EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Input Layer Regularization and Automated Regularization Hyperparameter Tuning for Myelin Water Estimation Using Deep Learning

Mirage Modi iD, Shashank Sule iD, Jonathan Palumbo, Michael Rozowski iD, Griffin S Hampton iD, Mustapha Bouhrara iD, Wojciech Czaja, Richard G Spencer

NMR in Biomedicine · 2026-06 · 39 (6)

DOI: 10.1002/nbm.70276 ↗

Kurz gefasst

Fachartikel in der Zeitschrift NMR in Biomedicine, online erschienen am 22.04.2026. Verfasst von Mirage Modi und 7 weiteren Autor:innen. Beteiligte Einrichtung: National Institute on Aging, National Institutes of Health, Baltimore, Maryland, USA. Hauptthemen laut MEDLINE: Deep Learning, Myelin Sheath, Water. Die Arbeit nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Intramural Research Program of the National Institutes of Health (NIH).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We present a deep learning framework that combines classical regularization and data preprocessing to improve estimation of the myelin water fraction (MWF) in the brain from magnetic resonance relaxometry data. The proposed method is developed within the context of biexponential signal modeling, a standard approach for quantifying MWF. Building on prior work on input layer regularization (ILR), we introduce several key extensions. First, we incorporate optimal regularization hyperparameter selection using either a dedicated neural network or generalized cross‐validation (GCV), applied on a signal‐by‐signal (or pixel‐by‐pixel) basis to generate concatenated input features. Second, we extend the framework to directly estimate MWF in addition to exponential time constants. On synthetic data, the proposed architecture outperforms both conventional regularized fitting methods and standard multilayer perceptrons. When applied to in vivo brain data, it again yields superior accuracy, with GCV‐based parameter selection performing slightly better than the neural network alternative. These findings demonstrate that ILR enhances MWF estimation within the biexponential model and that classical regularization techniques, when integrated with deep learning, can substantially improve quantitative estimation of myelin content.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningMyelin SheathWaterMagnetic Resonance ImagingHumansBrainAlgorithms

Stichwörter der Autor:innen

additive modelsbilevel optimizationinverse problemsmultiexponential analysis

Substanzen

Water

Autor:innen und Institutionen

  • National Institute on Aging, National Institutes of Health, Baltimore, Maryland, USA.
  • Department of Mathematics, University of Maryland, College Park, Maryland, USA.

ORCID-Profile: Mirage Modi, Shashank Sule, Michael Rozowski, Griffin S Hampton, Mustapha Bouhrara

Förderung

  • Intramural Research Program of the National Institutes of Health (NIH)

Zitieren

APA

Modi, M., Sule, S., Palumbo, J., Rozowski, M., Hampton, G. S., Bouhrara, M., Czaja, W., & Spencer, R. G. (2026). Input Layer Regularization and Automated Regularization Hyperparameter Tuning for Myelin Water Estimation Using Deep Learning. NMR in Biomedicine, 39(6). https://doi.org/10.1002/nbm.70276

Vancouver

Modi M, Sule S, Palumbo J, Rozowski M, Hampton GS, Bouhrara M, et al. Input Layer Regularization and Automated Regularization Hyperparameter Tuning for Myelin Water Estimation Using Deep Learning. NMR in Biomedicine. 2026;39(6). doi:10.1002/nbm.70276

BibTeX
@article{Modi2026,
  author = {Modi, Mirage and Sule, Shashank and Palumbo, Jonathan and Rozowski, Michael and Hampton, Griffin S and Bouhrara, Mustapha and Czaja, Wojciech and Spencer, Richard G},
  title = {Input Layer Regularization and Automated Regularization Hyperparameter Tuning for Myelin Water Estimation Using Deep Learning},
  journal = {NMR in Biomedicine},
  year = {2026},
  volume = {39},
  number = {6},
  doi = {10.1002/nbm.70276}
}
Kostenlos starten →