Deep Learning‐Based Auto‐Navigation for Free‐Breathing Golden‐Angle Radial MRI
Magnetic Resonance in Medicine · 2026
DOI: 10.1002/mrm.70313 ↗Kurz gefasst
Fachartikel in der Zeitschrift Magnetic Resonance in Medicine, 2026. Verfasst von Joel Jose Quitlong Nario und 5 weiteren Autor:innen. Beteiligte Einrichtung: Weill Cornell Graduate School of Medical Sciences, New York, New York, USA. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Deep Learning, Image Processing, Computer-Assisted, Abdomen. Die Arbeit nennt 44 Literaturangaben. Gefördert von: NCI NIH HHS, NIH HHS, National Institutes of Health.
Abstract (Originalsprache)
Purpose
To develop a deep learning‐based auto‐navigation technique for free‐breathing golden‐angle radial MRI named RANGR ( R espiratory A uto‐ N avigator for G olden‐angle R adial free‐breathing abdominal MRI).
Methods
RANGR computes a one‐dimensional (1D) respiratory motion signal from 1D projections along the superior–inferior dimension ( z ) extracted directly from the acquired golden‐angle stack‐of‐stars k‐space data. The motion signal is used to retrospectively sort k‐space data into different undersampled motion states, which are reconstructed using Movienet, a neural network developed for dynamic reconstruction. RANGR was trained using PCA (Principal Component Analysis) as a reference in cases where PCA was successful. The performance of RANGR is evaluated against PCA using a dynamic phantom with programmable motion waveforms on a 1.5 T MR‐Linac system and free‐breathing imaging of patients with abdominal tumors. In vivo image quality was qualitatively scored by body radiologists.
Results
For phantom studies, RANGR can track motion with less than 1 mm error with respect to the ground‐truth. For in vivo studies, RANGR generalizes to cases where PCA failed due to limited liver coverage and/or the presence of high intensity regions outside the liver dome. RANGR outscores PCA on all qualitative image criteria as evaluated on a 5‐point Likert scale by two expert body radiologists ( p < 0.05). RANGR estimates motion faster than PCA on GPU (1.7 ± 0.3 vs. 168.7 ± 172.4 ms, p < 0.005). The total time from motion estimation to Movienet reconstruction is 2.91 ± 1.07 s.
Conclusion
RANGR presents a robust auto‐navigation solution based on deep learning for free‐breathing MRI using golden‐angle radial MRI acquisition.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Weill Cornell Graduate School of Medical Sciences, New York, New York, USA.
- Department of Radiology, NewYork-Presbyterian/Weill Cornell Medical Center, New York, New York, USA.
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, New York, USA.
- Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, New York, USA.
ORCID-Profile: Joel Jose Quitlong Nario, Victor Murray, Anthony Mekhanik, Maria El Homsi, Tae Hyung Kim, Ricardo Otazo
Förderung
- NCI NIH HHS
- NIH HHS
- National Institutes of Health
Zitieren
APA
Nario, J. J. Q., Murray, V., Mekhanik, A., El Homsi, M., Kim, T. H., & Otazo, R. (2026). Deep Learning‐Based Auto‐Navigation for Free‐Breathing Golden‐Angle Radial MRI. Magnetic Resonance in Medicine. https://doi.org/10.1002/mrm.70313
Vancouver
Nario JJQ, Murray V, Mekhanik A, El Homsi M, Kim TH, Otazo R. Deep Learning‐Based Auto‐Navigation for Free‐Breathing Golden‐Angle Radial MRI. Magnetic Resonance in Medicine. 2026. doi:10.1002/mrm.70313
BibTeX
@article{Nario2026,
author = {Nario, Joel Jose Quitlong and Murray, Victor and Mekhanik, Anthony and El Homsi, Maria and Kim, Tae Hyung and Otazo, Ricardo},
title = {Deep Learning‐Based Auto‐Navigation for Free‐Breathing Golden‐Angle Radial MRI},
journal = {Magnetic Resonance in Medicine},
year = {2026},
doi = {10.1002/mrm.70313}
}
EUVIMED