Gradient Descent Provably Solves Nonlinear Tomographic Reconstruction
- URL: http://arxiv.org/abs/2310.03956v1
- Date: Fri, 6 Oct 2023 00:47:57 GMT
- Title: Gradient Descent Provably Solves Nonlinear Tomographic Reconstruction
- Authors: Sara Fridovich-Keil, Fabrizio Valdivia, Gordon Wetzstein, Benjamin
Recht, Mahdi Soltanolkotabi
- Abstract summary: 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.
- Score: 60.95625458395291
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: In computed tomography (CT), the forward model consists of a linear Radon
transform followed by an exponential nonlinearity based on the attenuation of
light according to the Beer-Lambert Law. Conventional reconstruction often
involves inverting this nonlinearity as a preprocessing step and then solving a
convex inverse problem. However, this nonlinear measurement preprocessing
required to use the Radon transform is poorly conditioned in the vicinity of
high-density materials, such as metal. This preprocessing makes CT
reconstruction methods numerically sensitive and susceptible to artifacts near
high-density regions. In this paper, we study a technique where the signal is
directly reconstructed from raw measurements through the nonlinear forward
model. Though this optimization is nonconvex, we show that gradient descent
provably converges to the global optimum at a geometric rate, perfectly
reconstructing the underlying signal with a near minimal number of random
measurements. We also prove similar results in the under-determined setting
where the number of measurements is significantly smaller than the dimension of
the signal. This is achieved by enforcing prior structural information about
the signal through constraints on the optimization variables. We illustrate the
benefits of direct nonlinear CT reconstruction with cone-beam CT experiments on
synthetic and real 3D volumes. We show that this approach reduces metal
artifacts compared to a commercial reconstruction of a human skull with metal
dental crowns.
Related papers
- Optimized Linear Measurements for Inverse Problems using Diffusion-Based Image Generation [10.297832938258841]
We re-examine the problem of reconstructing a high-dimensional signal from a small set of linear measurements.
We show that optimizing the measurements for the SSIM perceptual loss leads to perceptually improved reconstruction.
arXiv Detail & Related papers (2024-05-22T20:38:58Z) - Unsupervised Density Neural Representation for CT Metal Artifact Reduction [45.28053148579478]
We propose a novel unsupervised density neural representation (Diner) to tackle the challenging problem of CT metal artifacts when scanned objects contain metals.
Existing metal artifact reduction (MAR) techniques mostly formulate the MAR as an image inpainting task, which ignores the energy-induced BHE.
We decompose the energy-dependent LACs into energy-independent densities and energy-dependent mass attenuation coefficients (MACs) by fully considering the physical model of X-ray absorption.
arXiv Detail & Related papers (2024-05-11T16:30:39Z) - CT Reconstruction using Diffusion Posterior Sampling conditioned on a Nonlinear Measurement Model [17.26789842018146]
Diffusion posterior sampling has been used to produce high quality CT images given low-quality measurements.
Current methods rely on a linear model of x-ray CT physics to reconstruct or restore images.
We propose a new method that solves the inverse problem of nonlinear CT image reconstruction via diffusion posterior sampling.
arXiv Detail & Related papers (2023-12-03T17:20:11Z) - 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) - Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse
Problems [64.29491112653905]
We propose a novel and efficient diffusion sampling strategy that synergistically combines the diffusion sampling and Krylov subspace methods.
Specifically, we prove that if tangent space at a denoised sample by Tweedie's formula forms a Krylov subspace, then the CG with the denoised data ensures the data consistency update to remain in the tangent space.
Our proposed method achieves more than 80 times faster inference time than the previous state-of-the-art method.
arXiv Detail & Related papers (2023-03-10T07:42:49Z) - Dimensionality-Varying Diffusion Process [52.52681373641533]
Diffusion models learn to reverse a signal destruction process to generate new data.
We make a theoretical generalization of the forward diffusion process via signal decomposition.
We show that our strategy facilitates high-resolution image synthesis and improves FID of diffusion model trained on FFHQ at $1024times1024$ resolution from 52.40 to 10.46.
arXiv Detail & Related papers (2022-11-29T09:05:55Z) - 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) - Nonlinear Transform Induced Tensor Nuclear Norm for Tensor Completion [12.788874164701785]
We propose a low-rank tensor completion (LRTC) model along the theoretical convergence of the NTTNN and the PAM algorithm.
Our method outperforms linear transform-based state-of-the-art nuclear norm (TNN) methods qualitatively and quantitatively.
arXiv Detail & Related papers (2021-10-17T09:25:37Z) - Fast signal recovery from quadratic measurements [0.0]
We present a novel approach for recovering a sparse signal from cross-correlated data.
The main idea of our proposed approach is to reduce the dimensionality of the problem by recovering only the diagonal of the unknown matrix.
Our theory shows that the proposed approach provides exact support recovery when the data is not too noisy, and that there are no false positives for any level of noise.
arXiv Detail & Related papers (2020-10-11T23:36:51Z) - Analytic Signal Phase in $N-D$ by Linear Symmetry Tensor--fingerprint
modeling [69.35569554213679]
We show that the Analytic Signal phase, and its gradient have a hitherto unstudied discontinuity in $2-D $ and higher dimensions.
This shortcoming can result in severe artifacts whereas the problem does not exist in $1-D $ signals.
We suggest the use of Linear Symmetry phase, relying on more than one set of Gabor filters, but with a negligible computational add-on.
arXiv Detail & Related papers (2020-05-16T21:17:26Z)
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.