EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Physics‐Guided Neural Network for Quantitative Parameter Mapping Using Balanced Steady State Free Precession MRI

Hye-Ryeong Choi, Huan Minh Luu, Sung-Hong Park iD

Magnetic Resonance in Medicine · 2026-09 · 96 (3) · 1313-1322

DOI: 10.1002/mrm.70411 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Magnetic Resonance in Medicine, online erschienen am 08.05.2026. Verfasst von Hye-Ryeong Choi und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Bio and Brain Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Brain, Neural Networks, Computer, Image Processing, Computer-Assisted. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Korea Health Industry Development Institute, National Research Foundation of Korea.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

To propose a new method using a physics‐guided neural network for quantitative parameter mapping in balanced steady‐state free precession (bSSFP) imaging. Theory and Methods We trained physics‐guided neural networks with a multilayer perceptron using simulated bSSFP signals generated from tissue parameters (, ,, ∆ f and ) uniformly sampled from predefined ranges corresponding to gray matter, white matter, and cerebrospinal fluid. Over 80 million samples were simulated using six phase‐cycling angles with L2 loss combining parameter and reconstructed signal terms. The model output was obtained both without and with test‐data–specific adaptation. PLANET and CELF were used as comparison methods. Evaluation was conducted using 10 brain digital phantoms from the BrainWeb database and in vivo bSSFP datasets acquired from 10 human subjects on a 3 T scanner using the same scan parameters.

Results

The proposed approaches improved mapping accuracy and consistency visually and quantitatively in both digital phantom and in vivo data compared with PLANET and CELF. Performance with test‐data adaptation was better than that without adaptation. The estimated parameters enabled more accurate reconstruction of images at unseen phase‐cycling angles and flip angles, suggesting the models' generalization capability.

Conclusion

Trained entirely on simulated data, the proposed physics‐guided neural networks enable accurate and efficient multiparameter mapping with high spatial resolution (1.3 × 1.3 × 2.6 ) from phase‐cycled bSSFP within a clinically reasonable scan time of 7 min, offering a promising alternative for MR parameter mapping and data augmentation in training and validating quantitative MRI.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingBrainNeural Networks, ComputerImage Processing, Computer-AssistedBrain MappingHumansPhantoms, ImagingAlgorithmsMultilayer PerceptronsComputer SimulationGray MatterWhite MatterReproducibility of Results

Stichwörter der Autor:innen

balanced steady‐state free precession (bSSFP)ellipse fitting methodphase‐cyclingphysics‐guided neural networksimultaneous quantitative mapping

Autor:innen und Institutionen

  • Department of Bio and Brain Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea.

ORCID-Profile: Sung-Hong Park

Förderung

  • Korea Health Industry Development Institute
  • National Research Foundation of Korea

Zitieren

APA

Choi, H. R., Luu, H. M., & Park, S. H. (2026). Physics‐Guided Neural Network for Quantitative Parameter Mapping Using Balanced Steady State Free Precession MRI. Magnetic Resonance in Medicine, 96(3), 1313-1322. https://doi.org/10.1002/mrm.70411

Vancouver

Choi HR, Luu HM, Park SH. Physics‐Guided Neural Network for Quantitative Parameter Mapping Using Balanced Steady State Free Precession MRI. Magnetic Resonance in Medicine. 2026;96(3):1313-1322. doi:10.1002/mrm.70411

BibTeX
@article{Choi2026,
  author = {Choi, Hye-Ryeong and Luu, Huan Minh and Park, Sung-Hong},
  title = {Physics‐Guided Neural Network for Quantitative Parameter Mapping Using Balanced Steady State Free Precession MRI},
  journal = {Magnetic Resonance in Medicine},
  year = {2026},
  volume = {96},
  number = {3},
  pages = {1313--1322},
  doi = {10.1002/mrm.70411}
}
Kostenlos starten →