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

TL;DR

Noise2Contrast introduces a self-supervised denoising method that leverages multiple image contrasts in medical imaging to improve denoising performance without needing ground-truth data.

Contribution

The paper presents a novel training scheme that combines multi-contrast information and domain-transfer operators for self-supervised tomographic image denoising.

Findings

Outperforms state-of-the-art self-supervised methods in MRI and CT data.

Achieves 4.7-11.0% PSNR and 4.8-7.3% SSIM improvements on brain MRI.

Achieves 43.6-50.5% PSNR and 57.1-77.1% SSIM improvements on dual-energy CT.

Abstract

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.