English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deep learning (DL) has shown promise for faster, high quality accelerated MRIreconstruction. However, supervised DL methods depend on extensive amounts offully-sampled (labeled) data and are sensitive to out-of-distribution (OOD)shifts, particularly low signal-to-noise ratio (SNR) acquisitions. To alleviatethis challenge, we propose Noise2Recon, a model-agnostic, consistency trainingmethod for joint MRI reconstruction and denoising that can use bothfully-sampled (labeled) and undersampled (unlabeled) scans in semi-supervisedand self-supervised settings. With limited or no labeled training data,Noise2Recon outperforms compressed sensing and deep learning baselines,including supervised networks, augmentation-based training, fine-tuneddenoisers, and self-supervised methods, and matches performance of supervisedmodels, which were trained with 14x more fully-sampled scans. Noise2Recon alsooutperforms all baselines, including state-of-the-art fine-tuning andaugmentation techniques, among low-SNR scans and when generalizing to other OODfactors, such as changes in acceleration factors and different datasets.Augmentation extent and loss weighting hyperparameters had negligible impact onNoise2Recon compared to supervised methods, which may indicate increasedtraining stability. Our code is available at https://github.com/ad12/meddlr.

Noise2Recon: Enabling Joint MRI Reconstruction and Denoising with Semi-Supervised and Self-Supervised Learning