Solving Energy-Independent Density for CT Metal Artifact Reduction via Neural Representation

• URL: http://arxiv.org/abs/2405.07047v2
• Date: Wed, 15 Jan 2025 12:47:35 GMT
• Title: Solving Energy-Independent Density for CT Metal Artifact Reduction via Neural Representation
• Authors: Qing Wu, Xu Guo, Lixuan Chen, Yanyan Liu, Dongming He, Xudong Wang, Xueli Chen, Yifeng Zhang, S. Kevin Zhou, Jingyi Yu, Yuyao Zhang,
• Abstract summary: Reconstructing CT images from metal-corrupted measurements becomes a challenging nonlinear inverse problem.<n>Existing state-of-the-art (SOTA) metal artifact reduction (MAR) algorithms rely on supervised learning with numerous paired CT samples.<n>In this work, we propose Density neural representation (Diner), a novel unsupervised MAR method.
• Score: 46.57879724994237
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: X-ray CT often suffers from shadowing and streaking artifacts in the presence of metallic materials, which severely degrade imaging quality. Physically, the linear attenuation coefficients (LACs) of metals vary significantly with X-ray energy, causing a nonlinear beam hardening effect (BHE) in CT measurements. Reconstructing CT images from metal-corrupted measurements consequently becomes a challenging nonlinear inverse problem. Existing state-of-the-art (SOTA) metal artifact reduction (MAR) algorithms rely on supervised learning with numerous paired CT samples. While promising, these supervised methods often assume that the unknown LACs are energy-independent, ignoring the energy-induced BHE, which results in limited generalization. Moreover, the requirement for large datasets also limits their applications in real-world scenarios. In this work, we propose Density neural representation (Diner), a novel unsupervised MAR method. Our key innovation lies in formulating MAR as an energy-independent density reconstruction problem that strictly adheres to the photon-tissue absorption physical model. This model is inherently nonlinear and complex, making it a rarely considered approach in inverse imaging problems. By introducing the water-equivalent tissues approximation and a new polychromatic model to characterize the nonlinear CT acquisition process, we directly learn the neural representation of the density map from raw measurements without using external training data. This energy-independent density reconstruction framework fundamentally resolves the nonlinear BHE, enabling superior MAR performance across a wide range of scanning scenarios. Extensive experiments on both simulated and real-world datasets demonstrate the superiority of our unsupervised Diner over popular supervised methods in terms of MAR performance and robustness.

