Deep Learning Enables 60% Accelerated Volumetric Brain MRI While Preserving Quantitative Performance: A Prospective, Multicenter, Multireader Trial

References

1. 1.↵
   1. Radlak K,
   2. Malinski L,
   3. Smolka B

   . Deep learning-based switching filter for impulsive noise removal in color images. Sensors 2020;20:2782 doi:10.3390/s20102782

   CrossRef
2. 2.↵
   1. Tanenbaum LN,
   2. Bash S,
   3. Johnson B, et al

   . Deep learning reconstructed, 40% faster spine MR examinations match or exceed the quality of standard of care exams. In: Proceedings of the Annual Meeting of the Radiological Society of North America; November 29 to December 5, 2020; Virtual
3. 3.↵
   1. Tanenbaum LN,
   2. Bash S,
   3. Gibbs W, et al

   . CNN based deep learning enhances brain 3D FLAIR perceived quality, SNR and resolution at ∼30% less scan time. In: Proceedings of the Annual Meeting of the American Society of Neuroradiology, May 30 to June 4, 2020; Virtual
4. 4.↵
   1. Tian C,
   2. Xu Y,
   3. Li Z

   , et al. Attention-guided CNN for image denoising. Neural Netw 2020;124:117–29 doi:10.1016/j.neunet.2019.12.024 pmid:31991307

   CrossRefPubMed
5. 5.↵
   1. Zhang K,
   2. Zuo W,
   3. Chen Y, et al

   . Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising. IEEE Trans Image Process 2017;26:3142–55 doi:10.1109/TIP.2017.2662206 pmid:28166495

   CrossRefPubMed
6. 6.↵
   1. Lunderwold AS,
   2. Lunderwold A

   . An overview of deep learning in medical imaging focusing on MRI. Z Med Phys 2019;29:102–27 doi:10.1016/j.zemedi.2018.11.002 pmid:30553609

   CrossRefPubMed
7. 7.↵
   1. Chaudhari A,
   2. Zhongnan F,
   3. Lee J, et al

   . Deep learning super-resolution enables rapid simultaneous morphological and quantitative magnetic resonance imaging. In: Proceeding of Machine Learning for Medical Image Reconstruction Workshop at MICCA, Granada, Spain; September 16, 2018
8. 8.↵
   1. Antun V,
   2. Renna F,
   3. Poon C, et al

   . On instabilities of deep learning in image reconstruction and the potential costs of AI. Proc Natl Acad Sci U S A 2020;117:30088–95 doi:10.1073/pnas.1907377117 pmid:32393633

   Abstract/FREE Full Text
9. 9.↵
   1. Bash S

   . Eye on AI: enhancing neuroimaging with artificial intelligence. Appl Radiol 2020;49:20–21
10. 10.↵
    1. Bryant M

    . Eye on AI: the potential and reality of AI in clinical application. Appl Radiol 2020;49:10–11
11. 11.↵
    1. Tanenbaum LN,
    2. Bash S,
    3. Davis M

    . Appl Radiol (AR Connect Expert Discussions); AI: clinical applications. In: Proceedings of the Annual Meeting of the Radiological Society of North America, Chicago, Illinois; December 1–6, 2019
12. 12.↵
    1. Bryant M

    . Bringing AI and genetics together to support clinical decisions. Appl Radiol July 1, 2020. https://appliedradiology.com/communities/Artificial-Intelligence/bringing-ai-and-genetics-together-to-support-clinical-decisions. Accessed July 1, 2020
13. 13.↵
    1. Melendez JC,
    2. McCrank E

    . Anxiety-related reactions associated with magnetic resonance imaging examinations. JAMA 1993;270:745–47 doi:10.1001/jama.1993.03510060091039 pmid:8336378

    CrossRefPubMedWeb of Science
14. 14.↵
    1. Tanenbaum L

    . Quality, efficiency and survival with patient centric imaging. In: Proceedings of the 7th Snowmass 2019: Hot Topics in Radiology: Advanced Applications and Artificial Intelligence, Snowmass, Colorado; February 10–15, 2019
15. 15.↵
    1. Zaitsev M,
    2. Maclaren J,
    3. Herbst M

    . Motion artifacts in MRI: a complex problem with many partial solutions. J Magn Reson Imaging 2015;42:887–901 doi:10.1002/jmri.24850 pmid:25630632

    CrossRefPubMed
16. 16.↵
    1. Andre J,
    2. Bresnahan B,
    3. Mossa-Basha M, et al

    . Toward quantifying the prevalence, severity, and cost associated with patient motion during clinical MR examinations. J Am Coll Radiol 2015;12:689–95 doi:10.1016/j.jacr.2015.03.007 pmid:25963225

    CrossRefPubMed
17. 17.↵
    1. Bash S,
    2. Thomas M,
    3. Fung M

    , et al. K-space based deep learning reconstruction empowers 60-70% acceleration of MR imaging of the spine. In: Proceedings of the Annual Meeting of the Radiological Society of North America, Chicago, Illinois; December 1–6, 2019
18. 18.↵
    1. Tanenbaum LN,
    2. Bash S,
    3. Thomas M

    , et al. K-space based deep learning reconstruction empowers 50% acceleration of MR spine imaging: a prospective, multicenter, multireader trial. In: Proceedings of the European Congress of Radiology, February 26 to March 1, 2020; Virtual