Hippocampus Subfield Segmentation Using a Patch-Based Boosted Ensemble of Autocontext Neural Networks

  • José V. ManjónEmail author
  • Pierrick Coupe
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10530)


The hippocampus is a brain structure that is involved in several cognitive functions such as memory and learning. It is a structure of great interest in the study of the healthy and diseased brain due to its relationship to several neurodegenerative pathologies. In this work, we propose a novel patch-based method that uses an ensemble of boosted neural networks to perform the hippocampus subfield segmentation on multimodal MRI. This new method minimizes both random and systematic errors using an overcomplete autocontext patch-based labeling using a novel boosting strategy. The proposed method works well on high resolution MRI but also on standard resolution images after superresolution. Finally, the proposed method was compared with a similar state-of-the-art methods showing better results in terms of both accuracy and efficiency.



This research was supported by the Spanish UPV2016-0099 grant from Universitat Politécnica de Valencia. This study has been also carried out with financial support from the French State, managed by the French National Research Agency (ANR) in the frame of the Investments for the future Program IdEx Bordeaux (ANR-10-IDEX-03-02, HL-MRI Project) and Cluster of excellence CPU and TRAIL (HR-DTI ANR-10-LABX-57).


  1. 1.
    Milner, B.: Psychological defects produced by temporal lobe excision. Res. Publ. Assoc. Res. Nerv. Ment. Dis. 36, 244–257 (1958)Google Scholar
  2. 2.
    Petersen, R., et al.: Memory and MRI-based hippocampal volumes in aging and AD. Neurology 54(3), 581–587 (2000)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Cendes, F., et al.: MRI volumetric measurement of amygdala and hippocampus in temporal lobe epilepsy. Neurology 43(4), 719–725 (1993)CrossRefGoogle Scholar
  4. 4.
    Altshuler, L.L., et al.: Amygdala enlargement in bipolar disorder and hippocampal reduction in schizophrenia: an MRI study demonstrating neuroanatomic specificity Arch. Gen. Psychiatry 55(7), 663 (1998)Google Scholar
  5. 5.
    Braak, H., Braak, E.: Neuropathological stageing of Alzheimer-related changes. Acta Neuropathol. 82(4), 239–259 (1991)CrossRefGoogle Scholar
  6. 6.
    Chupin, M., et al.: Fully automatic hippocampus segmentation and classification in Alzheimer’s disease and mild cognitive impairment applied on data from ADNI. Hippocampus 19(6), 579–587 (2009)CrossRefGoogle Scholar
  7. 7.
    Van Leemput, K., et al.: Automated segmentation of hippocampal subfields from ultra-high resolution in vivo MRI. Hippocampus 19(6), 549–557 (2009)CrossRefGoogle Scholar
  8. 8.
    Iglesias, J.E., et al.: A computational atlas of the hippocampal formation using ex vivo, ultra-high resolution MRI: application to adaptive segmentation of in vivo MRI. NeuroImage 115(15), 117–137 (2015)CrossRefGoogle Scholar
  9. 9.
    Chakravarty, M., et al.: Performing label-fusion-based segmentation using multiple automatically generated templates. Hum. Brain Mapp. 10(34), 2635–2654 (2013)CrossRefGoogle Scholar
  10. 10.
    Yushkevich, P.A., et al.: Automated volumetry and regional thickness analysis of hippocampal subfields and medial temporal cortical structures in mild cognitive impairment. Hum. Brain Mapp. 36(1), 258–287 (2015)CrossRefGoogle Scholar
  11. 11.
    Kulaga-Yoskovitz, J., Bernhardt, B.C., Hong, S., Mansi, T., Liang, K.E., van der Kouwe, A.J.W., Smallwood, J., Bernasconi, A., Bernasconi, N.: Multi-contrast submillimetric 3Tesla hippocampal subfield segmentation protocol and dataset. Sci Data 2, 150059 (2015)CrossRefGoogle Scholar
  12. 12.
    Serag, A., et al.: SEGMA: an automatic SEGMentation approach for human brain MRI using sliding window and random forests. Front Neuroinform. 11, 2 (2017)CrossRefGoogle Scholar
  13. 13.
    Manjón, J.V., et al.: HIST: hyperintensity segmentation tool. In: PatchMI workshop, MICCAI2016, Athens (2016)Google Scholar
  14. 14.
    Schapire, R.E.: The strength of weak learnability. Mach. Learn. 5(2), 197–227 (1990)Google Scholar
  15. 15.
    Manjón, J.V., et al.: Adaptive non-local means denoising of MR images with spatially varying noise levels. J Magn. Reson. Imaging 31, 192–203 (2010)CrossRefGoogle Scholar
  16. 16.
    Tustison, N.J., et al.: N4ITK: improved N3 bias correction. IEEE Trans. Med. Imaging 29(6), 1310–1320 (2010)CrossRefGoogle Scholar
  17. 17.
    Avants, B.B., et al.: Advanced normalization tools (ANTS). Insight J. (2009)Google Scholar
  18. 18.
    Nyúl, L.G., Udupa, J.K.: On standardizing the MR image intensity scale. Magn. Reson. Med. 42(6), 1072–1081 (1999)CrossRefGoogle Scholar
  19. 19.
    Coupé, P., et al.: Collaborative patch-based super-resolution for diffusion-weighted images. NeuroImage 83, 245–261 (2013)CrossRefGoogle Scholar
  20. 20.
    Caldairou, B., Bernhardt, B.C., Kulaga-Yoskovitz, J., Kim, H., Bernasconi, N., Bernasconi, A.: A surface patch-based segmentation method for hippocampal subfields. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016 Part II. LNCS, vol. 9901, pp. 379–387. Springer, Cham (2016). doi: 10.1007/978-3-319-46723-8_44 CrossRefGoogle Scholar
  21. 21.
    Romero, J.E., Coupe, P., Manjón, J.V.: High resolution hippocampus subfield segmentation using multispectral multiatlas patch-based label fusion. In: Wu, G., Coupé, P., Zhan, Y., Munsell, B.C., Rueckert, D. (eds.) Patch-MI 2016. LNCS, vol. 9993, pp. 117–124. Springer, Cham (2016). doi: 10.1007/978-3-319-47118-1_15 CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Instituto de Aplicaciones de Las Tecnologías de La Información Y de Las Comunicaciones Avanzadas (ITACA)Universitat Politècnica de ValènciaValenciaSpain
  2. 2.Univ. Bordeaux, LaBRI, UMR 5800, PICTURATalenceFrance
  3. 3.CNRS, LaBRI, UMR 5800, PICTURATalenceFrance

Personalised recommendations