# Noise2Contrast: Multi-Contrast Fusion Enables Self-Supervised Tomographic Image Denoising

arXiv: https://arxiv.org/abs/2212.04832 · HTML: https://mlsanity.com/paper/2212.04832/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 19 references that are in the map.
- First posted on arXiv 9 Dec 2022.

## Builds on (most cited first, 11 of 11)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Noise2Noise: Learning Image Restoration without Clean Data](https://mlsanity.com/paper/1803.04189/) (2018)
- [Noise2Void - Learning Denoising from Single Noisy Images](https://mlsanity.com/paper/1811.10980/) (2018)
- [Noise2Self: Blind Denoising by Self-Supervision](https://mlsanity.com/paper/1901.11365/) (2019)
- [Learning with Known Operators reduces Maximum Training Error Bounds](https://mlsanity.com/paper/1907.01992/) (2019)
- [Noise Distribution Adaptive Self-Supervised Image Denoising using Tweedie Distribution and Score Matching](https://mlsanity.com/paper/2112.03696/) (2021)
- [Ultra Low-Parameter Denoising: Trainable Bilateral Filter Layers in Computed Tomography](https://mlsanity.com/paper/2201.10345/) (2022)
- [Self-supervised Dynamic CT Perfusion Image Denoising with Deep Neural Networks](https://mlsanity.com/paper/2005.09766/) (2020)
- [Noise2Context: Context-assisted Learning 3D Thin-layer Low Dose CT Without Clean Data](https://mlsanity.com/paper/2011.12525/) (2020)
- [Trainable Joint Bilateral Filters for Enhanced Prediction Stability in Low-dose CT](https://mlsanity.com/paper/2207.07368/) (2022)
- [Enhanced Magnetic Resonance Image Synthesis with Contrast-Aware Generative Adversarial Networks](https://mlsanity.com/paper/2102.09386/) (2021)

## Built on by (most cited first, 3 of 3)

- [Unsupervised Training of a Dynamic Context-Aware Deep Denoising Framework for Low-Dose Fluoroscopic Imaging](https://mlsanity.com/paper/2411.00830/) (2024)
- [Filter2Noise: A Framework for Interpretable and Zero-Shot Low-Dose CT Image Denoising](https://mlsanity.com/paper/2504.13519/) (2025)
- [Beyond MSE: Rician Likelihood Denoising for Self-Supervised Cardiac T2 and T1ρ MRI](https://mlsanity.com/paper/2609.31777/) (2026)

## Abstract (arXiv)

Self-supervised image denoising techniques emerged as convenient methods that allow training denoising models without requiring ground-truth noise-free data. Existing methods usually optimize loss metrics that are calculated from multiple noisy realizations of similar images, e.g., from neighboring tomographic slices. However, those approaches fail to utilize the multiple contrasts that are routinely acquired in medical imaging modalities like MRI or dual-energy CT. In this work, we propose the new self-supervised training scheme Noise2Contrast that combines information from multiple measured image contrasts to train a denoising model. We stack denoising with domain-transfer operators to utilize the independent noise realizations of different image contrasts to derive a self-supervised loss. The trained denoising operator achieves convincing quantitative and qualitative results, outperforming state-of-the-art self-supervised methods by 4.7-11.0%/4.8-7.3% (PSNR/SSIM) on brain MRI data and by 43.6-50.5%/57.1-77.1% (PSNR/SSIM) on dual-energy CT X-ray microscopy data with respect to the noisy baseline. Our experiments on different real measured data sets indicate that Noise2Contrast training generalizes to other multi-contrast imaging modalities.