Alzheimer’s disease early detection from sparse data using brain importance maps

Andreas Kodewitz 1 Sylvie Lelandais 1 Christophe Montagne 1 Vincent Vigneron 1
1 IBISC - Informatique, Biologie Intégrative et Systèmes Complexes
Abstract : Statistical methods are increasingly used in the analysis of FDG-PET images for the early diagnosis of Alzheimer’s disease. We will present a method to extract information about the location of metabolic changes induced by Alzheimer’s disease based on a machine learning approach that directly links features and brain areas to search for regions of interest (ROIs). This approach has the advantage over voxel-wise statistics to also consider the interactions between the features/voxels. We produce “maps” to visualize the most informative regions of the brain and compare the maps created by our approach with voxel-wise statistics. In classification experiments, using the extracted map, we achieved classification rates of up to 95.5%.
Keywords : Nuclear Imaging Brain Computer-aided diagnosis Machine learning Alzheimer’s disease
Document type :
Journal articles
Complete list of metadatas
https://hal.archives-ouvertes.fr/hal-01695694
Contributor : Frédéric Davesne <>
Submitted on : Monday, January 29, 2018 - 4:24:51 PM
Last modification on : Monday, October 28, 2019 - 10:50:22 AM

Identifiers

  • HAL Id : hal-01695694, version 1

Collections

UNIV-EVRY | IBISC | IBISC-SIBI

Citation

Andreas Kodewitz, Sylvie Lelandais, Christophe Montagne, Vincent Vigneron. Alzheimer’s disease early detection from sparse data using brain importance maps. Electronic Letters on Computer Vision and Image Analysis, Computer Vision Center Press, 2013, 12 (1), pp.42--56. ⟨hal-01695694⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

131

Contact

Informations

CCSD