Sulcal Morphology Analysis from MRI Data for Classification of Alzheimer's Disease

Alzheimer's disease (AD) is a progressive and irreversible neurodegenerative disorder, characterized by structural changes in the brain, leading to a gradual loss of cognitive functions, and eventually death. A successful diagnosis of the disease is very difficult, since both the early symptoms and the structural brain changes can be mistaken for normal ageing or for other forms for dementia. An early detection of AD has important implications for future developments of disease-modifying treatments. The aim of this thesis was to utilize the morphology of cortical sulci as a biomarker for quantifying the atrophy in AD and in mild cognitive impairment (MCI), a transitional condition between normal ageing and AD. The thesis consists of four, in which both the global and local properties of cortical sulci were analyzed. The results indicate that sulcal morphology features could be powerful biomarkers, which accurately distinguish AD from normal control subjects. The addition of cortical thickness measures notably increased the classification accuracies. However, sulcal morphology features alone were more sensitive in classifying early MCI from AD and cognitively normal controls.