Accelerating CEST MRI With Deep Learning‐Based Frequency Selection and Parameter Estimation
NMR in Biomedicine · 2025-07 · 38 (7)
DOI: 10.1002/nbm.70068 ↗Kurz gefasst
Fachartikel in der Zeitschrift NMR in Biomedicine, online erschienen am 21.05.2025. Verfasst von Chushu Shen und 4 weiteren Autor:innen. Beteiligte Einrichtung: Biomedical Imaging Research Institute, Cedars-Sinai Medical Center, Los Angeles, California, USA. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Deep Learning. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 20 Literaturangaben. Gefördert von: NIH HHS, National Institutes of Health.
Abstract (Originalsprache)
Chemical exchange saturation transfer (CEST) MRI is a powerful molecular imaging technique for detecting metabolites through proton exchange. While CEST MRI provides high sensitivity, its clinical application is hindered by prolonged scan time due to the need for imaging across numerous frequency offsets for parameter estimation. Since scan time is directly proportional to the number of frequency offsets, identifying and selecting the most informative frequency can significantly reduce acquisition time. We propose a novel deep learning‐based framework that integrates frequency selection and parameter estimation to accelerate CEST MRI. Our method leverages channel pruning via batch normalization to identify the most informative frequency offsets while simultaneously training the network for accurate parametric map prediction. Using data from six healthy volunteers, channel pruning selects 13 informative frequency offsets out of 53 without compromising map quality. Images from selected frequency offsets were reconstructed using the MR Multitasking method, which employs a low‐rank tensor model to enable under‐sampling of k‐space lines for each frequency offset, further reducing scan time. Predicted parametric maps of amide proton transfer (APT), nuclear overhauser effect (NOE), and magnetization transfer (MT) based on these selected frequencies were comparable in quality to maps generated using all frequency offsets, achieving superior performance compared to Fisher information‐based selection methods from our previous work. This integrated approach has the potential to reduce the whole‐brain CEST MRI scan time from the original 5:30 min to under 1:30 min without compromising map quality. By leveraging deep learning for frequency selection and parametric map prediction, the proposed framework demonstrates its potential for efficient and practical clinical implementation. Future studies will focus on extending this method to patient populations and addressing challenges such as B 0 inhomogeneity and abnormal signal variation in diseased tissues.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Biomedical Imaging Research Institute, Cedars-Sinai Medical Center, Los Angeles, California, USA.
- Department of Bioengineering, University of California Los Angeles, Los Angeles, California, USA.
- Department of Radiation Oncology, University of California Los Angeles, Los Angeles, California, USA.
- Department of Medicine, University of California Los Angeles, Los Angeles, California, USA.
Förderung
- NIH HHS
- National Institutes of Health
Zitieren
APA
Shen, C., Cheema, K., Xie, Y., Ruan, D., & Li, D. (2025). Accelerating CEST MRI With Deep Learning‐Based Frequency Selection and Parameter Estimation. NMR in Biomedicine, 38(7). https://doi.org/10.1002/nbm.70068
Vancouver
Shen C, Cheema K, Xie Y, Ruan D, Li D. Accelerating CEST MRI With Deep Learning‐Based Frequency Selection and Parameter Estimation. NMR in Biomedicine. 2025;38(7). doi:10.1002/nbm.70068
BibTeX
@article{Shen2025,
author = {Shen, Chushu and Cheema, Karandeep and Xie, Yibin and Ruan, Dan and Li, Debiao},
title = {Accelerating CEST MRI With Deep Learning‐Based Frequency Selection and Parameter Estimation},
journal = {NMR in Biomedicine},
year = {2025},
volume = {38},
number = {7},
doi = {10.1002/nbm.70068}
}
EUVIMED