EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Noise2Average: An iterative residual learning strategy for image denoising without clean data

Zihan Li, Ziyu Li, Berkin Bilgic, Kui Ying, David H Salat, Jonathan R Polimeni, Hongen Liao, Susie Y Huang, Qiyuan Tian iD

Imaging Neuroscience · 24.03.2026 · 4

DOI: 10.1162/imag.a.1163 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Imaging Neuroscience, online erschienen am 24.03.2026. Verfasst von Zihan Li und 8 weiteren Autor:innen. Beteiligte Einrichtung: School of Biomedical Engineering, Tsinghua University, Beijing, P.R. China. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 89 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Institute on Aging, NIH Office of the Director, National Institute of Biomedical Imaging and Bioengineering.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Magnetic resonance imaging (MRI) is a widely adopted non-invasive imaging tool for both clinical diagnosis and neuroscientific research. Nonetheless, the quality of MRI is often hampered by noise. Supervised deep learning-based denoising has proven to outperform conventional methods but requires high-signal-to-noise ratio (SNR) reference data for supervising the training, which considerably reduces its practical feasibility. To address this challenge, we propose a new iterative residual learning strategy entitled “Noise2Average” for denoising MRI data with multiple repetitions, which can be combined with transfer learning for subject-specific self-supervised training. Noise2Average learns to map each noisy repetition to the average of all noisy repetitions by fine-tuning parameters of a pre-trained convolutional neural network (CNN) and recovers higher SNR by averaging all denoised results at the first iteration, and performs this supervised residual learning-based denoising process repeatedly with the denoising results from the previous iteration as the training target for several iterations. The efficacy of Noise2Average is systematically and comprehensively demonstrated on four types of commonly acquired MRI data, including two or more consecutively acquired highly accelerated T1-weighted (T1w) image volumes, two T1w image volumes acquired with different echo times, two diffusion-weighted image (DWI) volumes acquired with opposite phase encoding directions, and two DWI volumes synthesized using different sets of DWI volumes from a diffusion tensor imaging (DTI) scan. Quantitative evaluations show that Noise2Average preserves more image sharpness and textural details and produces more accurate quantitative microstructural metrics from DTI signal modeling than the classic Noise2Noise method and conventional benchmark denoising methods BM4D and AONLM, with denoising performance slightly inferior to that of supervised learning-based denoising method. By reducing the requirement for training data and scan time, Noise2Average substantially increases the feasibility and accessibility of deep learning-based denoising methods for MRI and potentially benefits a wider range of clinical and neuroscientific studies.

Schlagwörter

Stichwörter der Autor:innen

diffusion tensor imagingmagnetic resonance imagingself-supervised learningtransfer learning

Autor:innen und Institutionen

  • School of Biomedical Engineering, Tsinghua University, Beijing, P.R. China.
  • Oxford Centre for Integrative Neuroimaging, FMRIB, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, United Kingdom.
  • Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Charlestown, MA, United States.
  • Department of Radiology, Harvard Medical School, Boston, MA, United States.
  • Harvard-MIT Program in Health Sciences and Technology, Massachusetts Institute of Technology, Cambridge, MA, United States.
  • Department of Engineering Physics, Tsinghua University, Beijing, P.R. China.

ORCID-Profile: Qiyuan Tian

Förderung

  • National Institute on Aging
  • NIH Office of the Director
  • National Institute of Biomedical Imaging and Bioengineering
  • National Natural Science Foundation of China
  • Tsinghua University

Zitieren

APA

Li, Z., Li, Z., Bilgic, B., Ying, K., Salat, D. H., Polimeni, J. R., Liao, H., Huang, S. Y., & Tian, Q. (2026). Noise2Average: An iterative residual learning strategy for image denoising without clean data. Imaging Neuroscience, 4. https://doi.org/10.1162/imag.a.1163

Vancouver

Li Z, Li Z, Bilgic B, Ying K, Salat DH, Polimeni JR, et al. Noise2Average: An iterative residual learning strategy for image denoising without clean data. Imaging Neuroscience. 2026;4. doi:10.1162/imag.a.1163

BibTeX
@article{Li2026,
  author = {Li, Zihan and Li, Ziyu and Bilgic, Berkin and Ying, Kui and Salat, David H and Polimeni, Jonathan R and Liao, Hongen and Huang, Susie Y and Tian, Qiyuan},
  title = {Noise2Average: An iterative residual learning strategy for image denoising without clean data},
  journal = {Imaging Neuroscience},
  year = {2026},
  volume = {4},
  doi = {10.1162/imag.a.1163}
}
Kostenlos starten →