Improving the Quality of Synthetic FLAIR Images with Deep Learning Using a Conditional Generative Adversarial Network for Pixel-by-Pixel Image Translation

REFERENCES

1. 1.↵
   2. Bobman SA,
   3. Riederer SJ,
   4. Lee JN, et al

   . Cerebral magnetic resonance image synthesis. AJNR Am J Neuroradiol 1985;6:265–69 pmid:2984911

   Abstract/FREE Full Text
2. 2.↵
   2. Warntjes JB,
   3. Leinhard OD,
   4. West J, et al

   . Rapid magnetic resonance quantification on the brain: optimization for clinical usage. Magn Reson Med 2008;60:320–29 doi:10.1002/mrm.21635 pmid:18666127

   CrossRefPubMed
3. 3.↵
   2. Hagiwara A,
   3. Hori M,
   4. Cohen-Adad J, et al

   . Linearity, bias, intrascanner repeatability, and interscanner reproducibility of quantitative multidynamic multiecho sequence for rapid simultaneous relaxometry at 3 T: a validation study with a standardized phantom and healthy controls. Invest Radiol 2019;54:39–47 doi:10.1097/RLI.0000000000000510 pmid:30300164

   CrossRefPubMed
4. 4.↵
   2. Blystad I,
   3. Warntjes JB,
   4. Smedby O, et al

   . Synthetic MRI of the brain in a clinical setting. Acta Radiol 2012;53:1158–63 doi:10.1258/ar.2012.120195 pmid:23024181

   CrossRefPubMed
5. 5.↵
   2. Granberg T,
   3. Uppman M,
   4. Hashim F, et al

   . Clinical feasibility of synthetic MRI in multiple sclerosis: a diagnostic and volumetric validation study. AJNR Am J Neuroradiol 2016;37:1023–29 doi:10.3174/ajnr.A4665 pmid:26797137

   Abstract/FREE Full Text
6. 6.↵
   2. Tanenbaum LN,
   3. Tsiouris AJ,
   4. Johnson AN, et al

   . Synthetic MRI for clinical neuroimaging: results of the Magnetic Resonance Image Compilation (MAGiC) prospective, multicenter, multireader trial. AJNR Am J Neuroradiol 2017;38:1103–10 doi:10.3174/ajnr.A5227 pmid:28450439

   Abstract/FREE Full Text
7. 7.↵
   2. Hagiwara A,
   3. Hori M,
   4. Yokoyama K, et al

   . Synthetic MRI in the detection of multiple sclerosis plaques. AJNR Am J Neuroradiol 2017;38:257–63 doi:10.3174/ajnr.A5012 pmid:27932506

   Abstract/FREE Full Text
8. 8.↵
   2. Hagiwara A,
   3. Hori M,
   4. Yokoyama K, et al

   . Analysis of white matter damage in patients with multiple sclerosis via a novel in vivo magnetic resonance method for measuring myelin, axons, and g-ratio. AJNR Am J Neuroradiol 2017;38:1934–40 doi:10.3174/ajnr.A5312 pmid:28775058

   Abstract/FREE Full Text
9. 9.↵
   2. Andica C,
   3. Hagiwara A,
   4. Nakazawa M, et al

   . Synthetic MR imaging in the diagnosis of bacterial meningitis. Magn Reson Med Sci 2017;16:91–92 doi:10.2463/mrms.ci.2016-0082 pmid:28003620

   CrossRefPubMed
10. 10.↵
    2. Wallaert L,
    3. Hagiwara A,
    4. Andica C, et al

    . The advantage of synthetic MRI for the visualization of anterior temporal pole lesions on double inversion recovery (DIR), phase-sensitive inversion recovery (PSIR), and myelin images in a patient with CADASIL. Magn Reson Med Sci 2018;17:275–76 doi:10.2463/mrms.ci.2017-0110 pmid:29238005

    CrossRefPubMed
11. 11.↵
    2. Helmersson T

    . Evaluation of Synthetic MRI for Clinical Use [master's thesis]. Department of Medical and Health Sciences. Linköping: Linköping University; 2010. http://liu.diva-portal.org/smash/record.jsf?pid=diva2%3A389732&dswid=9594. Accessed August 30, 2018:71
12. 12.↵
    2. Yasaka K,
    3. Akai H,
    4. Kunimatsu A, et al

    . Deep learning with convolutional neural network in radiology. Jpn J Radiol 2018;36:257–72 doi:10.1007/s11604-018-0726-3 pmid:29498017

    CrossRefPubMed
13. 13.↵
    2. Nakao T,
    3. Hanaoka S,
    4. Nomura Y, et al

    . Deep neural network-based computer-assisted detection of cerebral aneurysms in MR angiography. J Magn Reson Imaging 2018;47:948–53 doi:10.1002/jmri.25842 pmid:28836310

    CrossRefPubMed
14. 14.↵
    2. Goodfellow I,
    3. Pouget-Abadie J,
    4. Mirza M, et al

    . Generative adversarial nets. In: Proceedings of Advances in Neural Information Processing Systems; 2014:2672–80
15. 15.↵
    2. Wolterink JM,
    3. Leiner T,
    4. Viergever MA, et al

    . Generative adversarial networks for noise reduction in low-dose CT. IEEE Trans Med Imaging 2017;36:2536–45 doi:10.1109/TMI.2017.2708987 pmid:28574346

    CrossRefPubMed
16. 16.↵
    2. Kim KH,
    3. Do WJ,
    4. Park SH

    . Improving resolution of MR images with an adversarial network incorporating images with different contrast. Med Phys 2018;45:3120–31 doi:10.1002/mp.12945 pmid:29729006

