PatchNR: learning from very few images by patch normalizing flow regularization

Altekrüger, Fabian; Denker, Alexander; Hagemann, Paul; Hertrich, Johannes; Maaß, Peter; Steidl, Gabriele

doi:10.1088/1361-6420/acce5e

Cited by 9 publications

(1 citation statement)

References 79 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another class of methods learns priors in only normal-dose CT images by generative models and incorporates them into low-dose CT reconstruction. Fabian et al proposed PatchNR (Altekrüger et al 2023) to learn a regularization term from the patches of a few normal-dose images with normalizing flows (Kobyzev et al 2020) and used it in iterative low-dose reconstruction. He et al utilized a score-based model (Song and Ermon 2020) to learn priors in normal-dose images and conducted iterative reconstruction, thus proposing EASEL (He et al 2022).…”

Section: Introductionmentioning

confidence: 99%

Self-supervised dual-domain balanced dropblock-network for low-dose CT denoising

An,

Chen,

2024

Phys. Med. Biol.

View full text Add to dashboard Cite

Objective. Self-supervised learning methods have been successfully applied for low-dose Computed Tomography (LDCT) denoising, with the advantage of not requiring labeled data. Conventional self-supervised methods operate only in the image domain, ignoring valuable priors in the sinogram domain. Recently proposed dual-domain methods address this limitation but encounter issues with blurring artifacts in the reconstructed image due to the inhomogeneous distribution of noise levels in low-dose sinograms. Approach. To tackle this challenge, this paper proposes SDBDNet, an end-to-end dual-domain self-supervised method for LDCT denoising. With the network designed based on the properties of inhomogeneous noise in low-dose sinograms and the principle of moderate sinogram-domain denoising, SDBDNet achieves effective denoising in dual domains without introducing blurring artifacts. Specifically, we split the sinogram into two subsets based on the positions of detector cells to generate paired training data with high similarity and independent noise. These sub-sinograms are then restored to their original size using 1-D interpolation and learning-based correction. To achieve adaptive and moderate smoothing in the sinogram domain, we integrate Dropblock, a type of convolution layer with regularization, into SDBDNet, and set a weighted average between the denoised sinograms and their noisy counterparts, leading to a well-balanced dual-domain approach. Main results. Numerical experiments show that our method outperforms popular non-learning and self-supervised learning methods, demonstrating its effectiveness and superior performance. Significance. While introducing a novel high-performance dual-domain self-supervised LDCT denoising method, this paper also emphasizes and verifies the importance of appropriate sinogram-domain denoising in dual-domain methods, which might inspire future work.

show abstract

Section: Introductionmentioning

confidence: 99%

Self-supervised dual-domain balanced dropblock-network for low-dose CT denoising

An,

Chen,

2024

Phys. Med. Biol.

View full text Add to dashboard Cite

show abstract

Learning from small data sets: Patch‐based regularizers in inverse problems for image reconstruction

Piening,

Altekrüger,

Hertrich

et al. 2024

GAMM-Mitteilungen

View full text Add to dashboard Cite

The solution of inverse problems is of fundamental interest in medical and astronomical imaging, geophysics as well as engineering and life sciences. Recent advances were made by using methods from machine learning, in particular deep neural networks. Most of these methods require a huge amount of data and computer capacity to train the networks, which often may not be available. Our paper addresses the issue of learning from small data sets by taking patches of very few images into account. We focus on the combination of model‐based and data‐driven methods by approximating just the image prior, also known as regularizer in the variational model. We review two methodically different approaches, namely optimizing the maximum log‐likelihood of the patch distribution, and penalizing Wasserstein‐like discrepancies of whole empirical patch distributions. From the point of view of Bayesian inverse problems, we show how we can achieve uncertainty quantification by approximating the posterior using Langevin Monte Carlo methods. We demonstrate the power of the methods in computed tomography, image super‐resolution, and inpainting. Indeed, the approach provides also high‐quality results in zero‐shot super‐resolution, where only a low‐resolution image is available. The article is accompanied by a GitHub repository containing implementations of all methods as well as data examples so that the reader can get their own insight into the performance.

show abstract

Robustness and exploration of variational and machine learning approaches to inverse problems: An overview

Auras,

Gandikota,

Droege

et al. 2024

GAMM-Mitteilungen

View full text Add to dashboard Cite

This paper provides an overview of current approaches for solving inverse problems in imaging using variational methods and machine learning. A special focus lies on point estimators and their robustness against adversarial perturbations. In this context results of numerical experiments for a one‐dimensional toy problem are provided, showing the robustness of different approaches and empirically verifying theoretical guarantees. Another focus of this review is the exploration of the subspace of data‐consistent solutions through explicit guidance to satisfy specific semantic or textural properties.

show abstract

PatchNR: learning from very few images by patch normalizing flow regularization

Cited by 9 publications

References 79 publications

Self-supervised dual-domain balanced dropblock-network for low-dose CT denoising

Self-supervised dual-domain balanced dropblock-network for low-dose CT denoising

Learning from small data sets: Patch‐based regularizers in inverse problems for image reconstruction

Robustness and exploration of variational and machine learning approaches to inverse problems: An overview

Contact Info

Product

Resources

About