EUVIMEDOpdag EUVIMED
Open access

Bias‐reduced neural networks for parameter estimation in quantitative MRI

Andrew Mao iD, Sebastian Flassbeck iD, Jakob Assländer iD

Magnetic Resonance in Medicine · 2024

DOI: 10.1002/mrm.30135 ↗

At a glance

Journal article in Magnetic Resonance in Medicine, 2024. Written by Andrew Mao and 2 co-authors. Institution: Bernard and Irene Schwartz Center for Biomedical Imaging, Department of Radiology, New York University Grossman School of Medicine, New York, New Yor…. Major MEDLINE topics: Magnetic Resonance Imaging, Neural Networks, Computer, Algorithms, Brain. Cited 9 times so far (Crossref); 50 references. The full text is freely available in PubMed Central. Funded by: NIA NIH HHS, NIBIB NIH HHS, NINDS NIH HHS.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Purpose

To develop neural network (NN)‐based quantitative MRI parameter estimators with minimal bias and a variance close to the Cramér–Rao bound. Theory and Methods We generalize the mean squared error loss to control the bias and variance of the NN's estimates, which involves averaging over multiple noise realizations of the same measurements during training. Bias and variance properties of the resulting NNs are studied for two neuroimaging applications.

Results

In simulations, the proposed strategy reduces the estimates' bias throughout parameter space and achieves a variance close to the Cramér–Rao bound. In vivo, we observe good concordance between parameter maps estimated with the proposed NNs and traditional estimators, such as nonlinear least‐squares fitting, while state‐of‐the‐art NNs show larger deviations.

Conclusion

The proposed NNs have greatly reduced bias compared to those trained using the mean squared error and offer significantly improved computational efficiency over traditional estimators with comparable or better accuracy.

Subjects

MeSH terms (MEDLINE)

Magnetic Resonance ImagingNeural Networks, ComputerAlgorithmsBrainComputer SimulationImage Processing, Computer-AssistedHumansBiasNeuroimagingReproducibility of ResultsLeast-Squares Analysis

Author keywords

Cramér–Rao boundefficiencyneural networksparameter estimationquantitative MRI

Authors and institutions

  • Bernard and Irene Schwartz Center for Biomedical Imaging, Department of Radiology, New York University Grossman School of Medicine, New York, New York, USA.
  • Center for Advanced Imaging Innovation and Research (CAI2R), Department of Radiology, New York University Grossman School of Medicine, New York, New York, USA.
  • Vilcek Institute of Graduate Biomedical Sciences, New York University Grossman School of Medicine, New York, New York, USA.

ORCID profiles: Andrew Mao, Sebastian Flassbeck, Jakob Assländer

Funding

  • NIA NIH HHS
  • NIBIB NIH HHS
  • NINDS NIH HHS
  • NIGMS NIH HHS
  • National Institute of Neurological Disorders and Stroke
  • National Institute of Biomedical Imaging and Bioengineering
  • National Institute on Aging
  • National Institute of General Medical Sciences

Cite

APA

Mao, A., Flassbeck, S., & Assländer, J. (2024). Bias‐reduced neural networks for parameter estimation in quantitative MRI. Magnetic Resonance in Medicine. https://doi.org/10.1002/mrm.30135

Vancouver

Mao A, Flassbeck S, Assländer J. Bias‐reduced neural networks for parameter estimation in quantitative MRI. Magnetic Resonance in Medicine. 2024. doi:10.1002/mrm.30135

BibTeX
@article{Mao2024,
  author = {Mao, Andrew and Flassbeck, Sebastian and Assländer, Jakob},
  title = {Bias‐reduced neural networks for parameter estimation in quantitative MRI},
  journal = {Magnetic Resonance in Medicine},
  year = {2024},
  doi = {10.1002/mrm.30135}
}
Start for free →