Deep Spectral-Based Shape Features for Alzheimer’s Disease Classification

  • Mahsa Shakeri
  • Herve Lombaert
  • Shashank Tripathi
  • Samuel Kadoury
  • for the Alzheimer’s Disease Neuroimaging Initiative
Conference paper

DOI: 10.1007/978-3-319-51237-2_2

Part of the Lecture Notes in Computer Science book series (LNCS, volume 10126)
Cite this paper as:
Shakeri M., Lombaert H., Tripathi S., Kadoury S., for the Alzheimer’s Disease Neuroimaging Initiative (2016) Deep Spectral-Based Shape Features for Alzheimer’s Disease Classification. In: Reuter M., Wachinger C., Lombaert H. (eds) Spectral and Shape Analysis in Medical Imaging. SeSAMI 2016. Lecture Notes in Computer Science, vol 10126. Springer, Cham

Abstract

Alzheimer’s disease (AD) and mild cognitive impairment (MCI) are the most prevalent neurodegenerative brain diseases in elderly population. Recent studies on medical imaging and biological data have shown morphological alterations of subcortical structures in patients with these pathologies. In this work, we take advantage of these structural deformations for classification purposes. First, triangulated surface meshes are extracted from segmented hippocampus structures in MRI and point-to-point correspondences are established among population of surfaces using a spectral matching method. Then, a deep learning variational auto-encoder is applied on the vertex coordinates of the mesh models to learn the low dimensional feature representation. A multi-layer perceptrons using softmax activation is trained simultaneously to classify Alzheimer’s patients from normal subjects. Experiments on ADNI dataset demonstrate the potential of the proposed method in classification of normal individuals from early MCI (EMCI), late MCI (LMCI), and AD subjects with classification rates outperforming standard SVM based approach.

Keywords

Classification Spectral matching Variational autoencoder Alzheimer’s disease 

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Mahsa Shakeri
    • 1
    • 2
  • Herve Lombaert
    • 3
  • Shashank Tripathi
    • 1
  • Samuel Kadoury
    • 1
    • 2
  • for the Alzheimer’s Disease Neuroimaging Initiative
  1. 1.MedicalPolytechnique MontrealMontrealCanada
  2. 2.CHU Sainte-Justine Research CenterMontrealCanada
  3. 3.Inria Sophia-AntipolisValbonneFrance

Personalised recommendations