Accelerated CEST imaging through deep learning quantification from reduced frequency offsets
Magnetic Resonance in Medicine · 2025-01 · 93 (1) · 301-310
DOI: 10.1002/mrm.30269 ↗Kurz gefasst
Fachartikel in der Zeitschrift Magnetic Resonance in Medicine, online erschienen am 13.09.2024. Verfasst von Karandeep Cheema und 5 weiteren Autor:innen. Beteiligte Einrichtung: Biomedical Imaging Research Institute, Cedars-Sinai Medical Center, Los Angeles, California, USA. Hauptthemen laut MEDLINE: Deep Learning, Magnetic Resonance Imaging, Image Processing, Computer-Assisted, Glioblastoma. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 15 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIAMS NIH HHS, NIBIB NIH HHS, NHLBI NIH HHS.
Abstract (Originalsprache)
Purpose
To shorten CEST acquisition time by leveraging Z‐spectrum undersampling combined with deep learning for CEST map construction from undersampled Z‐spectra.
Methods
Fisher information gain analysis identified optimal frequency offsets (termed “Fisher offsets”) for the multi‐pool fitting model, maximizing information gain for the amplitude and the FWHM parameters. These offsets guided initial subsampling levels. A U‐NET, trained on undersampled brain CEST images from 18 volunteers, produced CEST maps at 3 T with varied undersampling levels. Feasibility was first tested using retrospective undersampling at three levels, followed by prospective in vivo undersampling (15 of 53 offsets), reducing scan time significantly. Additionally, glioblastoma grade IV pathology was simulated to evaluate network performance in patient‐like cases.
Results
Traditional multi‐pool models failed to quantify CEST maps from undersampled images (structural similarity index [SSIM]
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.
ORCID-Profile: Karandeep Cheema, Pei Han, Anthony G Christodoulou
Förderung
- NIAMS NIH HHS
- NIBIB NIH HHS
- NHLBI NIH HHS
- Common Fund for Commodities
Zitieren
APA
Cheema, K., Han, P., Lee, H. L., Xie, Y., Christodoulou, A. G., & Li, D. (2025). Accelerated CEST imaging through deep learning quantification from reduced frequency offsets. Magnetic Resonance in Medicine, 93(1), 301-310. https://doi.org/10.1002/mrm.30269
Vancouver
Cheema K, Han P, Lee HL, Xie Y, Christodoulou AG, Li D. Accelerated CEST imaging through deep learning quantification from reduced frequency offsets. Magnetic Resonance in Medicine. 2025;93(1):301-310. doi:10.1002/mrm.30269
BibTeX
@article{Cheema2025,
author = {Cheema, Karandeep and Han, Pei and Lee, Hsu-Lei and Xie, Yibin and Christodoulou, Anthony G and Li, Debiao},
title = {Accelerated CEST imaging through deep learning quantification from reduced frequency offsets},
journal = {Magnetic Resonance in Medicine},
year = {2025},
volume = {93},
number = {1},
pages = {301--310},
doi = {10.1002/mrm.30269}
}
EUVIMED