# Stabilize, Decompose, and Denoise: Self-Supervised Fluoroscopy Denoising

arXiv: https://arxiv.org/abs/2208.14022 · HTML: https://mlsanity.com/paper/2208.14022/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 50 references that are in the map.
- First posted on arXiv 30 Aug 2022.

## Builds on (most cited first, 21 of 21)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [Noise2Noise: Learning Image Restoration without Clean Data](https://mlsanity.com/paper/1803.04189/) (2018)
- [FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising](https://mlsanity.com/paper/1710.04026/) (2017)
- [A Deep Reinforced Model for Abstractive Summarization](https://mlsanity.com/paper/1705.04304/) (2017)
- [Noise2Void - Learning Denoising from Single Noisy Images](https://mlsanity.com/paper/1811.10980/) (2018)
- [Reinforcement Learning in Healthcare: A Survey](https://mlsanity.com/paper/1908.08796/) (2019)
- [Deep Reinforcement Learning for Dialogue Generation](https://mlsanity.com/paper/1606.01541/) (2016)
- [Noise2Self: Blind Denoising by Self-Supervision](https://mlsanity.com/paper/1901.11365/) (2019)
- [Learning Blind Video Temporal Consistency](https://mlsanity.com/paper/1808.00449/) (2018)
- [High-Quality Self-Supervised Deep Image Denoising](https://mlsanity.com/paper/1901.10277/) (2019)
- [FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimation](https://mlsanity.com/paper/1907.01361/) (2019)
- [A Tutorial on Kernel Density Estimation and Recent Advances](https://mlsanity.com/paper/1704.03924/) (2017)
- [ViDeNN: Deep Blind Video Denoising](https://mlsanity.com/paper/1904.10898/) (2019)
- [Model-blind Video Denoising Via Frame-to-frame Training](https://mlsanity.com/paper/1811.12766/) (2018)
- [Self-Supervised training for blind multi-frame video denoising](https://mlsanity.com/paper/2004.06957/) (2020)
- [Panoramic Robust PCA for Foreground-Background Separation on Noisy, Free-Motion Camera Video](https://mlsanity.com/paper/1712.06229/) (2017)
- [First image then video: A two-stage network for spatiotemporal video denoising](https://mlsanity.com/paper/2001.00346/) (2020)
- [Efficient Neural Network Approximation of Robust PCA for Automated Analysis of Calcium Imaging Data](https://mlsanity.com/paper/2108.01665/) (2021)
- [Approximated Robust Principal Component Analysis for Improved General Scene Background Subtraction](https://mlsanity.com/paper/1603.05875/) (2016)

## Built on by (most cited first, 1 of 1)

- [Unsupervised Training of a Dynamic Context-Aware Deep Denoising Framework for Low-Dose Fluoroscopic Imaging](https://mlsanity.com/paper/2411.00830/) (2024)

## Abstract (arXiv)

Fluoroscopy is an imaging technique that uses X-ray to obtain a real-time 2D video of the interior of a 3D object, helping surgeons to observe pathological structures and tissue functions especially during intervention. However, it suffers from heavy noise that mainly arises from the clinical use of a low dose X-ray, thereby necessitating the technology of fluoroscopy denoising. Such denoising is challenged by the relative motion between the object being imaged and the X-ray imaging system. We tackle this challenge by proposing a self-supervised, three-stage framework that exploits the domain knowledge of fluoroscopy imaging. (i) Stabilize: we first construct a dynamic panorama based on optical flow calculation to stabilize the non-stationary background induced by the motion of the X-ray detector. (ii) Decompose: we then propose a novel mask-based Robust Principle Component Analysis (RPCA) decomposition method to separate a video with detector motion into a low-rank background and a sparse foreground. Such a decomposition accommodates the reading habit of experts. (iii) Denoise: we finally denoise the background and foreground separately by a self-supervised learning strategy and fuse the denoised parts into the final output via a bilateral, spatiotemporal filter. To assess the effectiveness of our work, we curate a dedicated fluoroscopy dataset of 27 videos (1,568 frames) and corresponding ground truth. Our experiments demonstrate that it achieves significant improvements in terms of denoising and enhancement effects when compared with standard approaches. Finally, expert rating confirms this efficacy.