SRNR: Deep learning-based MRI super-resolution using noisy high-resolution reference data
Open Access
- 3 November 2026
- journal article
- Published by MIT Press in Imaging Neuroscience
- Vol. 4
Abstract
Deep learning-based super-resolution (SR) techniques offer a powerful tool to enhance the spatial resolution of magnetic resonance imaging (MRI) without increasing scan time. However, most supervised SR methods rely on high-resolution, high-signal-to-noise ratio (SNR) reference data for training, which are difficult to acquire in many clinical settings, such as in time-constrained pediatric imaging. Inspired by the Noise2Noise principle, we propose SRNR, a new training paradigm that enables supervised SR using noisy high-resolution images as references. SRNR was systematically evaluated on both pediatric and adult simulated data across different noise levels of the reference data. SRNR generated super-resolved image volumes with high similarity to the high-resolution references (PSNR: 32.5–35.2 dB) and improved downstream image analysis performance, including tissue segmentation (white matter Dice coefficient: 0.951–0.960) and cortical surface reconstruction (cortical thickness absolute difference: 0.200–0.255 mm). Furthermore, SRNR was shown to be effective on clinically acquired pediatric brain MRI data, achieving improvements consistent with those observed in the simulated experiments. These results demonstrate that SRNR substantially reduces reliance on clean, high-SNR training data and enables effective SR under clinically realistic acquisition constraints, thereby improving the feasibility of deploying deep learning-based SR in pediatric MRI and related applications.Keywords
Funding Information
- National Natural Science Foundation of China (82302166)
- Tsinghua University (Startup Fund)
This publication has 54 references indexed in Scilit:
- Cortical Thickness Differences in Autistic Children With and Without Intellectual DisabilityAutism Research, 2025
- High‐fidelity fast volumetric brain MRI using synergistic wave‐controlled aliasing in parallel imaging and a hybrid denoising generative adversarial network (HDnGAN)Medical Physics, 2021
- Automated brain extraction of multisequence MRI using artificial neural networksHuman Brain Mapping, 2019
- Utility of deep learning super‐resolution in the context of osteoarthritis MRI biomarkersJournal of Magnetic Resonance Imaging, 2019
- Techniques for minimizing sedation in pediatric MRIJournal of Magnetic Resonance Imaging, 2019
- Highly‐accelerated volumetric brain examination using optimized wave‐CAIPI encodingJournal of Magnetic Resonance Imaging, 2019
- Super‐resolution musculoskeletal MRI using deep learningMagnetic Resonance in Medicine, 2018
- Wave‐CAIPI for highly accelerated MP‐RAGE imagingMagnetic Resonance in Medicine, 2017
- Super‐resolution methods in MRI: Can they improve the trade‐off between resolution, signal‐to‐noise ratio, and acquisition time?Magnetic Resonance in Medicine, 2012
- The rician distribution of noisy mri dataMagnetic Resonance in Medicine, 1995