Title :
Genetic algorithm-based PCA eigenvector selection and weighting for automated identification of dementia using FDG-PET imaging
Author :
Xia, Yong ; Wen, Lingfeng ; Eberl, Stefan ; Fulham, Michael ; Feng, Dagan
Author_Institution :
Biomedical and Multimedia Information Technology (BMIT) Research Group, School of Information, Technologies, University of Sydney, Australia
Abstract :
Parametric FDG-PET data offer the potential for an automated identification of the different dementia syndromes. Principal component analysis (PCA) can be used for feature extraction in FDG-PET. However, standard PCA is not always successful in delineating the features that have the best discrimination ability. We report a genetic algorithm-based method to identify an optimal combination of eigenvectors so that the resultant features are capable of successfully separating patients with suspected Alzheimer´s disease and frontotemporal dementia from normal controls. We compared our approach with standard PCA on a set of 210 clinical cases and improved the performance in separating the dementia types with an accuracy of 90.0% and a Kappa statistic of 0.849. There was very good agreement between the automated technique and the diagnosis given by clinicians.
Keywords :
Alzheimer´s disease; Artificial neural networks; Dementia; Eigenvalues and eigenfunctions; Genetics; Histograms; Positron emission tomography; Principal component analysis; Support vector machine classification; Support vector machines; Algorithms; Alzheimer Disease; Brain; Dementia; Diagnosis, Differential; Fluorodeoxyglucose F18; Humans; Image Enhancement; Image Interpretation, Computer-Assisted; Positron-Emission Tomography; Principal Component Analysis; Radiopharmaceuticals; Reproducibility of Results; Sensitivity and Specificity;
Conference_Titel :
Engineering in Medicine and Biology Society, 2008. EMBS 2008. 30th Annual International Conference of the IEEE
Conference_Location :
Vancouver, BC
Print_ISBN :
978-1-4244-1814-5
Electronic_ISBN :
1557-170X
DOI :
10.1109/IEMBS.2008.4650290