Advertisement

Automated Quantification of Enlarged Perivascular Spaces in Clinical Brain MRI Across Sites

  • Florian DubostEmail author
  • Max Dünnwald
  • Denver Huff
  • Vincent Scheumann
  • Frank Schreiber
  • Meike Vernooij
  • Wiro Niessen
  • Martin Skalej
  • Stefanie Schreiber
  • Steffen Oeltze-Jafra
  • Marleen de BruijneEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11796)

Abstract

Enlarged perivascular spaces (PVS) are structural brain changes visible in MRI, and are a marker of cerebral small vessel disease. Most studies use time-consuming and subjective visual scoring to assess these structures. Recently, automated methods to quantify enlarged perivascular spaces have been proposed. Most of these methods have been evaluated only in high resolution scans acquired in controlled research settings. We evaluate and compare two recently published automated methods for the quantification of enlarged perivascular spaces in 76 clinical scans acquired from 9 different scanners. Both methods are neural networks trained on high resolution research scans and are applied without fine-tuning the networks’ parameters. By adapting the preprocessing of clinical scans, regions of interest similar to those computed from research scans can be processed. The first method estimates only the number of PVS, while the second method estimates simultaneously also a high resolution attention map that can be used to detect and segment PVS. The Pearson correlations between visual and automated scores of enlarged perivascular spaces were higher with the second method. With this method, in the centrum semiovale, the correlation was similar to the inter-rater agreement, and also similar to the performance in high resolution research scans. Results were slightly lower than the inter-rater agreement for the hippocampi, and noticeably lower in the basal ganglia. By computing attention maps, we show that the neural networks focus on the enlarged perivascular spaces. Assessing the burden of said structures in the centrum semiovale with the automated scores reached a satisfying performance, could be implemented in the clinic and, e.g., help predict the bleeding risk related to cerebral amyloid angiopathy.

Keywords

Perivascular spaces Deep learning Clinical MRI 

Notes

Acknowledgements

This work received funding from the Netherlands Organisation for Health Research and Development (ZonMw - Project 104003005) and the federal state of Saxony-Anhalt, Germany (Project I 88).

References

  1. 1.
    Adams, H.H., et al.: Rating method for dilated Virchow-Robin spaces on magnetic resonance imaging. Stroke 44(6), 1732–1735 (2013)CrossRefGoogle Scholar
  2. 2.
    Boespflug, E.L., et al.: MR imaging-based multimodal autoidentification of perivascular spaces (mMAPS): automated morphologic segmentation of enlarged perivascular spaces at clinical field strength. Radiology 286(2), 632–642 (2017)CrossRefGoogle Scholar
  3. 3.
    Charidimou, A., et al.: MRI-visible perivascular spaces in cerebral amyloid angiopathy and hypertensive arteriopathy. Neurology 88(12), 1157–1164 (2017)CrossRefGoogle Scholar
  4. 4.
    Dubost, F., et al.: Enlarged perivascular spaces in brain MRI: automated quantification in four regions. NeuroImage 185, 534–544 (2019)CrossRefGoogle Scholar
  5. 5.
    Dubost, F., et al.: Weakly Supervised Object Detection with 2D and 3D Regression Neural Networks. arXiv preprint arXiv:1906.01891 (2019)
  6. 6.
    Dubost, F., et al.: 3D regression neural network for the quantification of enlarged perivascular spaces in brain MRI. Med. Image Anal. 51, 89–100 (2019)CrossRefGoogle Scholar
  7. 7.
    Ikram, M.A., et al.: The Rotterdam Study: 2018 update on objectives, design and main results. Eur. J. Epidemiol. 32(9), 807–850 (2017)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Potter, G.M., et al.: Cerebral perivascular spaces visible on magnetic resonance imaging: development of a qualitative rating scale and its observer reliability. Cerebrovasc. Dis. 39(3–4), 224–231 (2015)CrossRefGoogle Scholar
  9. 9.
    Smith, S.M., et al.: Advances in functional and structural MR image analysis and implementation as FSL. Neuroimage 23, S208–S219 (2004)CrossRefGoogle Scholar
  10. 10.
    Sudre, C.H., et al.: 3D multirater RCNN for multimodal multiclass detection and characterisation of extremely small objects. In: MIDL 2019 (2018)Google Scholar
  11. 11.
    van Wijnen, K.M., et al.: Automated lesion detection by regressing intensity-based distance with a neural network. In: MICCAI (2019)Google Scholar
  12. 12.
    Wilson, D., et al.: Cerebral microbleeds and intracranial haemorrhage risk in patients anticoagulated for atrial fibrillation after acute ischaemic stroke or transient ischaemic attack (CROMIS-2): a multicentre observational cohort study. Lancet Neurol. 17(6), 539–547 (2018)CrossRefGoogle Scholar
  13. 13.
    Zhang, J., Gao, Y., Park, S.H., Zong, X., Lin, W., Shen, D.: Segmentation of perivascular spaces using vascular features and structured random forest from 7T MR image. In: Wang, L., Adeli, E., Wang, Q., Shi, Y., Suk, H.-I. (eds.) MLMI 2016. LNCS, vol. 10019, pp. 61–68. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-47157-0_8CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Florian Dubost
    • 1
    Email author
  • Max Dünnwald
    • 2
    • 3
  • Denver Huff
    • 2
  • Vincent Scheumann
    • 2
  • Frank Schreiber
    • 2
  • Meike Vernooij
    • 1
    • 5
  • Wiro Niessen
    • 1
    • 6
  • Martin Skalej
    • 4
  • Stefanie Schreiber
    • 2
  • Steffen Oeltze-Jafra
    • 2
    • 7
  • Marleen de Bruijne
    • 1
    • 8
    Email author
  1. 1.Department of Radiology and Nuclear MedicineErasmus MCRotterdamThe Netherlands
  2. 2.Department of NeurologyOtto-von-Guericke University MagdeburgMagdeburgGermany
  3. 3.Faculty of Computer ScienceOtto-von-Guericke University MagdeburgMagdeburgGermany
  4. 4.Department of NeuroradiologyOtto-von-Guericke University MagdeburgMagdeburgGermany
  5. 5.Department of EpidemiologyErasmus MCRotterdamThe Netherlands
  6. 6.Department of Imaging Physics, Faculty of Applied ScienceTU DelftDelftThe Netherlands
  7. 7.Center for Behavioral Brain Sciences (CBBS)MagdeburgGermany
  8. 8.Department of Computer ScienceUniversity of CopenhagenCopenhagenDenmark

Personalised recommendations