# Consensus Neural Network for Medical Imaging Denoising with Only Noisy Training Samples

arXiv: https://arxiv.org/abs/1906.03639 · HTML: https://mlsanity.com/paper/1906.03639/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jun 2019.

## Built on by (most cited first, 12 of 12)

- [CoreDiff: Contextual Error-Modulated Generalized Diffusion Model for Low-Dose CT Denoising and Generalization](https://mlsanity.com/paper/2304.01814/) (2023)
- [Diffusion Probabilistic Priors for Zero-Shot Low-Dose CT Image Denoising](https://mlsanity.com/paper/2305.15887/) (2023)
- [Unsupervised Domain Adaptation for Low-dose CT Reconstruction via Bayesian Uncertainty Alignment](https://mlsanity.com/paper/2302.13251/) (2023)
- ["One-Shot" Reduction of Additive Artifacts in Medical Images](https://mlsanity.com/paper/2110.12274/) (2021)
- [Self Supervised Low Dose Computed Tomography Image Denoising Using Invertible Network Exploiting Inter Slice Congruence](https://mlsanity.com/paper/2211.01618/) (2022)
- [Neighboring Slice Noise2Noise: Self-Supervised Medical Image Denoising from Single Noisy Image Volume](https://mlsanity.com/paper/2411.10831/) (2024)
- [Self-supervised Deep Learning for Denoising in Ultrasound Microvascular Imaging](https://mlsanity.com/paper/2507.05451/) (2025)
- [S2MS: Self-Supervised Learning Driven Multi-Spectral CT Image Enhancement](https://mlsanity.com/paper/2201.10294/) (2022)
- [Self-supervised Physics-based Denoising for Computed Tomography](https://mlsanity.com/paper/2211.00745/) (2022)
- [One-Pot Multi-Frame Denoising](https://mlsanity.com/paper/2302.11544/) (2023)
- [SSC-UNet: UNet with Self-Supervised Contrastive Learning for Phonocardiography Noise Reduction](https://mlsanity.com/paper/2601.10735/) (2026)
- [Structure and Progress Aware Diffusion for Medical Image Segmentation](https://mlsanity.com/paper/2603.07889/) (2026)

## Abstract (arXiv)

Deep neural networks have been proved efficient for medical image denoising. Current training methods require both noisy and clean images. However, clean images cannot be acquired for many practical medical applications due to naturally noisy signal, such as dynamic imaging, spectral computed tomography, arterial spin labeling magnetic resonance imaging, etc. In this paper we proposed a training method which learned denoising neural networks from noisy training samples only. Training data in the acquisition domain was split to two subsets and the network was trained to map one noisy set to the other. A consensus loss function was further proposed to efficiently combine the outputs from both subsets. A mathematical proof was provided that the proposed training scheme was equivalent to training with noisy and clean samples when the noise in the two subsets was uncorrelated and zero-mean. The method was validated on Low-dose CT Challenge dataset and NYU MRI dataset and achieved improved performance compared to existing unsupervised methods.