Improved Segmentation of the Intracranial and Ventricular Volumes in Populations with Cerebrovascular Lesions and Atrophy Using 3D CNNs

Abstract

Successful segmentation of the total intracranial vault (ICV) and ventricles is of critical importance when studying neurodegeneration through neuroimaging. We present iCVMapper and VentMapper, robust algorithms that use a convolutional neural network (CNN) to segment the ICV and ventricles from both single and multi-contrast MRI data. Our models were trained on a large dataset from two multi-site studies (N = 528 subjects for ICV, N = 501 for ventricular segmentation) consisting of older adults with varying degrees of cerebrovascular lesions and atrophy, which pose significant challenges for most segmentation approaches. The models were tested on 238 participants, including subjects with vascular cognitive impairment and high white matter hyperintensity burden. Two of the three test sets came from studies not used in the training dataset. We assessed our algorithms relative to four state-of-the-art ICV extraction methods (MONSTR, BET, Deep Extraction, FreeSurfer, DeepMedic), as well as two ventricular segmentation tools (FreeSurfer, DeepMedic). Our multi-contrast models outperformed other methods across many of the evaluation metrics, with average Dice coefficients of 0.98 and 0.96 for ICV and ventricular segmentation respectively. Both models were also the most time efficient, segmenting the structures in orders of magnitude faster than some of the other available methods. Our networks showed an increased accuracy with the use of a conditional random field (CRF) as a post-processing step. We further validated both segmentation models, highlighting their robustness to images with lower resolution and signal-to-noise ratio, compared to tested techniques. The pipeline and models are available at: https://icvmapp3r.readthedocs.io and https://ventmapp3r.readthedocs.io to enable further investigation of the roles of ICV and ventricles in relation to normal aging and neurodegeneration in large multi-site studies.

This is a preview of subscription content, access via your institution.

We’re sorry, something doesn't seem to be working properly.

Please try refreshing the page. If that doesn't work, please contact support so we can address the problem.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

References

  1. Apostolova, L. G., Green, A. E., Babakchanian, S., Hwang, K. S., Chou, Y.-Y., Toga, A. W., & Thompson, P. M. (2012). Hippocampal atrophy and ventricular enlargement in Normal aging, mild cognitive impairment (MCI), and Alzheimer Disease. Alzheimer Dis Assoc Disord, 26(1), 17–27.

    PubMed  PubMed Central  Article  Google Scholar 

  2. Aribisala, B. S., Valdés Hernández, M. C., Royle, N. A., Morris, Z., Maniega, S. M., Bastin, M. E., Deary, I. J., & Wardlaw, J. M. (2012). Brain atrophy associations with white matter lesions in the ageing brain: The Lothian birth cohort 1936. Eur Radiol, 23(4), 1084–1092.

    PubMed  Article  Google Scholar 

  3. Bigler, E. D., & Tate, D. F. (2001). Brain Volume, Intracranial Volume, and Dementia. Investig Radiol, 36(9), 539–546.

    CAS  Article  Google Scholar 

  4. Boccardi, M. (2003). The MRI pattern of frontal and temporal brain atrophy in Fronto-temporal dementia. Neurobiol Aging, 24(1), 95–103.

    PubMed  Article  Google Scholar 

  5. Breteler, M. M., van Amerongen, N. M., van Swieten, J. C., Claus, J. J., Grobbee, D. E., van Gijn, J., Hofman, A., & van Harskamp, F. (1994). Cognitive correlates of ventricular enlargement and cerebral white matter lesions on magnetic resonance imaging. The Rotterdam study. Stroke, 25(6), 1109–1115.

    CAS  PubMed  Article  Google Scholar 

  6. Burton, E. J., McKeith, I. G., Burn, D. J., David Williams, E., & O’Brien, J. T. (2004). Cerebral atrophy in Parkinson’s Disease with and without dementia: A comparison with Alzheimer's Disease, dementia with Lewy bodies and controls. Brain J Neurol, 127(Pt 4), 791–800.