Related papers

• Unsupervised Multi-Parameter Inverse Solving for Reducing Ring Artifacts in 3D X-Ray CBCT [35.73129314731503]
  Ring artifacts are prevalent in 3D cone-beam computed tomography (CBCT) due to non-ideal responses of X-ray detectors. Current state-of-the-art (SOTA) ring artifact reduction (RAR) algorithms rely on extensive paired CT samples for supervised learning. We introduce textbfRiner, an unsupervised method formulating 3D CBCT RAR as a multi- parameter inverse problem.
  arXiv  Detail & Related papers  (2024-12-08T08:22:58Z)
• PFCM: Poisson flow consistency models for low-dose CT image denoising [3.3153763098433258]
  We introduce PFCM, a novel family of deep generative models that combines the robustness of PFGM++ with the efficient single-step sampling of consistency models. We exploit to adapt PFCM for the task of low-dose CT image denoising, via a task-specific'' sampler that hijacks'' the generative process. The resulting sampler achieves excellent performance in terms of LPIPS, SSIM, and PSNR on the Mayo low-dose CT dataset.
  arXiv  Detail & Related papers  (2024-02-13T01:39:56Z)
• Gradient Descent Provably Solves Nonlinear Tomographic Reconstruction [60.95625458395291]
  In computed tomography (CT) the forward model consists of a linear transform followed by an exponential nonlinearity based on the attenuation of light according to the Beer-Lambert Law. We show that this approach reduces metal artifacts compared to a commercial reconstruction of a human skull with metal crowns.
  arXiv  Detail & Related papers  (2023-10-06T00:47:57Z)
• Unsupervised CT Metal Artifact Reduction by Plugging Diffusion Priors in Dual Domains [8.40564813751161]
  metallic implants often cause disruptive artifacts in computed tomography (CT) images, impeding accurate diagnosis. Several supervised deep learning-based approaches have been proposed for reducing metal artifacts (MAR) We propose an unsupervised MAR method based on the diffusion model, a generative model with a high capacity to represent data distributions.
  arXiv  Detail & Related papers  (2023-08-31T14:00:47Z)
• Unsupervised Polychromatic Neural Representation for CT Metal Artifact Reduction [48.1445005916672]
  We present a novel Polychromatic neural representation (Polyner) to tackle the challenging problem of CT imaging when metallic implants exist within the human body. Our Polyner achieves comparable or better performance than supervised methods on in-domain datasets.
  arXiv  Detail & Related papers  (2023-06-27T04:50:58Z)
• DDMM-Synth: A Denoising Diffusion Model for Cross-modal Medical Image Synthesis with Sparse-view Measurement Embedding [7.6849475214826315]
  We propose a novel framework called DDMM- Synth for medical image synthesis. It combines an MRI-guided diffusion model with a new CT measurement embedding reverse sampling scheme. It can adjust the projection number of CT a posteriori for a particular clinical application and its modified version can even improve the results significantly for noisy cases.
  arXiv  Detail & Related papers  (2023-03-28T07:13:11Z)
• Orientation-Shared Convolution Representation for CT Metal Artifact Learning [63.67718355820655]
  During X-ray computed tomography (CT) scanning, metallic implants carrying with patients often lead to adverse artifacts. Existing deep-learning-based methods have gained promising reconstruction performance. We propose an orientation-shared convolution representation strategy to adapt the physical prior structures of artifacts.
  arXiv  Detail & Related papers  (2022-12-26T13:56:12Z)
• Orthogonal Matrix Retrieval with Spatial Consensus for 3D Unknown-View Tomography [58.60249163402822]
  Unknown-view tomography (UVT) reconstructs a 3D density map from its 2D projections at unknown, random orientations. The proposed OMR is more robust and performs significantly better than the previous state-of-the-art OMR approach.
  arXiv  Detail & Related papers  (2022-07-06T21:40:59Z)
• Multi-Channel Convolutional Analysis Operator Learning for Dual-Energy CT Reconstruction [108.06731611196291]
  We develop a multi-channel convolutional analysis operator learning (MCAOL) method to exploit common spatial features within attenuation images at different energies. We propose an optimization method which jointly reconstructs the attenuation images at low and high energies with a mixed norm regularization on the sparse features.
  arXiv  Detail & Related papers  (2022-03-10T14:22:54Z)
• InDuDoNet+: A Model-Driven Interpretable Dual Domain Network for Metal Artifact Reduction in CT Images [53.4351366246531]
  We construct a novel interpretable dual domain network, termed InDuDoNet+, into which CT imaging process is finely embedded. 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.
  arXiv  Detail & Related papers  (2021-12-23T15:52:37Z)
• Regularization by Denoising Sub-sampled Newton Method for Spectral CT Multi-Material Decomposition [78.37855832568569]
  We propose to solve a model-based maximum-a-posterior problem to reconstruct multi-materials images with application to spectral CT. In particular, we propose to solve a regularized optimization problem based on a plug-in image-denoising function. We show numerical and experimental results for spectral CT materials decomposition.
  arXiv  Detail & Related papers  (2021-03-25T15:20:10Z)
• Combining multimodal information for Metal Artefact Reduction: An unsupervised deep learning framework [1.1374919153601266]
  Metal artefact reduction (MAR) techniques aim at removing metal-induced noise from clinical images. In MRI, no method has yet been introduced to correct the susceptibility artefact. We propose an unsupervised deep learning method for multimodal MAR.
  arXiv  Detail & Related papers  (2020-04-20T14:12:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.