EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

SELFIE: Self‐Supervised Learning for Fast Dynamic Golden‐Angle Radial MRI

Melanie Schellenberg iD, Anthony Mekhanik iD, Victor Murray iD, Pamela Argiriadi, Yulia Lakhman iD, Galina Levin, Oguz Akin iD, Ricardo Otazo iD

NMR in Biomedicine · 2026-07 · 39 (7)

DOI: 10.1002/nbm.70309 ↗

Kurz gefasst

Fachartikel in der Zeitschrift NMR in Biomedicine, online erschienen am 20.05.2026. Verfasst von Melanie Schellenberg und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, New York, USA. Hauptthemen laut MEDLINE: Supervised Machine Learning, Magnetic Resonance Imaging, Image Processing, Computer-Assisted. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: NCI NIH HHS, NIH HHS, National Institutes of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accelerated golden‐angle radial acquisitions are widely used for dynamic MRI, but compressed sensing (CS)–based reconstruction presents residual artifacts at high acceleration and long computation times. Supervised deep learning (DL) enables fast reconstruction with improved image quality but usually relies on CS because fully‐sampled references are unavailable. The proposed SELFIE (SElf‐supervised Learning for Fast dynamIc golden‐anglE radial MRI) technique enables self‐supervised reconstruction that neither requires fully‐sampled nor CS training references. SELFIE operates slice‐by‐slice in the image domain and thus avoids computationally expensive k‐space data‐consistency operations, allowing for a single forward‐pass inference. Self‐supervision is achieved by leveraging two properties of dynamic imaging with golden‐angle radial sampling: (i) variable temporal resolution to form data‐derived self‐references at multiple temporal resolutions and (ii) temporal sparsity. SELFIE was evaluated on dynamic contrast–enhanced (DCE)‐MRI in patients with gynecologic cancer and on motion‐resolved free‐breathing abdominal MRI in patients with liver cancer. Reconstructions were compared against CS and supervised DL using quantitative image‐quality metrics and qualitative assessment from radiologists. Across both applications, SELFIE achieved image quality and dynamic fidelity (contrast enhancement and motion depiction) comparable to CS and supervised DL, while reconstructing 3D time series in seconds per case, substantially faster than CS. Ranking analysis and reader study favored SELFIE over CS and were comparable to supervised DL, with no statistically significant differences. Overall, SELFIE provides a fast, reference‐free reconstruction framework for dynamic golden‐angle radial MRI with competitive performance, representing a viable alternative to existing methods.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Supervised Machine LearningMagnetic Resonance ImagingImage Processing, Computer-AssistedHumansAlgorithmsFemale

Stichwörter der Autor:innen

dynamic MRIgolden‐angle radial MRIreconstructionself‐supervised learning

Autor:innen und Institutionen

  • Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, New York, USA.
  • Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, New York, USA.

ORCID-Profile: Melanie Schellenberg, Anthony Mekhanik, Victor Murray, Yulia Lakhman, Oguz Akin, Ricardo Otazo

Förderung

  • NCI NIH HHS
  • NIH HHS
  • National Institutes of Health

Zitieren

APA

Schellenberg, M., Mekhanik, A., Murray, V., Argiriadi, P., Lakhman, Y., Levin, G., Akin, O., & Otazo, R. (2026). SELFIE: Self‐Supervised Learning for Fast Dynamic Golden‐Angle Radial MRI. NMR in Biomedicine, 39(7). https://doi.org/10.1002/nbm.70309

Vancouver

Schellenberg M, Mekhanik A, Murray V, Argiriadi P, Lakhman Y, Levin G, et al. SELFIE: Self‐Supervised Learning for Fast Dynamic Golden‐Angle Radial MRI. NMR in Biomedicine. 2026;39(7). doi:10.1002/nbm.70309

BibTeX
@article{Schellenberg2026,
  author = {Schellenberg, Melanie and Mekhanik, Anthony and Murray, Victor and Argiriadi, Pamela and Lakhman, Yulia and Levin, Galina and Akin, Oguz and Otazo, Ricardo},
  title = {SELFIE: Self‐Supervised Learning for Fast Dynamic Golden‐Angle Radial MRI},
  journal = {NMR in Biomedicine},
  year = {2026},
  volume = {39},
  number = {7},
  doi = {10.1002/nbm.70309}
}
Kostenlos starten →