Four-Dimensional ASL MR Angiography Phantoms with Noise Learned by Neural Styling

  • Renzo PhellanEmail author
  • Thomas Linder
  • Michael Helle
  • Thiago V. Spina
  • Alexandre Falcão
  • Nils D. Forkert
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11043)


Annotated datasets for evaluation and validation of medical image processing methods can be difficult and expensive to obtain. Alternatively, simulated datasets can be used, but adding realistic noise properties is especially challenging. This paper proposes using neural styling, a deep learning based algorithm, which can automatically learn noise patterns from real medical images and reproduce these patterns in the simulated datasets. In this work, the imaging modality to be simulated is four-dimensional arterial spin labeling magnetic resonance angiography (4D ASL MRA), a modality that includes information of the cerebrovascular geometry and blood flow. The cerebrovascular geometry used to create the simulated phantoms is obtained from segmentations of 3D time-of-flight (TOF) MRA images of healthy volunteers. Dynamic blood flow is simulated according to a mathematical model designed specifically to describe the signal generated by 4D ASL MRA series. Finally, noise is added by using neural styling to learn the noise patterns present in real 4D ASL MRA datasets. Qualitative evaluation of two simulated 4D ASL MRA datasets revealed high similarity of the blood flow dynamics and noise properties as compared to the corresponding real 4D ASL MRA datasets. These simulated phantoms, with realistic noise properties, can be useful for the development, optimization, and evaluation of image processing methods focused on segmentation and blood flow parameters estimation in 4D ASL MRA series.


Angiography Simulated phantoms Vascular segmentation Noise patterns Convolutional neural networks 



This work was supported by Natural Sciences and Engineering Research Council of Canada. Dr. Alexandre X. Falcão thanks CNPq 302970/2014-2 and FAPESP 2014/12236-1.


  1. 1.
    Robson, P.M., Dai, W., Shankaranarayanan, A., Rofsky, N.M., Alsop, D.C.: Time-resolved vessel-selective digital subtraction MR angiography of the cerebral vasculature with arterial spin labeling. Radiology 257(2), 507–515 (2010)CrossRefGoogle Scholar
  2. 2.
    Phellan, R., Lindner, T., Helle, M., Falcao, A., Forkert, N.D.: Automatic temporal segmentation of vessels of the brain using 4D ASL MRA images. IEEE Trans. Biomed. Eng. 65, 1486–1494 (2017)CrossRefGoogle Scholar
  3. 3.
    Hamarneh, G., Jassi, P.: Vascusynth: simulating vascular trees for generating volumetric image data with ground-truth segmentation and tree analysis. Comput. Med. Imaging Graph. 34(8), 605–616 (2010)CrossRefGoogle Scholar
  4. 4.
    Gatys, L.A., Ecker, A.S., Bethge, M.: A neural algorithm of artistic style (2015). arXiv preprint: arXiv:1508.06576
  5. 5.
    Kholmovski, E.G., Alexander, A.L., Parker, D.L.: Correction of slab boundary artifact using histogram matching. J. Magn. Reson. Imaging 15(5), 610–617 (2002)CrossRefGoogle Scholar
  6. 6.
    Sled, J.G., Zijdenbos, A.P., Evans, A.C.: A nonparametric method for automatic correction of intensity nonuniformity in MRI data. IEEE Trans. Med. Imaging 17(1), 87–97 (1998)CrossRefGoogle Scholar
  7. 7.
    Forkert, N., et al.: Automatic brain segmentation in Time-of-Flight MRA images. Methods Inf. Med. 48(5), 399–407 (2009)CrossRefGoogle Scholar
  8. 8.
    Forkert, N.D., et al.: 3D cerebrovascular segmentation combining fuzzy vessel enhancement and level-sets with anisotropic energy weights. Magn. Reson. Imaging 31(2), 262–271 (2013)CrossRefGoogle Scholar
  9. 9.
    Okell, T.W., Chappell, M.A., Schulz, U.G., Jezzard, P.: A kinetic model for vessel-encoded dynamic angiography with arterial spin labeling. Magn. Reson. Med. 68(3), 969–979 (2012)CrossRefGoogle Scholar
  10. 10.
    Falcão, A.X., Stolfi, J., de Alencar Lotufo, R.: The image foresting transform: theory, algorithms, and applications. IEEE Trans. Pattern Anal. Mach. Intell. 26(1), 19–29 (2004)CrossRefGoogle Scholar
  11. 11.
    MacDonald, M.E., Frayne, R.: Phase contrast MR imaging measurements of blood flow in healthy human cerebral vessel segments. Physiol. Measur. 36(7), 1517 (2015)CrossRefGoogle Scholar
  12. 12.
    Litjens, G., et al.: A survey on deep learning in medical image analysis. Med. Image Anal. 42, 60–88 (2017)CrossRefGoogle Scholar
  13. 13.
    Johnson, J.: Neural-style (2015).
  14. 14.
    Criminisi, A., Pérez, P., Toyama, K.: Region filling and object removal by exemplar-based image inpainting. IEEE Trans. Image Process. 13(9), 1200–1212 (2004)CrossRefGoogle Scholar
  15. 15.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition (2014). arXiv preprint: arXiv:1409.1556

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Renzo Phellan
    • 1
    Email author
  • Thomas Linder
    • 2
  • Michael Helle
    • 3
  • Thiago V. Spina
    • 4
  • Alexandre Falcão
    • 5
  • Nils D. Forkert
    • 1
  1. 1.Department of Radiology, Hotchkiss Brain Institute, and Biomedical Engineering Graduate ProgramUniversity of CalgaryCalgaryCanada
  2. 2.Clinic for Radiology and NeuroradiologyUniversity Medical Center Schleswig-HolsteinKielGermany
  3. 3.Philips Technologie GmbH, Innovative TechnologiesHamburgGermany
  4. 4.Brazilian Synchrotron Light LaboratoryBrazilian Center for Research in Energy and MaterialsCampinasBrazil
  5. 5.Laboratory of Image Data Science, Institute of ComputingUniversity of CampinasCampinasBrazil

Personalised recommendations