Early detection of Alzheimer’s disease (AD) is essential to provide the patients with adequate and timely treatments and to help researchers monitor their effectiveness. Structural Magnetic Resonance Imaging (MRI) is a diagnostic tool that provides high-resolution images and a high brain tissue contrast. Classification methods have been proposed that use MRI-based biomarkers as features to distinguish between normal controls and AD patients. Most approaches rely substantially on the quality of at least one of the following: 1) the assumptions of which brain regions are affected; 2) the segmentation of these brain structures, which suffers from large variability across studies; 3) a voxelwise inter-subject correspondence, which is difficult to achieve, particularly considering the large anatomical variability of the brain across different subjects. Also, such methods focus on structural (volume, shape, density) changes only. It has recently been considered that also the MR image intensities and textures can provide complementary information that is overlooked by the structural-based features. In this thesis, we build on the existing literature on classification approaches that use MR image textures for early detection of AD. Firstly, we focus our analysis on a type of lesions in the white matter, which are thought to play a role in cognitive decline. Results show that the lesion textures are more discriminative than the widely used lesion volumes and locations. Secondly, we propose three approaches that use texture descriptors, determined at local patches over the entire brain. Results show that: 1) texture descriptors are able to achieve high classification rates, comparably to structural-based features; 2) no assumptions need to be made about the expectedly affected brain regions, and consequently no prior segmentations are needed; 3) by only affine-registering the images we are still able to localize discriminative regions using finely sampled patches in the brain.
|Award date||21 Nov 2013|
|Place of Publication||Enschede|
|Publication status||Published - 21 Nov 2013|