EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Using a deep learning prior for accelerating hyperpolarized 13 C MRSI on synthetic cancer datasets

Zuojun Wang, Guanxiong Luo iD, Ye Li, Peng Cao iD

Magnetic Resonance in Medicine · 2024

DOI: 10.1002/mrm.30053 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Magnetic Resonance in Medicine, 2024. Verfasst von Zuojun Wang und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Diagnostic Radiology, The University of Hong Kong, Hong Kong, People's Republic of China. Hauptthemen laut MEDLINE: Deep Learning, Prostatic Neoplasms, Magnetic Resonance Imaging, Brain Neoplasms. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Hong Kong Innovation and Technology Fund.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

We aimed to incorporate a deep learning prior with k‐space data fidelity for accelerating hyperpolarized carbon‐13 MRSI, demonstrated on synthetic cancer datasets.

Methods

A two‐site exchange model, derived from the Bloch equation of MR signal evolution, was firstly used in simulating training and testing data, that is, synthetic phantom datasets. Five singular maps generated from each simulated dataset were used to train a deep learning prior, which was then employed with the fidelity term to reconstruct the undersampled MRI k‐space data. The proposed method was assessed on synthetic human brain tumor images ( N = 33), prostate cancer images ( N = 72), and mouse tumor images ( N = 58) for three undersampling factors and 2.5% additive Gaussian noise. Furthermore, varied levels of Gaussian noise with SDs of 2.5%, 5%, and 10% were added on synthetic prostate cancer data, and corresponding reconstruction results were evaluated.

Results

For quantitative evaluation, peak SNRs were approximately 32 dB, and the accuracy was generally improved for 5 to 8 dB compared with those from compressed sensing with L1‐norm regularization or total variation regularization. Reasonable normalized RMS error were obtained. Our method also worked robustly against noise, even on a data with noise SD of 10%.

Conclusion

The proposed singular value decomposition + iterative deep learning model could be considered as a general framework that extended the application of deep learning MRI reconstruction to metabolic imaging. The morphology of tumors and metabolic images could be measured robustly in six times acceleration using our method.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningProstatic NeoplasmsMagnetic Resonance ImagingBrain NeoplasmsImage Processing, Computer-AssistedPhantoms, ImagingHumansMaleMiceAnimalsSignal-To-Noise RatioAlgorithmsBrainCarbon Isotopes

Stichwörter der Autor:innen

MRSIcancer imagesdeep learning priorpyruvate

Substanzen

Carbon IsotopesCarbon-13

Autor:innen und Institutionen

  • Department of Diagnostic Radiology, The University of Hong Kong, Hong Kong, People's Republic of China.
  • Institute for Diagnostic and Interventional Radiology, University Medical Center Göttingen, Göttingen, Germany.
  • Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology of Chinese Academy of Sciences, Shenzhen, People's Republic of China.

ORCID-Profile: Guanxiong Luo, Peng Cao

Förderung

  • Hong Kong Innovation and Technology Fund

Zitieren

APA

Wang, Z., Luo, G., Li, Y., & Cao, P. (2024). Using a deep learning prior for accelerating hyperpolarized 13 C MRSI on synthetic cancer datasets. Magnetic Resonance in Medicine. https://doi.org/10.1002/mrm.30053

Vancouver

Wang Z, Luo G, Li Y, Cao P. Using a deep learning prior for accelerating hyperpolarized 13 C MRSI on synthetic cancer datasets. Magnetic Resonance in Medicine. 2024. doi:10.1002/mrm.30053

BibTeX
@article{Wang2024,
  author = {Wang, Zuojun and Luo, Guanxiong and Li, Ye and Cao, Peng},
  title = {Using a deep learning prior for accelerating hyperpolarized 13 C MRSI on synthetic cancer datasets},
  journal = {Magnetic Resonance in Medicine},
  year = {2024},
  doi = {10.1002/mrm.30053}
}
Kostenlos starten →