Detection of Corpus Callosum Malformations in Pediatric Population Using the Discriminative Direction in Multiple Kernel Learning

  • Denis Peruzzo
  • Filippo Arrigoni
  • Fabio Triulzi
  • Cecilia Parazzini
  • Umberto Castellani
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8674)


In this paper we propose a Multiple Kernel Learning (MKL) classifier to detect malformations of the Corpus Callosum (CC) and apply it in a pediatric population. Furthermore, we extend the concept of discriminative direction to the linear MKL methods, implementing it in a single subject analysis framework.

The CC is characterized using different measures derived from Magnetic Resonance Imaging (MRI) data and the MKL approach is used to efficiently combine them. The discriminative direction analysis highlights those features that lead the classification for each given subject. In the case of a CC with malformation this means highlighting the abnormal characteristics of the CC that guide the diagnosis.

Experiments show that the method correctly identifies the malformative aspects of the CC. Moreover, it is able to identify dishomogeneus, localized or widespread abnormalities among the different features.

The proposed method is therefore suitable for supporting neuroradiologists in the decision-making process, providing them not only with a suggested diagnosis, but also with a description of the pathology.


magnetic resonance imaging multiple kernel learning brain imaging computer-aided diagnosis 


  1. 1.
    Bach, F.R., Lanckriet, G.R.G., Jordan, M.I.: Multiple kernel learning, conic duality, and the smo algorithm. In: Proceedings of the 21st International Conference on Machine Learning, ICML, pp. 41–48 (2004)Google Scholar
  2. 2.
    Castro, E., Martinez-Ramon, M., Pearlson, G., Sui, J., Calhoun, V.D.: Characterization of groups using composite kernels and multi-source fmri analysis data: application to schizophrenia. Neuroimage 58, 526–536 (2011)CrossRefGoogle Scholar
  3. 3.
    Cuingnet, R., Galunes, J.A., Chupin, M., Benali, H., Colliot, O., Alzheimers, T.: Disease Neuroimaging Initiative. Spatial and anatomical regularization of svm a general framework for neuroimaging data. IEEE Transaction on Medical Imaging 35(3), 682–696 (2013)Google Scholar
  4. 4.
    Golland, P., Girmson, W.E.L., Shenton, M.E., Kikinis, R.: Detection and analysis of statistical differencies in anatomical shape. Medical Image Analysis 9, 69–86 (2005)CrossRefGoogle Scholar
  5. 5.
    Herron, T.J., Kang, X., Woods, D.L.: Automated measurement of the human corpus callosum using mri. Frontiers in Neuroinformatics 6(25), 1–15 (2012)Google Scholar
  6. 6.
    Sato, J.R., Thomaz, C.E., Cardoso, E.F., Fujita, A., Martin, M.d.G., Amaro Jr., E.: Hyperplane navigation: a method to set individual scores in fmri group datasets. Neuroimage 42, 1473–1480 (2008)CrossRefGoogle Scholar
  7. 7.
    Xu, Z., Jin, R., Yang, H., King, I., Lyu, M.R.: Simple and efficient multiple kernel learning by group lasso. In: Proceedings of the 27th International Conference on Machine learning, ICML, pp. 1175–1182 (2010)Google Scholar
  8. 8.
    Zhou, L., Hartley, R., Wang, L., Lieby, P., Barnes, N.: Identifying anatomical shape difference by regularized discriminative direction. IEEE Transaction on Medical Imaging 28(6), 937–950 (2009)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Denis Peruzzo
    • 1
    • 2
  • Filippo Arrigoni
    • 1
  • Fabio Triulzi
    • 1
    • 3
  • Cecilia Parazzini
    • 4
  • Umberto Castellani
    • 2
  1. 1.Scientific Institute IRCCS “Eugenio Medea”Bosisio PariniItaly
  2. 2.University of VeronaVeronaItaly
  3. 3.Fondazione IRCCS “Ca’ Granda”Ospedale Maggiore PoliclinicoMilanItaly
  4. 4.Children Hospital “Vittore Buzzi”MilanItaly

Personalised recommendations