EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Spectral Representation of Neurochemicals With Phase, Frequency Offset, and Lineshape Invariance: Application to JPRESS for In Vivo Concentration and T 2 Mapping by Deep Learning

Yan Zhang iD, Jun Shen

Magnetic Resonance in Medicine · 2026

DOI: 10.1002/mrm.70291 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Magnetic Resonance in Medicine, 2026. Verfasst von Yan Zhang und 1 weiteren Autor:innen. Beteiligte Einrichtung: National Institute of Mental Health, National Institutes of Health, Bethesda, Maryland, USA. Hauptthemen laut MEDLINE: Deep Learning, Brain, Magnetic Resonance Imaging, Image Processing, Computer-Assisted. Die Arbeit nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Intramural NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Using artificial intelligence neural networks to generate a representation that maps the input directly to neurochemical concentrations and metabolite‐level average transverse relaxation times (T 2 ).

Methods

The proposed model used time‐domain JPRESS data as input and was trained to be invariant to phase shifts, frequency offsets, and lineshape variations, using computer‐synthesized data without prior knowledge of in vivo metabolite concentration distributions. TE‐specific representations were generated using a combination of WaveNet and gated recurrent units (GRUs) and integrated into a unified JPRESS representation.

Results

By focusing solely on target metabolite signals, the model effectively filtered out background signals, including spectral artifacts and unregistered metabolites. The predicted concentrations and metabolite‐level average T 2 values were consistent with those reported in the literature. The model demonstrated robustness to phase shifts, frequency offsets, and line broadening. Additionally, it was capable of detecting low‐concentration neurochemicals, such as gamma‐aminobutyric acid (GABA), without spectral editing.

Conclusion

This study demonstrates that deep learning can be used for automatically quantifying both metabolite concentrations and transverse relaxation times with high practical viability.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningBrainMagnetic Resonance ImagingImage Processing, Computer-AssistedHumansMagnetic Resonance Spectroscopygamma-Aminobutyric AcidAlgorithmsArtifactsNeural Networks, Computer

Stichwörter der Autor:innen

GRUJ‐point resolved spectroscopy (JPRESS)T2WaveNetdeep learningmetabolite concentrations

Substanzen

gamma-Aminobutyric Acid

Autor:innen und Institutionen

  • National Institute of Mental Health, National Institutes of Health, Bethesda, Maryland, USA.

ORCID-Profile: Yan Zhang

Förderung

  • Intramural NIH HHS

Zitieren

APA

Zhang, Y., & Shen, J. (2026). Spectral Representation of Neurochemicals With Phase, Frequency Offset, and Lineshape Invariance: Application to JPRESS for In Vivo Concentration and T 2 Mapping by Deep Learning. Magnetic Resonance in Medicine. https://doi.org/10.1002/mrm.70291

Vancouver

Zhang Y, Shen J. Spectral Representation of Neurochemicals With Phase, Frequency Offset, and Lineshape Invariance: Application to JPRESS for In Vivo Concentration and T 2 Mapping by Deep Learning. Magnetic Resonance in Medicine. 2026. doi:10.1002/mrm.70291

BibTeX
@article{Zhang2026,
  author = {Zhang, Yan and Shen, Jun},
  title = {Spectral Representation of Neurochemicals With Phase, Frequency Offset, and Lineshape Invariance: Application to JPRESS for In Vivo Concentration and T 2 Mapping by Deep Learning},
  journal = {Magnetic Resonance in Medicine},
  year = {2026},
  doi = {10.1002/mrm.70291}
}
Kostenlos starten →