EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

The “hidden noise” problem in MR image reconstruction

Jiayang Wang iD, Di An, Justin P Haldar iD

Magnetic Resonance in Medicine · 2024-09 · 92 (3) · 982-996

DOI: 10.1002/mrm.30100 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Magnetic Resonance in Medicine, online erschienen am 04.04.2024. Verfasst von Jiayang Wang und 2 weiteren Autor:innen. Beteiligte Einrichtung: Signal and Image Processing Institute, Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, …. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Algorithms, Image Processing, Computer-Assisted, Signal-To-Noise Ratio. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIBIB NIH HHS, NINDS NIH HHS, NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

The performance of modern image reconstruction methods is commonly judged using quantitative error metrics like root mean squared‐error and the structural similarity index, which are calculated by comparing reconstructed images against fully sampled reference data. In practice, the reference data will contain noise and is not a true gold standard. In this work, we demonstrate that the “hidden noise” present in reference data can substantially confound standard approaches for ranking different image reconstruction results.

Methods

Using both experimental and simulated k‐space data and several different image reconstruction techniques, we examined whether there was correlation between performance metrics obtained with typical noisy reference data versus those obtained with higher‐quality reference data.

Results

For conventional performance metrics, the reconstructions that matched best with the higher‐quality reference data were substantially different from the reconstructions that matched best with typical noisy reference data. This leads to suboptimal reconstruction results if the performance with respect to noisy reference data is used to select which reconstruction methods/parameters to employ. These issues were reduced when employing alternative error metrics that better account for noise.

Conclusion

Reference data containing hidden noise can substantially mislead the ranking of image reconstruction methods when using conventional error metrics, but this issue can be mitigated with alternative error metrics.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingAlgorithmsImage Processing, Computer-AssistedSignal-To-Noise RatioHumansBrainPhantoms, ImagingReproducibility of ResultsArtifactsComputer Simulation

Stichwörter der Autor:innen

image quality assessmentimage reconstructionnoise

Autor:innen und Institutionen

  • Signal and Image Processing Institute, Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, California, USA.

ORCID-Profile: Jiayang Wang, Justin P Haldar

Förderung

  • NIBIB NIH HHS
  • NINDS NIH HHS
  • NIH HHS
  • Ming Hsieh Institute for Research on Engineering-Medicine for Cancer
  • University of Southern California (Annenberg Graduate Fellowship)
  • NIMH NIH HHS
  • National Institutes of Health

Zitieren

APA

Wang, J., An, D., & Haldar, J. P. (2024). The “hidden noise” problem in MR image reconstruction. Magnetic Resonance in Medicine, 92(3), 982-996. https://doi.org/10.1002/mrm.30100

Vancouver

Wang J, An D, Haldar JP. The “hidden noise” problem in MR image reconstruction. Magnetic Resonance in Medicine. 2024;92(3):982-996. doi:10.1002/mrm.30100

BibTeX
@article{Wang2024,
  author = {Wang, Jiayang and An, Di and Haldar, Justin P},
  title = {The “hidden noise” problem in MR image reconstruction},
  journal = {Magnetic Resonance in Medicine},
  year = {2024},
  volume = {92},
  number = {3},
  pages = {982--996},
  doi = {10.1002/mrm.30100}
}
Kostenlos starten →