Encoding Metal Mask Projection for Metal Artifact Reduction in Computed Tomography

Lyu, Yuanyuan; Lin, Wei-An; Liao, Haofu; Lu, Jingjing; Zhou, S. Kevin

doi:10.1007/978-3-030-59713-9_15

Cited by 49 publications

(53 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The sizes of the 10 metallic implants for test data are: [2061,890,881,451,254,124,118,112,53,35] in pixels. Consistent to (Lin et al, 2019;Lyu et al, 2020), we simply put the adjacent sizes into one group for average MAR performance evaluation. We adopt the procedures widely used by existing studies (Zhang and Yu, 2018;Liao et al, 2019b;Lin et al, 2019;Yu et al, 2020;Lyu et al, 2020) to simulate Y and X ma .…”

Section: Details Descriptionmentioning

confidence: 99%

“…Driven by the tremendous success of deep learning (DL) in medical image reconstruction and analysis (Ronneberger et al, 2015;Wang et al, 2018a), researchers began to apply the convolutional neural network (CNN) for MAR (Zhang and Yu, 2018;Lin et al, 2019;Liao et al, 2019b;Yu et al, 2020;Lyu et al, 2020). The existing DLbased MAR methods can be roughly grouped into three research lines, i.e., sinogram domain enhancement, image domain enhancement, and dual domain (joint sinogram and CT image) enhancement.…”

Section: Introductionmentioning

confidence: 99%

“…The image-domain-based approaches exploit deep CNNs to directly learn the mapping function from metal-corrupted CT images to the clean ones based on residual learning (Huang et al, 2018) or adversarial learning (Wang et al, 2018b;Liao et al, 2019b). For the research line of dual domain, recent studies (Lin et al, 2019;Yu et al, 2020;Lyu et al, 2020) accomplish the mutual learning between sinogram and CT image by integrating the differentiate FP layer and filtered back-projection (FBP) layer into deep network frameworks, which further improves the MAR performance.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

InDuDoNet+: A Model-Driven Interpretable Dual Domain Network for Metal Artifact Reduction in CT Images

Wang¹,

Li²,

Zhang³

et al. 2021

Preprint

View full text Add to dashboard Cite

During the computed tomography (CT) imaging process, metallic implants within patients always cause harmful artifacts, which adversely degrade the visual quality of reconstructed CT images and negatively affect the subsequent clinical diagnosis. For the metal artifact reduction (MAR) task, current deep learning based methods have achieved promising performance. However, most of them share two main common limitations: 1) the CT physical imaging geometry constraint is not comprehensively incorporated into deep network structures; 2) the entire framework has weak interpretability for the specific MAR task; hence, the role of every network module is difficult to be evaluated. To alleviate these issues, in the paper, we construct a novel interpretable dual domain network, termed InDuDoNet+, into which CT imaging process is finely embedded. Concretely, we derive a joint spatial and Radon domain reconstruction model and propose an optimization algorithm with only simple operators for solving it. By unfolding the iterative steps involved in the proposed algorithm into the corresponding network modules, we easily build the InDuDoNet+ with clear interpretability. Furthermore, we analyze the CT values among different tissues, and merge the prior observations into a prior network for our InDuDoNet+, which significantly improve its generalization performance. Comprehensive experiments on synthesized data and clinical data substantiate the superiority of the proposed methods as well as the superior generalization performance beyond the current state-of-the-art (SOTA) MAR methods. Code is available at https://github.com/hongwang01/InDuDoNet_plus.

show abstract

Section: Details Descriptionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

InDuDoNet+: A Model-Driven Interpretable Dual Domain Network for Metal Artifact Reduction in CT Images

Wang¹,

Li²,

Zhang³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…While artifacts caused by metallic implants increase the possibility of false diagnosis and analysis. Recently, supervised learning with synthesized paired images are applied to solve MAR problem and achieve great success [1][2][3][4][5][6][7]. However, performance degrading appears in practice.…”

Section: Introductionmentioning

confidence: 99%

“…Two spaces express same contents while in different manners. This image prior provides an inspiration for unsupervised learning, which has been implemented by supervised methods [6,7,15,16]. However, it has not been implemented by unsupervised learning till now.…”

Section: Introductionmentioning

confidence: 99%

Attention-Embedded Decomposed Network with Unpaired CT Images Prior for Metal Artifact Reduction

Zhao

Ren

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Recently, unsupervised learning is proposed to avoid the performance degrading caused by synthesized paired computed tomography (CT) images. However, existing unsupervised methods for metal artifact reduction (MAR) only use features in image space, which is not enough to restore regions heavily corrupted by metal artifacts. Besides, they lack the distinction and selection for effective features. To address these issues, we propose an attention-embedded decomposed network to reducing metal artifacts in both image space and sinogram space with unpaired images. Specifically, combining with the CT images prior, we decompose the artifact-affected images to artifact images and content images. Besides, normal convolutions are embedded with attention design in pixel-wise and channel-wise to strengthen the representational capacity. Extensive experiments show notable improvements on both synthesized data and clinical data.

show abstract

DL‐based inpainting for metal artifact reduction for cone beam CT using metal path length information

et al. 2022

View full text Add to dashboard Cite

Background Metallic implants, which are inserted into the patient's body during trauma interventions, are the main cause of heavy artifacts in 3D X‐ray acquisitions. These artifacts then hinder the evaluation of the correct implant's positioning, thus leading to a disturbed patient's healing process and increased revision rates. Purpose This problem is tackled by so‐called metal artifact reduction (MAR) methods. This paper examines possible advances in the inpainting process of such MAR methods to decrease disruptive artifacts while simultaneously preserving important anatomical structures adjacent to the inserted implants. Methods In this paper, a learning‐based inpainting method for cone‐beam computed tomography is proposed that couples a convolutional neural network (CNN) with an estimated metal path length as prior knowledge. Further, the proposed method is solely trained and evaluated on real measured data. Results The proposed inpainting approach shows advantages over the inpainting method used by the currently clinically approved frequency split metal artifact reduction (fsMAR) method as well as the learning‐based state‐of‐the‐art (SOTA) method PConv‐Net. The major improvement of the proposed inpainting method lies in the ability to correctly preserve important anatomical structures in those regions adjacent to the metal implants. Especially these regions are highly important for a correct implant's positioning in an intraoperative setup. Using the proposed inpainting, the corresponding MAR volumes reach a mean structural similarity index measure (SSIM) score of 0.9974 and outperform the other methods by up to 6 dB on single slices regarding the peak signal‐to‐noise ratio (PSNR) score. Furthermore, it can be shown that the proposed method can generalize to clinical cases at hand. Conclusions In this paper, a learning‐based inpainting network is proposed that leverages prior knowledge about the metal path length of the inserted implant. Evaluations on real measured data reveal an increased overall MAR performance, especially regarding the preservation of anatomical structures adjacent to the inserted implants. Further evaluations suggest the ability of the proposed approach to generalize to clinical cases.

show abstract

Encoding Metal Mask Projection for Metal Artifact Reduction in Computed Tomography

Cited by 49 publications

References 15 publications

InDuDoNet+: A Model-Driven Interpretable Dual Domain Network for Metal Artifact Reduction in CT Images

InDuDoNet+: A Model-Driven Interpretable Dual Domain Network for Metal Artifact Reduction in CT Images

Attention-Embedded Decomposed Network with Unpaired CT Images Prior for Metal Artifact Reduction

DL‐based inpainting for metal artifact reduction for cone beam CT using metal path length information

Contact Info

Product

Resources

About