Brain MRI morphological patterns extraction tool based on Extreme Learning Machine and majority vote classification

Maite Termenon, Manuel Grana, Alexandre Savio, Anton Akusok*, Yoan Miche, Kaj-Mikael Bjork, Amaury Lendasse

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review

12 Citations (Scopus)

Abstract

The aim of this paper is to build a tool that able to extract the regions from a brain magnetic resonance image that discriminate healthy controls from subjects with probable dementia of the Alzheimer type. We propose the use of an Extreme Learning Machine method to select the most discriminant regions and thereafter to perform the final classification according to a majority vote decision based strategy. We are selecting the optimal number of votes required to put a subject into the class "Alzheimer" by maximizing the global accuracy and minimizing the number of false positives. The discriminative regions selected in the case study are located in the hippocampus, amygdala, thalamus and putamen, among others. These locations are closely related with a Alzheimer disease according to the medical literature. (C) 2015 Elsevier B.V. All rights reserved.

Original languageEnglish
Pages (from-to)344-351
Number of pages8
JournalNeurocomputing
Volume174
DOIs
Publication statusPublished - 22 Jan 2016
MoE publication typeA1 Journal article-refereed

Keywords

  • ELM
  • MRI
  • Classification
  • COMPUTER-AIDED DIAGNOSIS
  • TENSOR IMAGING FEATURES
  • ALZHEIMERS-DISEASE
  • FEATURE-SELECTION
  • MODEL SELECTION
  • ATROPHY
  • SERIES

Cite this