Advertisement

Deep Learning with Synthetic Diffusion MRI Data for Free-Water Elimination in Glioblastoma Cases

  • Miguel Molina-RomeroEmail author
  • Benedikt Wiestler
  • Pedro A. Gómez
  • Marion I. Menzel
  • Bjoern H. Menze
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11072)

Abstract

Glioblastoma is the most common and aggressive brain tumor. In clinical practice, diffusion MRI (dMRI) enables tumor infiltration assessment, tumor recurrence prognosis, and identification of white-matter tracks close to the resection volume. However, the vasogenic edema (free-water) surrounding the tumor causes partial volume contamination, which induces a bias in the estimates of the diffusion properties and limits the clinical utility of dMRI.

We introduce a voxel-based deep learning method to map and correct free-water partial volume contamination in dMRI. Our model learns from synthetically generated data a non-parametric forward model that maps free-water partial volume contamination to volume fractions. This is independent of the diffusion protocol and can be used retrospectively. We show its benefits in glioblastoma cases: first, a gain of statistical power; second, quantification of free-water and tissue volume fractions; and third, correction of free-water contaminated diffusion metrics. Free-water elimination yields more relevant information from the available data.

Keywords

Glioblastoma Brain tumor DTI Deep learning Fractional anisotropy Free-water elimination Data harmonization 

Notes

Acknowledgments

The authors want to thank Dr. Ofer Pasternak for his support in the comparison of the methods. This work was supported by the TUM Institute of Advanced Study, funded by the German Excellence Initiative, and the European Commission (Grant Agreement Number 605162).

Supplementary material

473976_1_En_12_MOESM1_ESM.docx (247 kb)
Supplementary material 1 (docx 247 KB)

References

  1. 1.
    Field, A.S.: Diffusion imaging in brain tumors. In: Jones, D.K. (ed.) Diffusion MRI, Chap. 33, pp. 547–563. Oxford University Press, Oxford (2010)CrossRefGoogle Scholar
  2. 2.
    Bette, S., et al.: Local fractional anisotropy is reduced in areas with tumor recurrence in glioblastoma. Radiology 283(2), 499–507 (2017)CrossRefGoogle Scholar
  3. 3.
    Eaton-Rosen, Z., et al.: Beyond the resolution limit: diffusion parameter estimation in partial volume. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9902, pp. 605–612. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46726-9_70CrossRefGoogle Scholar
  4. 4.
    Metzler-Baddeley, C., et al.: How and how not to correct for CSF-contamination in diffusion MRI. Neuroimage 59(2), 1394–1403 (2012)CrossRefGoogle Scholar
  5. 5.
    Pierpaoli, C., Jones, D.K.: Removing CSF contamination in brain DT-MRIs by using a two-compartment tensor model. In: ISMRM, Kyoto, p. 1215 (2004)Google Scholar
  6. 6.
    Pasternak, O., et al.: Free water elimination and mapping from diffusion MRI. Magn. Reson. Med. 730, 717–730 (2009)CrossRefGoogle Scholar
  7. 7.
    Hoy, A.R., et al.: Optimization of a free water elimination two-compartment model for diffusion tensor imaging. Neuroimage 103, 323–333 (2014)CrossRefGoogle Scholar
  8. 8.
    Tanno, R., et al.: Bayesian image quality transfer with CNNs: exploring uncertainty in dMRI super-resolution. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10433, pp. 611–619. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-66182-7_70CrossRefGoogle Scholar
  9. 9.
    Alexander, D.C., et al.: Image quality transfer and applications in diffusion MRI. Neuroimage 152(March), 283–298 (2017)CrossRefGoogle Scholar
  10. 10.
    Molina-Romero, M., et al.: A diffusion model-free framework with echo time dependence for free-water elimination and brain tissue microstructure characterization. Magn. Reson. Med. 80, 2155–2172 (2018)CrossRefGoogle Scholar
  11. 11.
    Veraart, J., et al.: Denoising of diffusion MRI using random matrix theory. Neuroimage 142, 394–406 (2016)CrossRefGoogle Scholar
  12. 12.
    Chang, L., et al.: Restore: robust estimation of tensors by outlier rejection. Magn. Reson. Med. 53(5), 1088–1095 (2005)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Computer ScienceTechnische Universität MünchenMunichGermany
  2. 2.GE Healthcare Global Research OrganizationMunichGermany
  3. 3.Department of NeuroradiologyKlinikum rechts der Isar der Technische Universität MünchenMunichGermany

Personalised recommendations