EUVIMEDEUVIMED entdecken
Open Access

Navigator motion‐resolved MR fingerprinting using implicit neural representation: Feasibility for free‐breathing three‐dimensional whole‐liver multiparametric mapping

Chao Li iD, Jiahao Li, Jinwei Zhang, Eddy Solomon iD, Alexey V Dimov iD, Pascal Spincemaille iD, Thanh D Nguyen iD, Martin R Prince, Yi Wang iD

Magnetic Resonance in Medicine · 2026

DOI: 10.1002/mrm.70063 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Magnetic Resonance in Medicine, 2026. Verfasst von Chao Li und 8 weiteren Autor:innen. Beteiligte Einrichtung: Radiology, Weill Cornell Medicine, New York, New York, USA. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Liver, Imaging, Three-Dimensional, Neural Networks, Computer. Die Arbeit nennt 62 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIH HHS, NIBIB NIH HHS, NIDDK NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

To develop a multiparametric free‐breathing three‐dimensional, whole‐liver quantitative maps of water T 1 , water T 2 , fat fraction (FF) and R 2 *.

Methods

A multi‐echo 3D stack‐of‐spiral gradient‐echo sequence with inversion recovery and T 2 ‐prep magnetization preparations was implemented for multiparametric MRI. Fingerprinting and a neural network based on implicit neural representation (FINR) were developed to simultaneously reconstruct the motion deformation fields, the static images, perform water–fat separation, and generate T 1 , T 2 , R 2 *, and FF maps. FINR performance was evaluated in 10 healthy subjects by comparison with quantitative maps generated using conventional breath‐holding imaging.

Results

FINR consistently generated sharp images in all subjects free of motion artifacts. FINR showed minimal bias and narrow 95% limits of agreement for T 1 , T 2 , R 2 *, and FF values in the liver compared with conventional imaging. FINR training took about 3 h per subject, and FINR inference took less than 1 min to produce static images and motion deformation fields.

Conclusions

FINR is a promising approach for 3D whole‐liver T 1 , T 2 , R 2 *, and FF mapping in a single free‐breathing continuous scan.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingLiverImaging, Three-DimensionalNeural Networks, ComputerImage Interpretation, Computer-AssistedHumansMaleAdultFemaleMotionArtifactsFeasibility StudiesRespirationAlgorithmsYoung Adult

Stichwörter der Autor:innen

fingerprintingimplicit neural representation (INR)motion‐resolved imagingmultiparametric mappingnavigator

Autor:innen und Institutionen

  • Radiology, Weill Cornell Medicine, New York, New York, USA.
  • Applied and Engineering Physics, Cornell University, Ithaca, New York, USA.
  • Meinig School of Biomedical Engineering, Cornell University, Ithaca, New York, USA.

ORCID-Profile: Chao Li, Eddy Solomon, Alexey V Dimov, Pascal Spincemaille, Thanh D Nguyen, Yi Wang

Förderung

  • NIH HHS
  • NIBIB NIH HHS
  • NIDDK NIH HHS
  • National Institutes of Health

Zitieren

APA

Li, C., Li, J., Zhang, J., Solomon, E., Dimov, A. V., Spincemaille, P., Nguyen, T. D., Prince, M. R., & Wang, Y. (2026). Navigator motion‐resolved MR fingerprinting using implicit neural representation: Feasibility for free‐breathing three‐dimensional whole‐liver multiparametric mapping. Magnetic Resonance in Medicine. https://doi.org/10.1002/mrm.70063

Vancouver

Li C, Li J, Zhang J, Solomon E, Dimov AV, Spincemaille P, et al. Navigator motion‐resolved MR fingerprinting using implicit neural representation: Feasibility for free‐breathing three‐dimensional whole‐liver multiparametric mapping. Magnetic Resonance in Medicine. 2026. doi:10.1002/mrm.70063

BibTeX
@article{Li2026,
  author = {Li, Chao and Li, Jiahao and Zhang, Jinwei and Solomon, Eddy and Dimov, Alexey V and Spincemaille, Pascal and Nguyen, Thanh D and Prince, Martin R and Wang, Yi},
  title = {Navigator motion‐resolved MR fingerprinting using implicit neural representation: Feasibility for free‐breathing three‐dimensional whole‐liver multiparametric mapping},
  journal = {Magnetic Resonance in Medicine},
  year = {2026},
  doi = {10.1002/mrm.70063}
}
Kostenlos starten →