Noise2Recon: Enabling SNR-robust MRI reconstruction with semi-supervised and self-supervised learning.

Autor: Desai AD; Department of Electrical Engineering, Stanford University, Stanford, California, USA.; Department of Radiology, Stanford University, Stanford, California, USA., Ozturkler BM; Department of Electrical Engineering, Stanford University, Stanford, California, USA., Sandino CM; Department of Electrical Engineering, Stanford University, Stanford, California, USA., Boutin R; Department of Radiology, Stanford University, Stanford, California, USA., Willis M; Department of Radiology, Stanford University, Stanford, California, USA., Vasanawala S; Department of Radiology, Stanford University, Stanford, California, USA., Hargreaves BA; Department of Electrical Engineering, Stanford University, Stanford, California, USA.; Department of Radiology, Stanford University, Stanford, California, USA., Ré C; Department of Computer Science, Stanford University, Stanford, California, USA., Pauly JM; Department of Electrical Engineering, Stanford University, Stanford, California, USA., Chaudhari AS; Department of Radiology, Stanford University, Stanford, California, USA.; Department of Biomedical Data Science, Stanford University, Stanford, California, USA.
Jazyk: angličtina
Zdroj: Magnetic resonance in medicine [Magn Reson Med] 2023 Nov; Vol. 90 (5), pp. 2052-2070. Date of Electronic Publication: 2023 Jul 10.
DOI: 10.1002/mrm.29759
Abstrakt: Purpose: To develop a method for building MRI reconstruction neural networks robust to changes in signal-to-noise ratio (SNR) and trainable with a limited number of fully sampled scans.
Methods: We propose Noise2Recon, a consistency training method for SNR-robust accelerated MRI reconstruction that can use both fully sampled (labeled) and undersampled (unlabeled) scans. Noise2Recon uses unlabeled data by enforcing consistency between model reconstructions of undersampled scans and their noise-augmented counterparts. Noise2Recon was compared to compressed sensing and both supervised and self-supervised deep learning baselines. Experiments were conducted using retrospectively accelerated data from the mridata three-dimensional fast-spin-echo knee and two-dimensional fastMRI brain datasets. All methods were evaluated in label-limited settings and among out-of-distribution (OOD) shifts, including changes in SNR, acceleration factors, and datasets. An extensive ablation study was conducted to characterize the sensitivity of Noise2Recon to hyperparameter choices.
Results: In label-limited settings, Noise2Recon achieved better structural similarity, peak signal-to-noise ratio, and normalized-RMS error than all baselines and matched performance of supervised models, which were trained with 14 × $$ 14\times $$ more fully sampled scans. Noise2Recon outperformed all baselines, including state-of-the-art fine-tuning and augmentation techniques, among low-SNR scans and when generalizing to OOD acceleration factors. Augmentation extent and loss weighting hyperparameters had negligible impact on Noise2Recon compared to supervised methods, which may indicate increased training stability.
Conclusion: Noise2Recon is a label-efficient reconstruction method that is robust to distribution shifts, such as changes in SNR, acceleration factors, and others, with limited or no fully sampled training data.
(© 2023 International Society for Magnetic Resonance in Medicine.)
Databáze: MEDLINE
Externí odkaz: