01076

Cited by 167 publications

(163 citation statements)

References 32 publications

Supporting

Mentioning

158

Contrasting

Order By: Relevance

“…Thirdly, CT metal artifact reduction (MAR) under limited-view acquisition is an important research direction. Current MAR techniques are mostly limited to fullview acquisition [41], [42]. The current state-of-the-art metal artifact reduction algorithm, such as DuDoNet [41], utilizes projection space and image space simultaneously which is similar to our CasRedSCAN design.…”

Section: Discussionmentioning

confidence: 99%

“…Current MAR techniques are mostly limited to fullview acquisition [41], [42]. The current state-of-the-art metal artifact reduction algorithm, such as DuDoNet [41], utilizes projection space and image space simultaneously which is similar to our CasRedSCAN design. Our CasRedSCAN could potentially integrated with current MAR network for MAR under limited view conditions.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

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

Zhou

Duncan

et al. 2021

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

Limited view tomographic reconstruction aims to reconstruct a tomographic image from a limited number of projection views arising from sparse view or limited angle acquisitions that reduce radiation dose or shorten scanning time. However, such a reconstruction suffers from severe artifacts due to the incompleteness of sinogram. To derive quality reconstruction, previous methods use UNet-like neural architectures to directly predict the full view reconstruction from limited view data; but these methods leave the deep network architecture issue largely intact and cannot guarantee the consistency between the sinogram of the reconstructed image and the acquired sinogram, leading to a non-ideal reconstruction. In this work, we propose a cascaded residual dense spatial-channel attention network consisting of residual dense spatial-channel attention networks and projection data fidelity layers. We evaluate our methods on two datasets. Our experimental results on AAPM Low Dose CT Grand Challenge datasets demonstrate that our algorithm achieves a consistent and substantial improvement over the existing neural network methods on both limited angle reconstruction and sparse view reconstruction. In addition, our experimental results on Deep Lesion datasets demonstrate that our method is able to generate high-quality reconstruction for 8 major lesion types.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

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

Zhou

Duncan

et al. 2021

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

show abstract

“…These images are implanted with metals and are projected onto CT sinograms using the FP algorithm; the attenuation coefficient of the implanted metals is set to 7.874 according to the National Institute of Standard and Technology (NIST) standard. Metal‐corrupted CT sinograms are synthesized using the dynamic wavelet thresholding method for x‐ray CT metal artifact reduction by Peng et al 19 and the dual domain network method for CT metal artifact reduction by Lin et al 31 In addition, to test the clinical efficacy of the proposed method, we evaluate it on a real clinical data (a CT image that contains real metal artifacts), which is shared by the authors of another MAR study 9 . The size of the clinical CT image is 512 × 512.…”

Section: Methodsmentioning

confidence: 99%

“…The current DL‐based MAR methods mainly seek to patch metal trace in corrupted sinograms, and then use filtered back‐projection (FBP) 24,25 to reconstruct the patched sinograms to CT images. For example, Ghani et al 26 used a ten‐layer fully convolutional network (FCN) 27 to patch metal trace; Park et al 28 used a U‐Net 29 like network to reduce metal artifacts; Zhang et al 30 proposed a multistep convolutional neural network (MSCNN) for MAR, and used an FCN to patch metal trace followed by a postprocessing step to suppress secondary artifacts; Lin et al 31 applied a U‐Net–like network to patch metal trace and employed the network for metal trace inpainting to reduce secondary artifacts. These DL‐based metal trace inpainting methods aimed to reduce more artifacts and incur less secondary artifacts than traditional sinogram restoration methods due to their better detail recovering capability.…”

Section: Introductionmentioning

confidence: 99%

An irregular metal trace inpainting network for x‐ray CT metal artifact reduction

Peng

et al. 2020

Medical Physics

View full text Add to dashboard Cite

Purpose: Metal implants in the patient's body can generate severe metal artifacts in x-ray computed tomography (CT) images. These artifacts may cover the tissues around the metal implants in CT images and even corrupt the tissue regions, thus affecting disease diagnosis using these images. Previous deep learning metal trace inpainting methods used both valid pixels of uncorrupted areas and invalid pixels of corrupted areas to patch metal trace (i.e., the holes of removed metal-corrupted regions). Such methods cannot recover fine details well and often suffer information mismatch due to interference of invalid pixels, thus incurring considerable secondary artifacts. In this paper, we develop a new irregular metal trace inpainting network for reducing metal artifacts. Methods: We develop a new deep learning network to patch irregular metal trace in metal-corrupted sinograms to reduce metal artifacts for isometric fan-beam CT. Our new method patches irregular metal trace in CT sinograms using only valid pixels, avoiding interference from invalid pixels. Furthermore, to enable the inpainting network to recover as many details as possible, we design an auxiliary inpainting network to suppress the probable secondary artifacts in CT images to assist fine detail restoration. The image produced by the auxiliary network is then projected onto a sinogram via a forward projection (FP) algorithm and is fused with the sinogram predicted by the inpainting network in order to predict the final recovered sinogram. Our entire network is trained end-to-end to extract cross-domain information between the sinogram domain and CT image domain. Results: We compare our proposed method with two traditional and four deep learning-based metal trace inpainting methods, and with an iterative reconstruction method on four datasets: dental fillings (panoramic and local perspectives), hip prostheses, and spine fixations. We use both quantitative and qualitative indices to evaluate our method, and the analyses suggest that our method reduces the most metal artifacts and produces the best quality CT images. Additionally, our proposed method takes 0.1512 s on average to process a CT slice, which meets the clinical requirement. Conclusions: This paper proposes a new deep learning network to patch irregular metal trace in corrupted sinograms to reduce metal artifacts. Our method restores more fine details in irregular metal trace and has a superior capability on metal artifact reduction compared with state-of-the-art methods.

show abstract

“…[24] introduces a 3D inpainting task to improve the performance of ultrasound image segmentation. [23,25] convert the metal artifact reduction problem to the X-ray image inpainting problem and the metal artifacts are removed by reconstructing from the inpainted X-ray images.…”

Section: Semantic Inpaintingmentioning

confidence: 99%

Face Completion with Semantic Knowledge and Collaborative Adversarial Learning

Liao

Funka-Lea

Zheng

et al. 2019

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Unlike a conventional background inpainting approach that infers a missing area from image patches similar to the background, face completion requires semantic knowledge about the target object for realistic outputs. Current image inpainting approaches utilize generative adversarial networks (GANs) to achieve such semantic understanding. However, in adversarial learning, the semantic knowledge is learned implicitly and hence good semantic understanding is not always guaranteed. In this work, we propose a collaborative adversarial learning approach to face completion to explicitly induce the training process. Our method is formulated under a novel generative framework called collaborative GAN (collaGAN), which allows better semantic understanding of a target object through collaborative learning of multiple tasks including face completion, landmark detection and semantic segmentation. Together with the collaGAN, we also introduce an inpainting concentrated scheme such that the model emphasizes more on inpainting instead of autoencoding. Extensive experiments show that the proposed designs are indeed effective and collaborative adversarial learning provides better feature representations of the faces. In comparison with other generative image inpainting models and single task learning methods, our solution produces superior performances on all tasks.

show abstract

DuDoNet: Dual Domain Network for CT Metal Artifact Reduction

Cited by 167 publications

References 32 publications

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

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

An irregular metal trace inpainting network for x‐ray CT metal artifact reduction

Face Completion with Semantic Knowledge and Collaborative Adversarial Learning

Contact Info

Product

Resources

About