2008 IEEE International Workshop on Imaging Systems and Techniques 2008
DOI: 10.1109/ist.2008.4659997
|View full text |Cite
|
Sign up to set email alerts
|

An automated supervised method for the diagnosis of Alzheimer’s disease based on fMRI data using weighted voting schemes

Abstract: We present an automated supervised method which assists in the diagnosis of Alzheimer's Disease (AD) using fMRI data. The method consists of five stages: a) preprocessing of fMRI data to remove motion and spatial noise artifacts, b) modeling of the data using Generalized Linear Models (GLM), c) feature extraction, d) feature selection and e) classification using majority and weighted voting schemes.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
2
0
2

Year Published

2010
2010
2018
2018

Publication Types

Select...
4
1
1

Relationship

0
6

Authors

Journals

citations
Cited by 7 publications
(4 citation statements)
references
References 24 publications
0
2
0
2
Order By: Relevance
“…Khazaee et al [134] developed an automatic classification system based on SVM and fMRI images, where an accuracy of 97.5% was achieved distinguishing AD from healthy people. Tripoliti et al have carried out several works [135][136][137] where an accuracy of 88% was achieved in the same two-class classification problem. Furthermore, they also distinguished elderly CTLs, patients with very mild AD and those with mild AD with 80.5% of accuracy and introducing a fourth class of healthy young people they achieved 87% of accuracy.…”
Section: Functional Mri (Fmri)mentioning
confidence: 99%
“…Khazaee et al [134] developed an automatic classification system based on SVM and fMRI images, where an accuracy of 97.5% was achieved distinguishing AD from healthy people. Tripoliti et al have carried out several works [135][136][137] where an accuracy of 88% was achieved in the same two-class classification problem. Furthermore, they also distinguished elderly CTLs, patients with very mild AD and those with mild AD with 80.5% of accuracy and introducing a fourth class of healthy young people they achieved 87% of accuracy.…”
Section: Functional Mri (Fmri)mentioning
confidence: 99%
“…While for predicting continuous outcomes, the random forest model will build regression trees [2] instead of classification trees, and then use model averaging techniques to combine the predictions from individual regression trees. This method has been shown to perform well in many classification and prediction scenarios[39, 40], including algorithmic approaches CSF[41], EEG[42] and fMRI [43, 44] findings. The random forest prediction model was performed using R package randomForest (V 4.5)[37], with all software default settings.…”
Section: Methodsmentioning
confidence: 99%
“…Στο βήμα της ταξινόμησης εξετάστηκαν δύο διαφορετικοί ταξινομητές: (α) ο αλγόριθμος των τυχαίων δασών [112,114,250] καθώς και κάποιες τροποποιήσεις αυτού [115,116,118,2510] και (β) οι μηχανές διανυσμάτων υποστήριξης [118,252].…”
Section: ταξινόμηση με χρήση των τυχαίων δασών και μηχανών διανυσμάτων υποστήριξηςunclassified
“…Στην παρούσα ενότητα παρουσιάζονται τροποποιήσεις του αλγορίθμου των τυχαίων δασών προκειμένου να επιτευχθεί ο παραπάνω στόχος (βελτίωση της απόδοσης του αλγορίθμου). Οι τροποποιήσεις παρεμβαίνουν είτε στον τρόπο κατασκευής των ταξινομητών, είτε στον τρόπο ψηφοφορίας, είτε και στα δύο [115][116][117][118]251] n είναι ο αριθμός των δειγμάτων εκπαίδευσης που ανήκουν στην κλάση i , .j n είναι ο αριθμός των δειγμάτων εκπαίδευσης με την j th τιμή για το δοθέν χαρακτηριστικό, nl είναι το πλήθος των δειγμάτων εκπαίδευσης και ij n είναι το πλήθος των δειγμάτων εκπαίδευσης που ανήκουν στην κλάση i με την j th τιμή για το δοθέν χαρακτηριστικό.…”
Section: ταξινόμηση με χρήση τροποποιήσεων του αλγορίθμου τυχαίων δασώνunclassified