A Zernike moment based method for classification of Alzheimer's disease from structural MRI

This paper proposed a method based on Zernike moments to classify the various stages of Alzheimer's Disease(AD) from structural MRIs. The proposed method is benefited from all three orthogonal directions of MRIs i.e. Axial, Sagittal and Coronal images. Three back-propagation algorithms had been...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2017 3rd International Conference on Pattern Recognition and Image Analysis (IPRIA) S. 38 - 43
Hauptverfasser: Shams-Baboli, Aref, Ezoji, Mehdi
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.04.2017
Schlagworte:
Alzheimer's disease
Artificial neural network
Artificial neural networks
Classification algorithms
Dementia
Feature extraction
magnetic resonance images
Magnetic resonance imaging
mild cognitive impairment
Training
Zernike moments
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This paper proposed a method based on Zernike moments to classify the various stages of Alzheimer's Disease(AD) from structural MRIs. The proposed method is benefited from all three orthogonal directions of MRIs i.e. Axial, Sagittal and Coronal images. Three back-propagation algorithms had been used to train the neural network with seven neurons in hidden layer to reach the best accuracy. We experimented this method with 232 MRIs from OASIS database. 70 percent of the subjects had been used for training and the other 30 percent was used to evaluate the trained network. We achieved accuracy of 86.46 percent in multiclass mode and 96.67 percent of accuracy in two class mode between HC and AD.
DOI:10.1109/PRIA.2017.7983061