Multilevel Feature Representation of FDG-PET Brain Images for Diagnosing Alzheimer's Disease - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE Journal of Biomedical and Health Informatics Année : 2019

Multilevel Feature Representation of FDG-PET Brain Images for Diagnosing Alzheimer's Disease

Xiaoxi Pan
Mouloud Adel
GSM
Caroline Fossati
  • Fonction : Auteur
  • PersonId : 832172
GSM
Thierry Gaidon
  • Fonction : Auteur

Résumé

Using a single imaging modality to diagnose Alzheimer's Disease (AD) or Mild Cognitive Impairment (MCI) is a challenging task. FluoroDeoxyGlucose Positron Emission Tomography (FDG-PET) is an important and effective modality used for that purpose. In this paper, we develop a novel method by using single modality (FDG-PET) but multi-level feature, which considers both region properties and connectivities between regions to classify AD or MCI from Normal Control (NC). First, three levels of features are extracted: statistical, connectivity and graph-based features. Then the connectivity features are decomposed into 3 different sets of features according to a proposed similarity-driven ranking method, which can not only reduce the feature dimension but also increase the classifier's diversity. Last, after feeding the 3 levels of features to different classifiers, a new classifier selection strategy, maximum Mean squared Error (mMsE), is developed to select a pair of classifiers with high diversity. In order to do the majority voting, a decision-making scheme, a nested cross validation technique is applied to choose another classifier according to the accuracy. Experiments on Alzheimer's Disease Neuroimaging Initiative (ADNI) database show that the proposed method outperforms most FDG-PET-based classification algorithms, especially for classifying progressive MCI (pMCI) from stable MCI (sMCI).
Fichier principal
Vignette du fichier
IEEE_2018.pdf (1.13 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02479738 , version 1 (01-04-2020)

Identifiants

Citer

Xiaoxi Pan, Mouloud Adel, Caroline Fossati, Thierry Gaidon, Eric Guedj. Multilevel Feature Representation of FDG-PET Brain Images for Diagnosing Alzheimer's Disease. IEEE Journal of Biomedical and Health Informatics, 2019, 23 (4), pp.1499-1506. ⟨10.1109/JBHI.2018.2857217⟩. ⟨hal-02479738⟩
52 Consultations
243 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More