Early Alzheimer Disease Detection by Bag of Visual Words and Hybrid Fusion on Structural Brain MRI

Olfa Ben Ahmed (1) , Jenny Benois-Pineau (1) , Chokri Ben-Amar (2) , Michèle Allard (3) , Gwenaelle Catheline (3)

1 Image et Son
2 CEM Lab - ENIS - Département de Génie Électrique de Sfax [ENIS]
3 INCIA - Institut de Neurosciences cognitives et intégratives d'Aquitaine

In this paper, we tackle the problem of recognition of Alzheimer's disease (AD) in structural MRI images using visual similarity. AD yields visible changes in the brain structures. We aim to recognize patient category such as AD, or prodromal stage of the AD called Mild Cognitive impairment (MCI), or normal control subject (NC).We use visual local descriptors and the bag of words approach on the most involved regions in AD (Hippocampus and PosteriorCingulate Cortex ) in MRI images. The Content- Based Visual information retrieval (CBVIR)approach is then applied to recognize patient category. The contribution of the paper is in the fusion of visual signatures and of classification results obtained on characteristic brain regions.

Domaines: Multimédia [cs.MM]

Olfa Ben Ahmed, Jenny Benois-Pineau, Chokri Ben-Amar, Michèle Allard, Gwenaelle Catheline. Early Alzheimer Disease Detection by Bag of Visual Words and Hybrid Fusion on Structural Brain MRI. Content-Based Multimedia Indexing'2013, Jun 2013, Veszprêm, Hungary. pp.1 - 5. ⟨hal-00853766⟩