    Article  Google Scholar 

  7. Carmichael, O. T., Kuller, L. H., Lopez, O. L., Thompson, P. M., Dutton, R. A., Lu, A., & Sharon E. Lee, et al. (2007). Cerebral ventricular changes associated with transitions between Normal cognitive function, mild cognitive impairment, and dementia. Alzheimer Dis Assoc Disord, 21(1), 14–24.

    PubMed  PubMed Central  Article  Google Scholar 

  8. Chou, Y.-Y., Leporé, N., Avedissian, C., Madsen, S. K., Parikshak, N., Xue, H., & Leslie M. Shaw, et al. (2009). Mapping correlations between ventricular expansion and CSF amyloid and tau biomarkers in 240 subjects with Alzheimer’s Disease, mild cognitive impairment and elderly controls. NeuroImage, 46(2), 394–410.

    PubMed  PubMed Central  Article  Google Scholar 

  9. Chou, Y.-Y., Leporé, N., Saharan, P., Madsen, S. K., Xue, H., Jack, C. R., & Leslie M. Shaw, et al. (2010). Ventricular maps in 804 ADNI subjects: Correlations with CSF biomarkers and clinical decline. Neurobiol Aging, 31(8), 1386–1400.

    PubMed  PubMed Central  Article  Google Scholar 

  10. Çiçek, Ö., Abdulkadir, A., Lienkamp, S.S., Brox, T., and Ronneberger, O., (2016). 3D U-net: Learning dense volumetric segmentation from sparse annotation. In Lecture Notes in Computer Science, 424–432.

  11. Dice, L. R. (1945). Measures of the amount of ecologic association between species. Ecology, 26(3), 297–302.

    Article  Google Scholar 

  12. Dijk, E.J. van, Prins, N.D., Vermeer, S.E., Koudstaaf, P.J., and Breteler, M.M.B.. (2002). Frequency of white matter lesions and silent lacunar infarcts. In Ageing and Dementia Current and Future Concepts, 25–39. Springer Vienna.

  13. Dong, C., Nabizadeh, N., Caunca, M., Cheung, Y. K., Rundek, T., Elkind, M. S. V., DeCarli, C., Sacco, R. L., Stern, Y., & Wright, C. B. (2015). Cognitive correlates of white matter lesion load and brain atrophy: The northern Manhattan study. Neurology, 85(5), 441–449.

    PubMed  PubMed Central  Article  Google Scholar 

  14. Driscoll, I., Davatzikos, C., An, Y., Wu, X., Shen, D., Kraut, M., & Resnick, S. M. (2009). Longitudinal pattern of regional brain volume change differentiates Normal Aging from MCI. Neurology, 72(22), 1906–1913.

    CAS  PubMed  PubMed Central  Article  Google Scholar 

  15. Fennema-Notestine, C., Burak Ozyurt, I., Clark, C. P., Morris, S., Bischoff-Grethe, A., Bondi, M. W., & Terry L. Jernigan, et al. (2006). Quantitative evaluation of automated skull-stripping methods applied to contemporary and legacy images: Effects of diagnosis, Bias correction, and slice location. Hum Brain Mapp, 27(2), 99–113.

    PubMed  Article  Google Scholar 

  16. Fischl, B., Salat, D. H., Busa, E., Albert, M., Dieterich, M., Haselgrove, C., van der Kouwe, A., Killiany, R., Kennedy, D., Klaveness, S., Montillo, A., Makris, N., Rosen, B., & Dale, A. M. (2002). Whole brain segmentation: Automated labeling of neuroanatomical structures in the human brain. Neuron, 33(3), 341–355.

    CAS  PubMed  Article  Google Scholar 

  17. Fischl, B., Sereno, M.I., and Dale, A.M.. (1999). Cortical surface-based analysis. NeuroImage. https://doi.org/10.1006/nimg.1998.0396.

