SCOUT: Fast Spectral CT Imaging in Ultra LOw-data Regimes via PseUdo-label GeneraTion
Not on the map. Why?
Abstract (arXiv)
Noise and artifacts during computed tomography (CT) scans are a fundamental challenge affecting disease diagnosis. However, current methods either involve excessively long reconstruction times or rely on data-driven models for optimization, failing to adequately consider the valuable information inherent in the data itself, especially medical 3D data. This work proposes a reconstruction method under ultra-low raw data conditions, requiring no external data and avoiding lengthy pre-training processes. By leveraging spatial nonlocal similarity and the conjugate properties of the projection domain to generate pseudo-3D data for self-supervised training, high-fidelity results can be achieved in a very short time. Extensive experiments demonstrate that this method not only mitigates detector-induced ring artifacts but also exhibits unprecedented capabilities in detail recovery. This method provides a new paradigm for research using unlabeled raw projection data. Code is available at https://github.com/yqx7150/SCOUT.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 28 of its 62 references that are in the map. First posted on arXiv 28 Feb 2026.
Builds on
28 of 62 references.
References · 28
- 2020Denoising Diffusion Probabilistic Modelscited by 21,076
- 2020Denoising Diffusion Implicit Modelscited by 9,781
- 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
- 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,114
- 2022Diffusion Models in Vision: A Surveycited by 1,015
- 2018Noise2Noise: Learning Image Restoration without Clean Datacited by 533
- 2022Improving Diffusion Models for Inverse Problems using Manifold Constraintscited by 508
- 2017Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)cited by 224
- 2021Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Imagescited by 173
- 2019Noisier2Noise: Learning to Denoise from Unpaired Noisy Datacited by 126
- 2024Towards Building Multilingual Language Model for Medicinecited by 92
- 2022Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spotscited by 84
16 more
- 2024Foundation Model for Advancing Healthcare: Challenges, Opportunities, and Future Directionscited by 77
- 2023Zero-Shot Noise2Noise: Efficient Image Denoising without any Datacited by 61
- 2018Can Deep Learning Outperform Modern Commercial CT Image Reconstruction Methods?cited by 54
- 2023CoreDiff: Contextual Error-Modulated Generalized Diffusion Model for Low-Dose CT Denoising and Generalizationcited by 52
- 2021CTSpine1K: A Large-Scale Dataset for Spinal Vertebrae Segmentation in Computed Tomographycited by 46
- 2021DU-GAN: Generative Adversarial Networks with Dual-Domain U-Net Based Discriminators for Low-Dose CT Denoisingcited by 46
- 2020TorchRadon: Fast Differentiable Routines for Computed Tomographycited by 44
- 2025Noise-Inspired Diffusion Model for Generalizable Low-Dose CT Reconstructioncited by 11
- 2026Deeper detection limits in astronomical imaging using self-supervised spatiotemporal denoisingcited by 6
- 2018Non-local Low-rank Cube-based Tensor Factorization for Spectral CT Reconstructioncited by 5
- 2022Spectral2Spectral: Image-spectral Similarity Assisted Spectral CT Deep Reconstruction without Referencecited by 5
- 2025Prompt-SID: Learning Structural Representation Prompt via Latent Diffusion for Single-Image Denoisingcited by 5
- 2025Zero-Shot Low-dose CT Denoising via Sinogram Flickingcited by 2
- 2025Lightweight Data-Free Denoising for Detail-Preserving Biomedical Image Restorationcited by 2
- 2018Block Matching Frame based Material Reconstruction for Spectral CTcited by 1
- 2025Self-supervised denoising of raw tomography detector data for improved image reconstructioncited by 1
Built on by
Not cited yet.