    CrossRefPubMed
17. 17.↵
    2. Isola P,
    3. Zhu J,
    4. Zhou T, et al

    . Image-to-image translation with conditional adversarial networks. arXiv:161107004 2017. http://adsabs.harvard.edu/abs/2016arXiv161107004I. Accessed August 13, 2018
18. 18.↵
    2. Polman CH,
    3. Reingold SC,
    4. Banwell B, et al

    . Diagnostic criteria for multiple sclerosis: 2010 revisions to the McDonald criteria. Ann Neurol 2011;69:292–302 doi:10.1002/ana.22366 pmid:21387374

    CrossRefPubMedWeb of Science
19. 19.↵
    2. Hagiwara A,
    3. Warntjes M,
    4. Hori M, et al

    . SyMRI of the brain: rapid quantification of relaxation rates and proton density, with synthetic MRI, automatic brain segmentation, and myelin measurement. Invest Radiol 2017;52:647–57 doi:10.1097/RLI.0000000000000365 pmid:28257339

    CrossRefPubMed
20. 20.↵
    2. Ambarki K,
    3. Lindqvist T,
    4. Wählin A, et al

    . Evaluation of automatic measurement of the intracranial volume based on quantitative MR imaging. AJNR Am J Neuroradiol 2012;33:1951–56 doi:10.3174/ajnr.A3067 pmid:22555574

    Abstract/FREE Full Text
21. 21.↵
    2. Clevert D,
    3. Unterthiner T,
    4. Hochreiter S

    . Fast and accurate deep network learning by exponential linear units (ELUs). arXiv:151107289 2015. http://adsabs.harvard.edu/abs/2015arXiv151107289C. Accessed October 5, 2018
22. 22.↵
    2. Kingma D,
    3. Ba J

    . Adam: a method for stochastic optimization. arXiv:14126980 2014. https://arxiv.org/abs/1412.6980. Accessed August 22, 2018
23. 23.↵
    2. Ronneberger O,
    3. Fischer P,
    4. Brox T

    . U-Net: convolutional networks for biomedical image segmentation. arXiv:150504597 2015. http://adsabs.harvard.edu/abs/2015arXiv150504597R. Accessed October 6, 2018
24. 24.↵
    2. Lin G,
    3. Khetan G,
    4. Fanti G, et al

    . PacGAN: the power of two samples in generative adversarial networks. arXiv:171204086 2017. https://arxiv.org/abs/1712.04086. Accessed August 23, 2018
25. 25.↵
    2. Salimans T,
    3. Goodfellow I,
    4. Zaremba W, et al

    . Improved techniques for training GANs. arXiv:160603498 2016. http://adsabs.harvard.edu/abs/2016arXiv160603498S. Accessed August 28, 2018
26. 26.↵
    2. Huszár F

    . How (not) to train your generative model: scheduled sampling, likelihood, adversary? arXiv:151105101 2015. http://adsabs.harvard.edu/abs/2015arXiv151105101H. Accessed August 28, 2018
27. 27.↵
    2. Arjovsky M,
    3. Bottou L

    . Towards principled methods for training generative adversarial networks. arXiv:170104862 2017. http://adsabs.harvard.edu/abs/2017arXiv170104862A. Accessed August 28, 2018
28. 28.↵
    2. Jenkinson M,
    3. Beckmann CF,
    4. Behrens TE, et al

    . FSL. Neuroimage 2012;62:782–90 doi:10.1016/j.neuroimage.2011.09.015 pmid:21979382

    CrossRefPubMedWeb of Science
29. 29.↵
    2. Wang Y,
    3. Yu B,
    4. Wang L, et al

    . 3D conditional generative adversarial networks for high-quality PET image estimation at low dose. Neuroimage 2018;174:550–62 doi:10.1016/j.neuroimage.2018.03.045 pmid:29571715

    CrossRefPubMed
30. 30.↵
    2. Egger C,
    3. Opfer R,
    4. Wang C, et al

    . MRI FLAIR lesion segmentation in multiple sclerosis: does automated segmentation hold up with manual annotation? Neuroimage Clin 2017;13:264–70 doi:10.1016/j.nicl.2016.11.020 pmid:28018853

    CrossRefPubMed
31. 31.↵
    2. Schmidt P,
    3. Gaser C,
    4. Arsic M, et al

    . An automated tool for detection of FLAIR-hyperintense white-matter lesions in multiple sclerosis. Neuroimage 2012;59:3774–83 doi:10.1016/j.neuroimage.2011.11.032 pmid:22119648

    CrossRefPubMed
32. 32.↵
    2. Maitra R,
    3. Riddles JJ

    . Synthetic magnetic resonance imaging revisited. IEEE Trans Med Imaging 2010;29:895–902 doi:10.1109/TMI.2009.2039487 pmid:20199923

    CrossRefPubMed
33. 33.↵
    2. Krauss W,
    3. Gunnarsson M,
    4. Andersson T, et al

    . Accuracy and reproducibility of a quantitative magnetic resonance imaging method for concurrent measurements of tissue relaxation times and proton density. Magn Reson Imaging 2015;33:584–91 doi:10.1016/j.mri.2015.02.013 pmid:25708264

    CrossRefPubMed
34. 34.↵
    2. Cohen O,
    3. Zhu B,
    4. Rosen MS

    . MR fingerprinting Deep RecOnstruction NEtwork (DRONE). Magn Reson Med 2018;80:885–94 doi:10.1002/mrm.27198 pmid:29624736

    CrossRefPubMed
35. 35.↵
    2. Welander P,
    3. Karlsson S,
    4. Eklund A

    . Generative adversarial networks for image-to-image translation on multi-contrast MR images: a comparison of CycleGAN and UNIT. arXiv:180607777 2018. https://arxiv.org/abs/1806.07777. Accessed August 28, 2018