EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Improved quantitative parameter estimation for prostate T2 relaxometry using convolutional neural networks

Patrick J Bolan, Sara L Saunders, Kendrick Kay, Mitchell Gross, Mehmet Akcakaya, Gregory J Metzger

Magnetic Resonance Materials in Physics, Biology and Medicine · 2024

DOI: 10.1007/s10334-024-01186-3 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Magnetic Resonance Materials in Physics, Biology and Medicine, 2024. Verfasst von Patrick J Bolan und 5 weiteren Autor:innen. Beteiligte Einrichtung: Center for Magnetic Resonance Research, University of Minnesota, 2021 6th Street SE, Minneapolis, MN, 55455, USA. bolan@umn.edu. Hauptthemen laut MEDLINE: Neural Networks, Computer, Prostate, Magnetic Resonance Imaging, Signal-To-Noise Ratio. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NHLBI NIH HHS, NIBIB NIH HHS, NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

Quantitative parameter mapping conventionally relies on curve fitting techniques to estimate parameters from magnetic resonance image series. This study compares conventional curve fitting techniques to methods using neural networks (NN) for measuring T 2 in the prostate. Materials and methods Large physics-based synthetic datasets simulating T 2 mapping acquisitions were generated for training NNs and for quantitative performance comparisons. Four combinations of different NN architectures and training corpora were implemented and compared with four different curve fitting strategies. All methods were compared quantitatively using synthetic data with known ground truth, and further compared on in vivo test data, with and without noise augmentation, to evaluate feasibility and noise robustness.

Results

In the evaluation on synthetic data, a convolutional neural network (CNN), trained in a supervised fashion using synthetic data generated from naturalistic images, showed the highest overall accuracy and precision amongst the methods. On in vivo data, this best performing method produced low-noise T 2 maps and showed the least deterioration with increasing input noise levels.

Discussion

This study showed that a CNN, trained with synthetic data in a supervised manner, may provide superior T 2 estimation performance compared to conventional curve fitting, especially in low signal-to-noise regions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerProstateMagnetic Resonance ImagingSignal-To-Noise RatioAlgorithmsImage Processing, Computer-AssistedHumansMaleProstatic NeoplasmsImage Interpretation, Computer-AssistedReproducibility of Results

Stichwörter der Autor:innen

T 2 mappingMagnetic resonance imagingNeural networksProstateRelaxometry

Autor:innen und Institutionen

  • Center for Magnetic Resonance Research, University of Minnesota, 2021 6th Street SE, Minneapolis, MN, 55455, USA. bolan@umn.edu.
  • Department of Radiology, University of Minnesota, Minneapolis, MN, USA. bolan@umn.edu.
  • Department of Biomedical Engineering, University of Minnesota, Minneapolis, MN, USA.
  • Center for Magnetic Resonance Research, University of Minnesota, 2021 6th Street SE, Minneapolis, MN, 55455, USA.
  • Department of Radiology, University of Minnesota, Minneapolis, MN, USA.
  • Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA.

Förderung

  • NHLBI NIH HHS
  • NIBIB NIH HHS
  • NIH HHS
  • ODCDC CDC HHS
  • NCI NIH HHS
  • National Institute of Biomedical Imaging and Bioengineering
  • National Cancer Institute
  • NIH Office of the Director

Zitieren

APA

Bolan, P. J., Saunders, S. L., Kay, K., Gross, M., Akcakaya, M., & Metzger, G. J. (2024). Improved quantitative parameter estimation for prostate T2 relaxometry using convolutional neural networks. Magnetic Resonance Materials in Physics, Biology and Medicine. https://doi.org/10.1007/s10334-024-01186-3

Vancouver

Bolan PJ, Saunders SL, Kay K, Gross M, Akcakaya M, Metzger GJ. Improved quantitative parameter estimation for prostate T2 relaxometry using convolutional neural networks. Magnetic Resonance Materials in Physics, Biology and Medicine. 2024. doi:10.1007/s10334-024-01186-3

BibTeX
@article{Bolan2024,
  author = {Bolan, Patrick J and Saunders, Sara L and Kay, Kendrick and Gross, Mitchell and Akcakaya, Mehmet and Metzger, Gregory J},
  title = {Improved quantitative parameter estimation for prostate T2 relaxometry using convolutional neural networks},
  journal = {Magnetic Resonance Materials in Physics, Biology and Medicine},
  year = {2024},
  doi = {10.1007/s10334-024-01186-3}
}
Kostenlos starten →