  18. Goubran, M., Ntiri, E.E., Akhavein, H., Holmes, M., Nestor, S., Ramirez, J., Adamo, S., et al. (2019). Hippocampal segmentation for brains with extensive atrophy using three-dimensional convolutional neural networks. Human Brain Mapping. https://doi.org/10.1002/hbm.24811.

  19. He, K., Zhang, X., Ren, S., and Sun, J., (2016). Deep Residual Learning for Image Recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770–78.

  20. Huo, Y., Asman, A. J., Plassard, A. J., & Landman, B. A. (2017). Simultaneous Total intracranial volume and posterior Fossa volume estimation using multi-atlas label fusion. Hum Brain Mapp, 38(2), 599–616.

    PubMed  Article  Google Scholar 

  21. Ioffe, S., and Szegedy, C., (2015). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. arXiv [cs.LG]. arXiv. http://arxiv.org/abs/1502.03167.

  22. Ivan, C. S., Seshadri, S., Beiser, A., Rhoda, A., Kase, C. S., Kelly-Hayes, M., & Wolf, P. A. (2004). Dementia after stroke: The Framingham study. Stroke, 35(6), 1264–1268.

    PubMed  Article  Google Scholar 

  23. Jaccard, P. (1912). The distribution of the Flora in the Alpine zone. 1. The New Phytologist, 11(2), 37–50.

    Article  Google Scholar 

  24. Jenkins, R., Fox, N. C., Rossor, A. M., Harvey, R. J., & Rossor, M. N. (2000). Intracranial volume and Alzheimer Disease: Evidence against the cerebral reserve hypothesis. Arch Neurol, 57(2), 220–224.

    CAS  PubMed  Article  Google Scholar 

  25. Kamnitsas, K., Liang, C., Ledig, C., Rueckert, D., & Glocker, B. (2015). Multi-scale 3D convolutional neural networks for lesion segmentation in brain MRI. Ischemic Stroke Lesion Segmentation, 13, 46.

    Google Scholar 

  26. Kamnitsas, K., Ledig, C., Newcombe, V. F. J., Simpson, J. P., Kane, A. D., Menon, D. K., Rueckert, D., & Glocker, B. (2017). Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. Med Image Anal, 36(February), 61–78.

    PubMed  Article  Google Scholar 

  27. Kayalibay, Baris, Grady Jensen, and Patrick van der Smagt. 2017. CNN-Based Segmentation of Medical Imaging Data. arXiv [cs.CV]. arXiv. http://arxiv.org/abs/1701.03056.

  28. Kingma, D.P., and Ba, J., (2014). Adam: A Method for Stochastic Optimization. arXiv [cs.LG]. arXiv. http://arxiv.org/abs/1412.6980.

  29. Kleesiek, J., Urban, G., Hubert, A., Schwarz, D., Maier-Hein, K., Bendszus, M., & Biller, A. (2016). Deep MRI brain extraction: A 3D convolutional neural network for skull stripping. NeuroImage, 129(April), 460–469.

    PubMed  Article  Google Scholar 

  30. Kraemer, M., Schormann, T., and Hagemann, G.. (2004). Delayed shrinkage of the brain after ischemic stroke: Preliminary observations with voxel-guided Morphometry. Journal of. https://onlinelibrary.wiley.com/doi/abs/10.1111/j.1552-6569.2004.tb00249.x.

  31. Krähenbühl, P., and Koltun, V., (2011). Efficient inference in fully connected CRFs with Gaussian edge potentials. In Advances in Neural Information Processing Systems 24, edited by J. Shawe-Taylor, R. S. Zemel, P. L. Bartlett, F. Pereira, and K. Q. Weinberger, 109–17. Curran Associates, Inc.

  32. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017). ImageNet classification with deep convolutional neural networks. Commun ACM, 60(6), 84–90.

    Article  Google Scholar 

  33. Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proc IEEE, 86(11), 2278–2324.

