Neuroimaging data as 18F-FDG PET is widely used to assist the diagnosis of Alzheimer’s
disease (AD). Looking for regions with hypoperfusion/ hypometabolism, clinicians may predict or
corroborate the diagnosis of the patients. Modern computer aided diagnosis (CAD) systems based on
the statistical analysis of whole neuroimages are more accurate than classical systems based on quantifying
the uptake of some predefined regions of interests (ROIs). In addition, these new systems allow
determining new ROIs and take advantage of the huge amount of information comprised in neuroimaging
data. A major branch of modern CAD systems for AD is based on multivariate techniques,
which analyse a neuroimage as a whole, considering not only the voxel intensities but also the relations among them. In
order to deal with the vast dimensionality of the data, a number of feature extraction methods have been successfully applied.
In this work, we propose a CAD system based on the combination of several feature extraction techniques. First,
some commonly used feature extraction methods based on the analysis of the variance (as principal component analysis),
on the factorization of the data (as non-negative matrix factorization) and on classical magnitudes (as Haralick features)
were simultaneously applied to the original data. These feature sets were then combined by means of two different combination
approaches: i) using a single classifier and a multiple kernel learning approach and ii) using an ensemble of classifier
and selecting the final decision by majority voting. The proposed approach was evaluated using a labelled neuroimaging
database along with a cross validation scheme. As conclusion, the proposed CAD system performed better than approaches
using only one feature extraction technique. We also provide a fair comparison (using the same database) of the
selected feature extraction methods.
Keywords: Alzheimer's disease, Computer aided diagnosis systems, Dimensionality reduction, Machine learning, Support
Vector Machine, 18F-FDG PET.
Rights & PermissionsPrintExport