Skip to main content

Multivariate Hippocampal Subfield Analysis of Local MRI Intensity and Volume: Application to Temporal Lobe Epilepsy

  • Conference paper

Part of the Lecture Notes in Computer Science book series (LNIP,volume 8674)

Abstract

We propose a multispectral MRI-based clinical decision support approach to carry out automated seizure focus lateralization in patients with temporal lobe epilepsy (TLE). Based on high-resolution T1- and T2-weighted MRI with hippocampal subfield segmentations, our approach samples MRI features along the medial sheet of each subfield to minimize partial volume effects. To establish correspondence of sampling points across subjects, we propagate a spherical harmonic parameterization derived from the hippocampal boundary along a Laplacian gradient field towards the medial sheet. Volume and intensity data sampled on the medial sheet are finally fed into a supervised classifier. Testing our approach in TLE patients in whom the seizure focus could not be lateralized using conventional MR volumetry, the proposed approach correctly lateralized all patients and outperformed classification performance based on global subfield volumes or mean T2-intensity (100% vs. 68%). Moreover, statistical group-level comparisons revealed patterns of subfield abnormalities that were not evident in the global measurements and that largely agree with known histopathological changes.

Keywords

  • multispectral MRI
  • computerized clinical decision support system
  • hippocampal subfield analysis
  • epilepsy

References

  1. Bernasconi, A., Bernasconi, N., Caramanos, Z., Reutens, D.C., Andermann, F., Dubeau, F., Tampieri, D., Pike, B.G., Arnold, D.L.: T2 relaxometry can lateralize mesial temporal lobe epilepsy in patients with normal MRI. Neuroimage 12, 739–746 (2000)

    CrossRef  Google Scholar 

  2. Blumcke, I., Coras, R., Miyata, H., Ozkara, C.: Defining clinico-neuropathological subtypes of mesial temporal lobe epilepsy with hippocampal sclerosis. Brain Pathol. 22, 402–411 (2012)

    CrossRef  Google Scholar 

  3. Bouix, S., Pruessner, J.C., Louis Collins, D., Siddiqi, K.: Hippocampal shape analysis using medial surfaces. NeuroImage 25, 1077–1089 (2005)

    CrossRef  MATH  Google Scholar 

  4. Naf, M., Szekely, G., Kikinis, R., Shenton, M.E., Kubler, O.: 3D Voronoi skeletons and their usage for the characterization and recognition of SD organ shape. Computer Vision and Image Understanding 66, 147–161 (1997)

    CrossRef  Google Scholar 

  5. Styner, M., Oguz, I., Xu, S., Brechbühler, C., Pantazis, D., Gerig, G.: Statistical Shape Analysis of Brain Structures using SPHARM-PDM. In: MICCAI Opensource Workshop (2006)

    Google Scholar 

  6. Jones, S.E., Buchbinder, B.R., Aharon, I.: Three-dimensional mapping of cortical thickness using Laplace’s equation. Hum. Brain Mapp. 11, 12–32 (2000)

    CrossRef  Google Scholar 

  7. Lagarias, J.C., Reeds, J.A., Wright, M.H., Wright, P.E.: Convergence properties of the Nelder-Mead simplex method in low dimensions. SIOPT 9, 112–147 (1998)

    MathSciNet  CrossRef  MATH  Google Scholar 

  8. Collins, D.L., Zijdenbos, A.P., Baaré, W.F.C., Evans, A.C.: ANIMAL+INSECT: Improved cortical structure segmentation. In: Kuba, A., Sámal, M., Todd-Pokropek, A. (eds.) IPMI 1999. LNCS, vol. 1613, pp. 210–223. Springer, Heidelberg (1999)

    CrossRef  Google Scholar 

  9. 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, 87–97 (1998)

    CrossRef  Google Scholar 

  10. Fonov, V., Evans, A.C., Botteron, K., Almli, C.R., McKinstry, R.C., Collins, D.L.: Unbiased average age-appropriate atlases for pediatric studies. Neuroimage 54, 313–327 (2011)

    CrossRef  Google Scholar 

  11. Kulaga-Yoskovitz, J., Bernasconi, N.: Hippocampal subfield segmentation on submillimetric MRI at 3 tesla. Epilepsia 54, 275 (2013)

    Google Scholar 

  12. Benjamini, Y., Hochberg, Y.: Controlling the false discovery rate: a practical and powerful approach to multiple testing. J. Royal Stat. Soc. 57, 289–300 (1995)

    MathSciNet  Google Scholar 

  13. Cascino, G.D., Jack Jr., C.R., Parisi, J.E., Sharbrough, F.W., Hirschorn, K.A., Meyer, F.B., Marsh, W.R., O’Brien, P.C.: Magnetic resonance imaging-based volume studies in temporal lobe epilepsy: pathological correlations. Ann. Neurol. 30, 31–36 (1991)

    CrossRef  Google Scholar 

  14. Briellmann, R.S., Kalnins, R.M., Berkovic, S.F., Jackson, G.D.: Hippocampal pathology in refractory temporal lobe epilepsy: T2-weighted signal change reflects dentate gliosis. Neurology 58, 265–271 (2002)

    CrossRef  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2014 Springer International Publishing Switzerland

About this paper

Cite this paper

Kim, H., Bernhardt, B.C., Kulaga-Yoskovitz, J., Caldairou, B., Bernasconi, A., Bernasconi, N. (2014). Multivariate Hippocampal Subfield Analysis of Local MRI Intensity and Volume: Application to Temporal Lobe Epilepsy. In: Golland, P., Hata, N., Barillot, C., Hornegger, J., Howe, R. (eds) Medical Image Computing and Computer-Assisted Intervention – MICCAI 2014. MICCAI 2014. Lecture Notes in Computer Science, vol 8674. Springer, Cham. https://doi.org/10.1007/978-3-319-10470-6_22

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-10470-6_22

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-10469-0

  • Online ISBN: 978-3-319-10470-6

  • eBook Packages: Computer ScienceComputer Science (R0)