    Article  Google Scholar 

  34. van Loenhoud, A. C., Groot, C., Vogel, J. W., van der Flier, W. M., & Ossenkoppele, R. (2018). Is Intracranial Volume a Suitable Proxy for Brain Reserve? Alzheimers Res Ther, 10(1), 91.

    PubMed  PubMed Central  Article  Google Scholar 

  35. Madsen, S.K., Gutman, B.A., Joshi, S.H., Toga, A.W., Jack Jr, C.R., Weiner, M.W., Thompson, P.M., and Alzheimer’s Disease Neuroimaging Initiative (ADNI). (2015). Mapping ventricular expansion onto cortical gray matter in older adults. Neurobiology of Aging 36 Suppl 1 (January): S32–41.

  36. Mathalon, D. H., Sullivan, E. V., Rawles, J. M., & Pfefferbaum, A. (1993). Correction for head size in brain-imaging measurements. Psychiatry Res, 50(2), 121–139.

    CAS  PubMed  Article  Google Scholar 

  37. Milletari, F., Navab, N., and Ahmadi, S., (2016). V-net: Fully convolutional neural networks for volumetric medical image segmentation. In 2016 Fourth International Conference on 3D Vision (3DV), 565–71.

  38. Nestor, S. M., Rupsingh, R., Borrie, M., Smith, M., Accomazzi, V., Wells, J. L., Fogarty, J., Bartha, R., & Initiative, A.’s. D. N. (2008). Ventricular enlargement as a possible measure of Alzheimer’s Disease progression validated using the Alzheimer's Disease Neuroimaging Initiative database. Brain J Neurol, 131(Pt 9), 2443–2454.

    Article  Google Scholar 

  39. Paschali, M., Conjeti, S., Navarro, F., and Navab, N., (2018). Generalizability vs. Robustness: Investigating Medical Imaging Networks Using Adversarial Examples. Medical Image Computing and Computer Assisted Intervention – MICCAI 2018. https://doi.org/10.1007/978-3-030-00928-1_56.

  40. Pearson, K., & Galton, F. (1895). VII. Note on regression and inheritance in the case of two parents. Proc R Soc Lond, 58(347-352), 240–242.

    Article  Google Scholar 

  41. Ramirez, J., Gibson, E., Quddus, A., Lobaugh, N. J., Feinstein, A., Levine, B., Scott, C. J. M., Levy-Cooperman, N., Gao, F. Q., & Black, S. E. (2011). Lesion explorer: A comprehensive segmentation and Parcellation package to obtain regional Volumetrics for subcortical Hyperintensities and intracranial tissue. NeuroImage, 54(2), 963–973.

    CAS  PubMed  Article  Google Scholar 

  42. Ramirez, J., Scott, C.J.M., McNeely, A.A., Berezuk, C., Gao, F., Szilagyi, G.M., and Black, S.E., (2014). Lesion Explorer: A Video-Guided, Standardized Protocol for Accurate and Reliable MRI-Derived Volumetrics in Alzheimer’s Disease and Normal Elderly. Journal of Visualized Experiments: JoVE, no. 86 (April). https://doi.org/10.3791/50887.

  43. Ronneberger, O., Fischer, P., and Brox, T., (2015). U-net: Convolutional networks for biomedical image segmentation. In Lecture Notes in Computer Science, 234–41.

  44. Ross, D. E., Ochs, A. L., DeSmit, M. E., Seabaugh, J. M., Havranek, M. D., & for the Alzheimer’s Disease Neuroimaging Initiative. (2015). Man versus machine part 2: Comparison of radiologists’ interpretations and NeuroQuant measures of brain asymmetry and progressive atrophy in patients with traumatic brain injury. The Journal of Neuropsychiatry and Clinical Neurosciences, 27(2), 147–152.

    PubMed  Article  Google Scholar 

  45. Roy, S., Butman, J. A., Pham, D. L., & Initiative, A. D. N. (2017). Robust skull stripping using multiple MR image contrasts insensitive to pathology. NeuroImage, 146(February), 132–147.

