Self-supervised Physics-based Denoising for Computed Tomography
Not on the map. Why?
Abstract (arXiv)
Computed Tomography (CT) imposes risk on the patients due to its inherent X-ray radiation, stimulating the development of low-dose CT (LDCT) imaging methods. Lowering the radiation dose reduces the health risks but leads to noisier measurements, which decreases the tissue contrast and causes artifacts in CT images. Ultimately, these issues could affect the perception of medical personnel and could cause misdiagnosis. Modern deep learning noise suppression methods alleviate the challenge but require low-noise-high-noise CT image pairs for training, rarely collected in regular clinical workflows. In this work, we introduce a new self-supervised approach for CT denoising Noise2NoiseTD-ANM that can be trained without the high-dose CT projection ground truth images. Unlike previously proposed self-supervised techniques, the introduced method exploits the connections between the adjacent projections and the actual model of CT noise distribution. Such a combination allows for interpretable no-reference denoising using nothing but the original noisy LDCT projections. Our experiments with LDCT data demonstrate that the proposed method reaches the level of the fully supervised models, sometimes superseding them, easily generalizes to various noise levels, and outperforms state-of-the-art self-supervised denoising algorithms.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 22 of its 50 references that are in the map. First posted on arXiv 1 Nov 2022.
Builds on
22 of 50 references.
References · 22
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2017Squeeze-and-Excitation Networkscited by 4,763
- 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,428
- 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
- 2018Noise2Noise: Learning Image Restoration without Clean Datacited by 526
- 2017FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoisingcited by 509
- 2018Noise2Void - Learning Denoising from Single Noisy Imagescited by 359
- 2019Noise2Self: Blind Denoising by Self-Supervisioncited by 274
- 2017Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)cited by 224
- 2013Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Indexcited by 193
- 2019High-Quality Self-Supervised Deep Image Denoisingcited by 161
- 2019Robust and interpretable blind image denoising via bias-free convolutional neural networkscited by 87
10 more
- 2020Noise2Same: Optimizing A Self-Supervised Bound for Image Denoisingcited by 56
- 20183D Convolutional Encoder-Decoder Network for Low-Dose CT via Transfer Learning from a 2D Trained Networkcited by 47
- 2018Cycle Consistent Adversarial Denoising Network for Multiphase Coronary CT Angiographycited by 23
- 2021Deformed2Self: Self-Supervised Denoising for Dynamic Medical Imagingcited by 15
- 2019Consensus Neural Network for Medical Imaging Denoising with Only Noisy Training Samplescited by 12
- 2019Unpaired image denoising using a generative adversarial network in X-ray CTcited by 10
- 2019Microscopy Image Restoration with Deep Wiener-Kolmogorov filterscited by 7
- 2020Noise2Kernel: Adaptive Self-Supervised Blind Denoising using a Dilated Convolutional Kernel Architecturecited by 7
- 2020Self-Supervised Training For Low Dose CT Reconstructioncited by 4
- 2021No-reference denoising of low-dose CT projectionscited by 1
Built on by
Citing papers per year: 2024: 1.
1 paper.