Fast deep learning reconstruction techniques for preclinical magnetic resonance fingerprinting
NMR in Biomedicine · 2024
DOI: 10.1002/nbm.5028 ↗Kurz gefasst
Fachartikel in der Zeitschrift NMR in Biomedicine, 2024. Verfasst von Raffaella Fiamma Cabini und 13 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mathematics, University of Pavia, Pavia, Italy. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Deep Learning. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: INFN next_AIM project, M. P. thanks ALSA.
Abstract (Originalsprache)
We propose a deep learning (DL) model and a hyperparameter optimization strategy to reconstruct T 1 and T 2 maps acquired with the magnetic resonance fingerprinting (MRF) methodology. We applied two different MRF sequence routines to acquire images of ex vivo rat brain phantoms using a 7‐T preclinical scanner. Subsequently, the DL model was trained using experimental data, completely excluding the use of any theoretical MRI signal simulator. The best combination of the DL parameters was implemented by an automatic hyperparameter optimization strategy, whose key aspect is to include all the parameters to the fit, allowing the simultaneous optimization of the neural network architecture, the structure of the DL model, and the supervised learning algorithm. By comparing the reconstruction performances of the DL technique with those achieved from the traditional dictionary‐based method on an independent dataset, the DL approach was shown to reduce the mean percentage relative error by a factor of 3 for T 1 and by a factor of 2 for T 2 , and to improve the computational time by at least a factor of 37. Furthermore, the proposed DL method enables maintaining comparable reconstruction performance, even with a lower number of MRF images and a reduced k‐space sampling percentage, with respect to the dictionary‐based method. Our results suggest that the proposed DL methodology may offer an improvement in reconstruction accuracy, as well as speeding up MRF for preclinical, and in prospective clinical, investigations.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Mathematics, University of Pavia, Pavia, Italy.
- INFN, Istituto Nazionale di Fisica Nucleare, Pavia, Italy.
- Advanced Imaging and Artificial Intelligence, Department of Neuroradiology, IRCCS Mondino Foundation, Pavia, Italy.
- Department of Physics, University of Pavia, Pavia, Italy.
- Department of Physics, University of Milan, Milan, Italy.
- INFN, Istituto Nazionale di Fisica Nucleare, Milan, Italy.
ORCID-Profile: Raffaella Fiamma Cabini, Leonardo Barzaghi, Davide Cicolari, Paolo Arosio, Stefano Carrazza, Silvia Figini, Marta Filibian, Andrea Gazzano, Rolf Krause, Manuel Mariani, Marco Peviani, Anna Pichiecchio, Diego Ulisse Pizzagalli, Alessandro Lascialfari
Förderung
- INFN next_AIM project
- M. P. thanks ALSA
Zitieren
APA
Cabini, R. F., Barzaghi, L., Cicolari, D., Arosio, P., Carrazza, S., Figini, S., Filibian, M., Gazzano, A., Krause, R., Mariani, M., Peviani, M., Pichiecchio, A., Pizzagalli, D. U., & Lascialfari, A. (2024). Fast deep learning reconstruction techniques for preclinical magnetic resonance fingerprinting. NMR in Biomedicine. https://doi.org/10.1002/nbm.5028
Vancouver
Cabini RF, Barzaghi L, Cicolari D, Arosio P, Carrazza S, Figini S, et al. Fast deep learning reconstruction techniques for preclinical magnetic resonance fingerprinting. NMR in Biomedicine. 2024. doi:10.1002/nbm.5028
BibTeX
@article{Cabini2024,
author = {Cabini, Raffaella Fiamma and Barzaghi, Leonardo and Cicolari, Davide and Arosio, Paolo and Carrazza, Stefano and Figini, Silvia and Filibian, Marta and Gazzano, Andrea and Krause, Rolf and Mariani, Manuel and Peviani, Marco and Pichiecchio, Anna and Pizzagalli, Diego Ulisse and Lascialfari, Alessandro},
title = {Fast deep learning reconstruction techniques for preclinical magnetic resonance fingerprinting},
journal = {NMR in Biomedicine},
year = {2024},
doi = {10.1002/nbm.5028}
}
EUVIMED