New Representation of Information Extracted from MRI Volumes Applied to Alzheimer’s Disease

Springer papers

Authors

Katarina Trojacanec , Ivan Kitanovski , Ivica Dimitrovski and Suzana Loshkovska

Abstract

The aim of the paper is to propose a new representation of the information extracted from the MRI volumes in the context of Alzheimer’s Disease (AD). Two main stages are required: segmentation and estimation of the quantitative measurements. The representation is comprised of the quantitative measurements highlighted in the literature as valuable markers for distinguishing AD from healthy controls: cortical thickness of the separate parts of the brain cortex, the volume of the ventricular structures: left and right lateral ventricle, third and fourth ventricle, and the volume of the left and right hippocampus, left and right amygdala. Moreover, a representation that addresses the change of the patient’s condition over the time is also proposed. An illustration and discussion of the proposed method is given by using the MRIs provided by the Alzheimer’s Disease Neuroimaging Initiative (ADNI).

Keywords

Medical volumetric data VOI Alzheimer’s Disease ADNI segmentation quantitative measurements