    PubMed  Article  Google Scholar 

  46. Smith, E. E., O’Donnell, M., Dagenais, G., Lear, S. A., Wielgosz, A., Sharma, M., Poirier, P., et al. (2015). Early cerebral small vessel Disease and brain volume, cognition, and gait. Ann Neurol, 77(2), 251–261.

    PubMed  PubMed Central  Article  Google Scholar 

  47. Smith, S. M., De Stefano, N., Jenkinson, M., & Matthews, P. M. (2001). Normalized accurate measurement of longitudinal brain change. J Comput Assist Tomogr, 25(3), 466–475.

    CAS  PubMed  Article  Google Scholar 

  48. Smith, S. M. (2002). Fast robust automated brain extraction. Hum Brain Mapp, 17(3), 143–155.

    PubMed  PubMed Central  Article  Google Scholar 

  49. Staffaroni, A. M., Elahi, F. M., McDermott, D., Marton, K., Karageorgiou, E., Sacco, S., Paoletti, M., et al. (2017). Neuroimaging in Dementia. Semin Neurol, 37(5), 510–537.

    PubMed  PubMed Central  Article  Google Scholar 

  50. Stebbins, G. T., Nyenhuis, D. L., Wang, C., Cox, J. L., Freels, S., Bangen, K., & Leyla deToledo-Morrell, et al. (2008). Gray matter atrophy in patients with ischemic stroke with cognitive impairment. Stroke, 39(3), 785–793.

    PubMed  Article  Google Scholar 

  51. Swartz, R. H., Stuss, D. T., Gao, F., & Black, S. E. (2008). Independent cognitive effects of atrophy and diffuse subcortical and Thalamico-cortical cerebrovascular Disease in dementia. Stroke, 39(3), 822–830.

    PubMed  Article  Google Scholar 

  52. Tajbakhsh, N., Shin, J. Y., Gurudu, S. R., Todd Hurst, R., Kendall, C. B., Gotway, M. B., & Liang, J. (2016). Convolutional neural networks for medical image analysis: Full training or fine tuning? IEEE Trans Med Imaging, 35(5), 1299–1312.

    PubMed  Article  Google Scholar 

  53. Thompson, P. M., Hayashi, K. M., De Zubicaray, G. I., Janke, A. L., Rose, S. E., Semple, J., & Michael S. Hong, et al. (2004). Mapping hippocampal and ventricular change in Alzheimer Disease. NeuroImage, 22(4), 1754–1766.

    PubMed  Article  Google Scholar 

  54. Tustison, N. J., Avants, B. B., Cook, P. A., Zheng, Y., Egan, A., Yushkevich, P. A., & Gee, J. C. (2010). N4ITK: Improved N3 Bias Correction. IEEE Transactions on Medical Imaging, 29(6), 1310–1320.

    PubMed  PubMed Central  Article  Google Scholar 

  55. Ulyanov, D., Vedaldi, A., and Lempitsky, V., (2016). Instance Normalization: The Missing Ingredient for Fast Stylization. arXiv [cs.CV]. arXiv. http://arxiv.org/abs/1607.08022.

  56. Whitwell, J. L., Boeve, B. F., Weigand, S. D., Senjem, M. L., Gunter, J. L., Baker, M. C., DeJesus-Hernandez, M., Knopman, D. S., Wszolek, Z. K., Petersen, R. C., Rademakers, R., Jack Jr., C. R., & Josephs, K. A. (2015). Brain atrophy over time in genetic and sporadic Frontotemporal dementia: A study of 198 serial magnetic resonance images. European Journal of Neurology: The Official Journal of the European Federation of Neurological Societies, 22(5), 745–752.

    CAS  Article  Google Scholar 

  57. Wolf, H., Hensel, A., Kruggel, F., Riedel-Heller, S. G., Arendt, T., Wahlund, L.-O., & Gertz, H.-J. (2004). Structural correlates of mild cognitive impairment. Neurobiol Aging, 25(7), 913–924.

