Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Feb;17(2):315-327.
doi: 10.1007/s11548-021-02535-6. Epub 2021 Dec 3.

Anisotropic neural deblurring for MRI acceleration

Maya Mayberg  1 , Michael Green  2 , Mark Vasserman  2 , Dominique Raichman  2 , Eugenia Belenky  2 , Michael Wolf  2 , Shai Shrot  2 , Nahum Kiryati  3 , Eli Konen  2 , Arnaldo Mayer  2
Affiliations

Anisotropic neural deblurring for MRI acceleration

Maya Mayberg et al. Int J Comput Assist Radiol Surg. 2022 Feb.

Abstract

Purpose: MRI has become the tool of choice for brain imaging, providing unrivalled contrast between soft tissues, as well as a wealth of information about anatomy, function, and neurochemistry. Image quality, in terms of spatial resolution and noise, is strongly dependent on acquisition duration. A typical brain MRI scan may last several minutes, with total protocol duration often exceeding 30 minutes. Long scan duration leads to poor patient experience, long waiting time for appointments, and high costs. Therefore, shortening MRI scans is crucial. In this paper, we investigate the enhancement of low-resolution (LR) brain MRI scanning, to enable shorter acquisition times without compromising the diagnostic value of the images.

Methods: We propose a novel fully convolutional neural enhancement approach. It is optimized for accelerated LR MRI acquisitions obtained by reducing the acquisition matrix size only along phase encoding direction. The network is trained to transform the LR acquisitions into corresponding high-resolution (HR) counterparts in an end-to-end manner. In contrast to previous neural-based MRI enhancement algorithms, such as DAGAN, the LR images used for training are real acquisitions rather than smoothed, downsampled versions of the HR images.

Results: The proposed method is validated qualitatively and quantitatively for an acceleration factor of 4. Favourable comparison is demonstrated against the state-of-the-art DeblurGAN and DAGAN algorithms in terms of PSNR and SSIM scores. The result was further confirmed by an image quality rating experiment performed by four senior neuroradiologists.

Conclusions: The proposed method may become a valuable tool for scan time reduction in brain MRI. In continuation of this research, the validation should be extended to larger datasets acquired for different imaging protocols, and considering several MRI machines produced by different vendors.

Keywords: Convolutional neural networks (CNN); Deblurring; Deep learning; Fast MRI; K-space.

PubMed Disclaimer

References

    1. Armanious K, Jiang C, Fischer M, Küstner T, Hepp T, Nikolaou K, Gatidis S, Yang B (2020) Medgan: medical image translation using GANs. Comput Med Imaging Gr 79:101684 - DOI
    1. Blau Y, Mechrez R, Timofte R, Michaeli T, Zelnik-Manor L (2019)The 2018 PIRM challenge on perceptual image super-resolution. In: Proceedings of the ECCV 2018 Workshops, LNCS 11133, Springer
    1. Chaudhari AS, Fang Z, Kogan F, Wood J, Stevens KJ, Gibbons EK, Lee JH, Gold GE, Hargreaves BA (2018) Super-resolution musculoskeletal MRI using deep learning. Magn Reson Med: An Off J Int Soc Magn Reson Med 80(5):2139–2154
    1. Cohen JP, Luck M, Honari S (2018) Distribution matching losses can hallucinate features in medical image translation. In: Proceedings of the MICCAI 2018, LNCS 11070, pp. 529–536, Springer
    1. Dar SUH, Yurt M, Shahdloo M, Ildız ME, Çukur T (2018) Synergistic reconstruction and synthesis via generative adversarial networks for accelerated multi-contrast MRI. arXiv preprint arXiv:1805.10704

LinkOut - more resources