EUVIMEDEUVIMED entdecken
Crossref

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

Arjun D Desai iD, Batu M Ozturkler, Christopher M Sandino iD, Robert Boutin, Marc Willis, Shreyas Vasanawala, Brian A Hargreaves, Christopher Ré, John M Pauly, Akshay S Chaudhari iD

Magnetic Resonance in Medicine · 2023

DOI: 10.1002/mrm.29759 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Magnetic Resonance in Medicine, 2023. Verfasst von Arjun D Desai und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical Engineering, Stanford University, Stanford, California, USA. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Deep Learning. Die Arbeit wurde bisher 35-mal zitiert (Crossref) und nennt 68 Literaturangaben. Gefördert von: NIAMS NIH HHS, NIBIB NIH HHS, GE Healthcare.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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 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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Image Processing, Computer-AssistedDeep LearningHumansSignal-To-Noise RatioRetrospective StudiesMagnetic Resonance ImagingSupervised Machine Learning

Stichwörter der Autor:innen

data efficiencydeep learningdenoisingdistribution shiftimage reconstructionself-supervised learningsemi-supervised learning

Autor:innen und Institutionen

  • Department of Electrical Engineering, Stanford University, Stanford, California, USA.
  • Department of Radiology, Stanford University, Stanford, California, USA.
  • Department of Computer Science, Stanford University, Stanford, California, USA.
  • Department of Biomedical Data Science, Stanford University, Stanford, California, USA.

ORCID-Profile: Arjun D Desai, Christopher M Sandino, Akshay S Chaudhari

Förderung

  • NIAMS NIH HHS
  • NIBIB NIH HHS
  • GE Healthcare
  • National Institute of Arthritis and Musculoskeletal and Skin Diseases
  • National Institute of Biomedical Imaging and Bioengineering
  • National Science Foundation of Sri Lanka
  • Philips
  • U.S. Department of Defense

Zitieren

APA

Desai, A. D., Ozturkler, B. M., Sandino, C. M., Boutin, R., Willis, M., Vasanawala, S., Hargreaves, B. A., Ré, C., Pauly, J. M., & Chaudhari, A. S. (2023). Noise2Recon: Enabling SNR‐robust MRI reconstruction with semi‐supervised and self‐supervised learning. Magnetic Resonance in Medicine. https://doi.org/10.1002/mrm.29759

Vancouver

Desai AD, Ozturkler BM, Sandino CM, Boutin R, Willis M, Vasanawala S, et al. Noise2Recon: Enabling SNR‐robust MRI reconstruction with semi‐supervised and self‐supervised learning. Magnetic Resonance in Medicine. 2023. doi:10.1002/mrm.29759

BibTeX
@article{Desai2023,
  author = {Desai, Arjun D and Ozturkler, Batu M and Sandino, Christopher M and Boutin, Robert and Willis, Marc and Vasanawala, Shreyas and Hargreaves, Brian A and Ré, Christopher and Pauly, John M and Chaudhari, Akshay S},
  title = {Noise2Recon: Enabling SNR‐robust MRI reconstruction with semi‐supervised and self‐supervised learning},
  journal = {Magnetic Resonance in Medicine},
  year = {2023},
  doi = {10.1002/mrm.29759}
}
Kostenlos starten →