Share：
Share this content in WeChat
X
[Chinese][PDF]44810
• Special Focus •
The clinical application and development prospect of deep learning MRI reconstruction algorithm
YAN Fuhua 

Cite this article as: YAN F H. The clinical application and development prospect of deep learning MRI reconstruction algorithm[J]. Chin J Magn Reson Imaging, 2023, 14(5): 8-10. DOI:10.12015/issn.1674-8034.2023.05.002.


[Abstract] With the development of MR technology, MRI has become more and more popular in the clinical application for the diagnosis. However, there are many problems and challenges that restrict each other in scanning time, image resolution and signal to noise ratio based on traditional MRI reconstruction methods. In recent years, deep learning (DL) MRI reconstruction algorithm has been proposed, which has greatly solved the shortcomings of traditional reconstruction algorithms. DL-MRI reconstruction has been applied in nervous system, muscle and skeletal system, body and cardiac imaging. It has excellent performance in reducing scan time, improving signal-to-noise ratio and resolution, and also has potential advantages in improving the lesion detection and characterization. At present, the commercialized DL-MRI reconstruction model can fully meet the clinical needs in the reconstruction speed. However, it is still need further study for the clinical application scenario and the effectiveness on imaging diagnosis, facilitated to playing the advantages of MRI and helpful for improving the clinical procedure.
[Keywords] magnetic resonance imaging；deep learning；image reconstruction

YAN Fuhua*  

Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200025, China

Corresponding author: Yan FH, E-mail: yfh11655@rjh.com.cn

Conflicts of interest   None.

Received  2023-02-12
Accepted  2023-05-15
DOI: 10.12015/issn.1674-8034.2023.05.002
Cite this article as: YAN F H. The clinical application and development prospect of deep learning MRI reconstruction algorithm[J]. Chin J Magn Reson Imaging, 2023, 14(5): 8-10. DOI:10.12015/issn.1674-8034.2023.05.002.

