Physics-Driven Independent Pair Generation for Iterative Self-Supervised Low-Dose CT Denoising

• URL: http://arxiv.org/abs/2609.02654v1
• Date: Tue, 01 Sep 2026 12:18:28 GMT
• Title: Physics-Driven Independent Pair Generation for Iterative Self-Supervised Low-Dose CT Denoising
• Abstract summary: Low-dose computed tomography (LDCT) measurements contain mixed Poisson-Gaussian noise.<n>Most self-supervised methods rely on generic image statistics and do not explicitly model this noise.<n>We propose a physics-driven framework with cross-domain iteration for self-supervised LDCT denoising.
• Score: 16.003879627285514
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Low-dose computed tomography (LDCT) measurements contain mixed Poisson-Gaussian noise. However, most self-supervised methods rely on generic image statistics and do not explicitly model this noise, which may limit their ability to effectively suppress realistic LDCT noise. To address this issue, we propose a physics-driven framework with cross-domain iteration for self-supervised LDCT denoising. The proposed framework proceeds in three main steps. First, a learned sinogram prior and the LDCT noise model guide posterior inference of photon counts, enabling separation of the Poisson and Gaussian components. Second, the separated Poisson and Gaussian components are respectively processed by binomial thinning and Gaussian data thinning to construct two branches, and residual scaling matches each branch's noise level to that of the observation, yielding a training pair with approximately independent noise realizations from one low-dose measurement. Finally, the pair is used to train an image-domain network whose forward-projected outputs update the prior. Through cross-domain iteration, the prior and the training pair are progressively refined while maintaining consistency with CT acquisition physics. Experiments on simulated data from AAPM, LIDC-IDRI, and LoDoPaB-CT and on real LDCT data show consistent gains over the evaluated self-supervised baselines across dose levels, with performance comparable to the evaluated supervised baseline.

Related papers

• Deep Slice Interpolation for Reducing Through-Plane Anisotropy and Noise in Head CT [0.0]
  We present a deep learning system that synthesizes intermediate CT slices from pairs of neighboring axial slices.<n>The system improves three-dimensional visualization while simultaneously producing inherently denoised outputs.
  arXiv  Detail & Related papers  (2026-06-08T10:45:51Z)
• Image Denoising Using Global and Local Circulant Representation [6.207058215096057]
  Haar-tSVD is a one-step, parallelizable plug-and-play denoiser.<n>It exploits a unified tensor singular value decomposition (t-SVD) projection combined with Haar transform to efficiently capture global and local patch correlations.<n>An adaptive noise estimation scheme is introduced to improve robustness according to eigenvalue analysis of the circulant structure.
  arXiv  Detail & Related papers  (2025-12-29T16:09:00Z)
• InJecteD: Analyzing Trajectories and Drift Dynamics in Denoising Diffusion Probabilistic Models for 2D Point Cloud Generation [48.55037712252843]
  InJecteD is a framework for interpreting Denoising Diffusion Probabilistic Models (DDPMs)<n>We apply this framework to three datasets from the Datasaurus Dozen bullseye, dino, and circle.<n>Our approach quantifies trajectory properties, including displacement, velocity, clustering, and drift field dynamics.
  arXiv  Detail & Related papers  (2025-09-09T14:53:19Z)
• Efficient Image Denoising Using Global and Local Circulant Representation [4.673484951060369]
  Haar-tSVD is a simple algorithm to explore the nonlocal self-similarity prior to the Haar transform.<n>We show that global and local patch correlations can be effectively captured through a unified tensor-singular value decomposition.<n>Experiments on different real-world denoising tasks validate the efficiency and effectiveness of Haar-tSVD.
  arXiv  Detail & Related papers  (2025-08-14T03:25:59Z)
• Noise Conditional Variational Score Distillation [60.38982038894823]
  Noise Conditional Variational Score Distillation (NCVSD) is a novel method for distilling pretrained diffusion models into generative denoisers.<n>By integrating this insight into the Variational Score Distillation framework, we enable scalable learning of generative denoisers.
  arXiv  Detail & Related papers  (2025-06-11T06:01:39Z)
• Zero-Shot Low-dose CT Denoising via Sinogram Flicking [5.101848799297469]
  We propose a zero-shot low-dose CT imaging method based on sinogram flicking.<n>By randomly swapping portions of the conjugate X-rays in the sinogram domain, we generate a large set of sinograms with consistent content but differing noise patterns.<n>We train the network on pairs of sinograms with the same content but different noise distributions using a lightweight model adapted from ZS-NSN.
  arXiv  Detail & Related papers  (2025-04-10T17:42:01Z)
• Optimizing Multi-Scale Representations to Detect Effect Heterogeneity Using Earth Observation and Computer Vision: Applications to Two Anti-Poverty RCTs [3.4137115855910762]
  Multi-Scale Representation Concatenation transforms arbitrary single-scale EO-based CATE estimation algorithms into multi-scale ones.<n>We benchmark the performance of Multi-Scale Representation Concatenation on a CATE estimation pipeline.<n>Results indicate that Multi-Scale Representation Concatenation improves the performance of deep learning models in EO-based CATE estimation.
  arXiv  Detail & Related papers  (2024-11-04T14:47:48Z)
• WIA-LD2ND: Wavelet-based Image Alignment for Self-supervised Low-Dose CT Denoising [74.14134385961775]
  We introduce a novel self-supervised CT image denoising method called WIA-LD2ND, only using NDCT data. WIA-LD2ND comprises two modules: Wavelet-based Image Alignment (WIA) and Frequency-Aware Multi-scale Loss (FAM)
  arXiv  Detail & Related papers  (2024-03-18T11:20:11Z)
• Treatment Learning Causal Transformer for Noisy Image Classification [62.639851972495094]
  In this work, we incorporate this binary information of "existence of noise" as treatment into image classification tasks to improve prediction accuracy. Motivated from causal variational inference, we propose a transformer-based architecture, that uses a latent generative model to estimate robust feature representations for noise image classification. We also create new noisy image datasets incorporating a wide range of noise factors for performance benchmarking.
  arXiv  Detail & Related papers  (2022-03-29T13:07:53Z)
• Residual-driven Fuzzy C-Means Clustering for Image Segmentation [152.609322951917]
  We elaborate on residual-driven Fuzzy C-Means (FCM) for image segmentation. Built on this framework, we present a weighted $ell_2$-norm fidelity term by weighting mixed noise distribution. The results demonstrate the superior effectiveness and efficiency of the proposed algorithm over existing FCM-related algorithms.
  arXiv  Detail & Related papers  (2020-04-15T15:46:09Z)
• Generative Modeling with Denoising Auto-Encoders and Langevin Sampling [88.83704353627554]
  We show that both DAE and DSM provide estimates of the score of the smoothed population density. We then apply our results to the homotopy method of arXiv:1907.05600 and provide theoretical justification for its empirical success.
  arXiv  Detail & Related papers  (2020-01-31T23:50:03Z)
• Noise2Inverse: Self-supervised deep convolutional denoising for tomography [0.0]
  Noise2Inverse is a deep CNN-based denoising method for linear image reconstruction algorithms. We develop a theoretical framework which shows that such training indeed obtains a denoising CNN. On simulated CT datasets, Noise2Inverse demonstrates an improvement in peak signal-to-noise ratio and structural similarity index.
  arXiv  Detail & Related papers  (2020-01-31T12:50:24Z)

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.