    PubMed  Article  Google Scholar 

  58. Yang, X., Tan, M. Z., & Qiu, A. (2012). CSF and brain structural imaging markers of the Alzheimer’s pathological cascade. PLoS One, 7(12), e47406.

    CAS  PubMed  PubMed Central  Article  Google Scholar 

  59. Yu, F., and V. Koltun. (2015). “Multi-Scale Context Aggregation by Dilated Convolutions.” arXiv Preprint arXiv:1511.07122. http://arxiv.org/abs/1511.07122.

  60. Yushkevich, P. A., Piven, J., Hazlett, H. C., Smith, R. G., Ho, S., Gee, J. C., & Gerig, G. (2006). User-guided 3D active contour segmentation of anatomical structures: Significantly improved efficiency and reliability. NeuroImage, 31(3), 1116–1128.

    PubMed  Article  Google Scholar 

Download references

Acknowledgments

We are grateful for the support of the Medical Imaging Trial Network of Canada (MITNEC) Grant #NCT02330510, and the following site Principal investigators: Christian Bocti, Michael Borrie, Howard Chertkow, Richard Frayne, Robin Hsiung, Robert Laforce, Jr., Michael D. Noseworthy, Frank S. Prato, Demetrios J. Sahlas, Eric E. Smith, Vesna Sossi, Alex Thiel, Jean-Paul Soucy, and Jean-Claude Tardif. We are also grateful for the support of the Canadian Atherosclerosis Imaging Network (CAIN) (http://www.canadianimagingnetwork.org/), and the following investigators: Therese Heinonen, Rob Beanlands, David Spence, Philippe L’Allier, Brian Rutt, Aaron Fenster, Matthias Friedrich, Ben Chow, and Richard Frayne. This research was conducted with the support of the Ontario Brain Institute, an independent non-profit corporation, funded partially by the Ontario government. The opinions, results and conclusions are those of the authors and no endorsement by the Ontario Brain Institute is intended or should be inferred.

Data Accessibility

The developed algorithm and trained models (network weights) are publicly available at: https://icvmapp3r.readthedocs.io and https://ventmapp3r.readthedocs.io under the GNU General Public License v3.0. An example dataset is included for testing purposes. We have developed an easy-to-use pipeline with a GUI and thorough documentation for making it accessible to users without programming knowledge. 

Funding

This study was funded by the Canadian Institute for Health Research (CIHR) MOP Grant #13129, CIHR Foundation grant #159910, Ontario Brain Institute and the L.C Campbell Foundation. RHS is supported by a Heart and Stroke Clinician-Scientist Phase II Award. The work was also supported by the Medical Imaging Trial Network of Canada (MITNEC) Grant #NCT02330510. Matching funds were provided by participant hospital and research foundations, including the Baycrest Foundation, Bruyere Research Institute, Centre for Addiction and Mental Health Foundation, London Health Sciences Foundation, McMaster University Faculty of Health Sciences, Ottawa Brain and Mind Research Institute, Queen’s University Faculty of Health Sciences, St. Michael’s Hospital, Sunnybrook Health Sciences Centre Foundation, the Thunder Bay Regional Health Sciences Centre, University Health Network, the University of Ottawa Faculty of Medicine, and the Windsor/Essex County ALS Association. The Temerty Family Foundation provided the major infrastructure matching funds.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Maged Goubran.

Ethics declarations

Conflict of Interest

The authors declare that they have no conflicts of interest.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

ESM 1

(DOCX 2242 kb)

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Ntiri, E.E., Holmes, M.F., Forooshani, P.M. et al. Improved Segmentation of the Intracranial and Ventricular Volumes in Populations with Cerebrovascular Lesions and Atrophy Using 3D CNNs. Neuroinform (2021). https://doi.org/10.1007/s12021-021-09510-1

Download citation

Keywords

  • Total intracranial volume
  • Ventricles
  • Image segmentation
  • Deep learning
  • Vascular lesions
  • Brain atrophy