[1]
LAUTERBUR P C. Image formation by induced local interactions. Examples employing nuclear magnetic resonance. 1973[J]. Clin Orthop Relat Res, 1989(244): 3-6.
[2]
VIARD A, EUSTACHE F, SEGOBIN S. History of magnetic resonance imaging: a trip down memory lane[J]. Neuroscience, 2021, 474: 3-13. DOI: 10.1016/j.neuroscience.2021.06.038">10.1016/j.neuroscience.2021.06.038">10.1016/j.neuroscience.2021.06.038.
[3]
ERNST R R. NMR Fourier zeugmatography[J]. J Magn Reson, 2011, 213(2): 510-512. DOI: 10.1016/j.jmr.2011.08.006">10.1016/j.jmr.2011.08.006">10.1016/j.jmr.2011.08.006.
[4]
HOLLAND G N, HAWKES R C, MOORE W S. Nuclear magnetic resonance (NMR) tomography of the brain: coronal and sagittal sections[J]. J Comput Assist Tomogr, 1980, 4(4): 429-433. DOI: 10.1097/00004728-198008000-00002">10.1097/00004728-198008000-00002">10.1097/00004728-198008000-00002.
[5]
PAL A, RATHI Y. A review and experimental evaluation of deep learning methods for MRI reconstruction[J/OL]. J Mach Learn Biomed Imaging, 2022, 1: 001 [2023-02-11]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9202830/. DOI: 10.1109/TMI.2018.2865356">10.1109/TMI.2018.2865356">10.1109/TMI.2018.2865356.
[6]
LEBEL R M. Performance characterization of a novel deep learning-based MR image reconstruction pipeline[EB/OL]. [2023-02-11]. https://arxiv.org/abs/2008.06559. DOI: 10.48550/arXiv.2008.06559">10.48550/arXiv.2008.06559">10.48550/arXiv.2008.06559.
[7]
HUTCHINSON M, RAFF U. Fast MRI data acquisition using multiple detectors[J]. Magn Reson Med, 1988, 6(1): 87-91. DOI: 10.1002/mrm.1910060110">10.1002/mrm.1910060110">10.1002/mrm.1910060110.
[8]
MÜLLER S. Multifrequency selective rf pulses for multislice MR imaging[J]. Magn Reson Med, 1988, 6(3): 364-371. DOI: 10.1002/mrm.1910060315">10.1002/mrm.1910060315">10.1002/mrm.1910060315.
[9]
LIANG D, CHENG J, KE Z, et al. Deep MRI reconstruction: unrolled optimization algorithms meet neural networks[EB/OL]. [2023-02-11]. https://arxiv.org/abs/1907.11711. DOI: 10.48550/arXiv.1907.11711">10.48550/arXiv.1907.11711">10.48550/arXiv.1907.11711.
[10]
KIM M, KIM H S, KIM H J, et al. Thin-slice pituitary MRI with deep learning-based reconstruction: diagnostic performance in a postoperative setting[J]. Radiology, 2021, 298(1): 114-122. DOI: 10.1148/radiol.2020200723">10.1148/radiol.2020200723">10.1148/radiol.2020200723.
[11]
QUARTERMAN P. Development of a high-speed MRI protocol with deep learning reconstruction method for brain imaging in a clinical setting[C/OL]. ISMRM, 2022 [2023-02-11]. https://archive.ismrm.org/2022/3967.html.
[12]
LEE D H, PARK J E, NAM Y K, et al. Deep learning-based thin-section MRI reconstruction improves tumour detection and delineation in pre- and post-treatment pituitary adenoma[J/OL]. Sci Rep, 2021, 11(1): 21302 [2023-02-11]. https://www.nature.com/articles/s41598-021-00558-2. DOI: 10.1038/s41598-021-00558-2">10.1038/s41598-021-00558-2">10.1038/s41598-021-00558-2.
[13]
CHOI K S, Figee M, Lebel R M, et al. Evaluation of the efficacy of a deep learning-based reconstruction in the connectomic deep brain stimulation[C/OL]. ISMRM, 2022 [2023-02-11]. https://archive.ismrm.org/2022/4779.html.
[14]
HAHN S, YI J, LEE H J, et al. Image quality and diagnostic performance of accelerated shoulder MRI with deep learning-based reconstruction[J]. AJR Am J Roentgenol, 2022, 218(3): 506-516. DOI: 10.2214/AJR.21.26577">10.2214/AJR.21.26577">10.2214/AJR.21.26577.
[15]
KOCH K M, SHERAFATI M, ARPINAR V E, et al. Analysis and evaluation of a deep learning reconstruction approach with denoising for orthopedic MRI[J/OL]. Radiol Artif Intell, 2021, 3(6): e200278 [2023-02-11]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8637471/. DOI: 10.1148/ryai.2021200278">10.1148/ryai.2021200278">10.1148/ryai.2021200278.
[16]
SUN S, TAN E T, MINTZ D N, et al. Evaluation of deep learning reconstructed high-resolution 3D lumbar spine MRI[J]. Eur Radiol, 2022, 32(9): 6167-6177. DOI: 10.1007/s00330-022-08708-4">10.1007/s00330-022-08708-4">10.1007/s00330-022-08708-4.
[17]
YASAKA K, TANISHIMA T, OHTAKE Y, et al. Deep learning reconstruction for 1.5 T cervical spine MRI: effect on interobserver agreement in the evaluation of degenerative changes[J]. Eur Radiol, 2022, 32(9): 6118-6125. DOI: 10.1007/s00330-022-08729-z">10.1007/s00330-022-08729-z">10.1007/s00330-022-08729-z.
[18]
ALMANSOUR H, HERRMANN J, GASSENMAIER S, et al. Deep learning reconstruction for accelerated spine MRI: prospective analysis of interchangeability[J/OL]. Radiology, 2023, 306(3): e212922 [2023-02-11]. https://pubs.rsna.org/doi/10.1148/radiol.212922?url_ver=Z39.88-2003&rfr_id=ori:rid:crossref.org&rfr_dat=cr_pub%20%200pubmed. DOI: 10.1148/radiol.212922">10.1148/radiol.212922">10.1148/radiol.212922.
[19]
PARK J C, PARK K J, PARK M Y, et al. Fast T2-weighted imaging with deep learning-based reconstruction: evaluation of image quality and diagnostic performance in patients undergoing radical prostatectomy[J]. J Magn Reson Imaging, 2022, 55(6): 1735-1744. DOI: 10.1002/jmri.27992">10.1002/jmri.27992">10.1002/jmri.27992.
[20]
UEDA T, OHNO Y, YAMAMOTO K, et al. Deep learning reconstruction of diffusion-weighted MRI improves image quality for prostatic imaging[J]. Radiology, 2022, 303(2): 373-381. DOI: 10.1148/radiol.204097">10.1148/radiol.204097">10.1148/radiol.204097.
[21]
MUSCOGIURI G, MARTINI C, GATTI M, et al. Feasibility of late gadolinium enhancement (LGE) in ischemic cardiomyopathy using 2D-multisegment LGE combined with artificial intelligence reconstruction deep learning noise reduction algorithm[J]. Int J Cardiol, 2021, 343: 164-170. DOI: 10.1016/j.ijcard.2021.09.012">10.1016/j.ijcard.2021.09.012">10.1016/j.ijcard.2021.09.012.
[22]
VAN DER VELDE N, HASSING H C, BAKKER B J, et al. Improvement of late gadolinium enhancement image quality using a deep learning-based reconstruction algorithm and its influence on myocardial scar quantification[J]. Eur Radiol, 2021, 31(6): 3846-3855. DOI: 10.1007/s00330-020-07461-w">10.1007/s00330-020-07461-w">10.1007/s00330-020-07461-w.
[23]
DELSO G, GARCÍA-POLO P, GORODEZKY M, et al. Improved myocardial T1 mapping accuracy with deep learning reconstruction of low flip angle MOLLI series[C/OL]. ISMRM, 2022 [2023-02-11]. https://archive.ismrm.org/2022/4779.html.

PREV Chinese expert consensus on peripheral nerve MRI
NEXT Application of deep learning reconstruction in improving the quality of neuromelanin magnetic resonance image
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn