Discrimination of Alzheimer's Disease using longitudinal information

Alzheimer's Disease (AD) is a neurological disorder that leads to a loss of cognitive functioning, affecting older people as well as their families. Although a few treatments are available to slow down the progress of the disease, they are limited in effectiveness and should start at an early stage of the disease. Since an early diagnosis of AD is crucial, to maximize treatment effectiveness and prepare the families for the worsening of symptoms, researchers are studying biomarkers and Computer-aided diagnosis (CAD) systems. Hence, this manuscript proposes a new methodology to obtain an efficient CAD system by relying on [$$^{18}$$18F]-Fluorodeoxyglucose Positron Emission Tomography (FDG-PET) scans, while taking into account the longitudinal information of a subject. The CAD system tries to identify regions of interest by simultaneously segmenting all the FDG-PET scans acquired over time for each subject and combining the segmentation result to find the most coherent information for all the subjects. Experimental results show that the proposed CAD system outperforms a state-of-the-art approach, either when only relying on baseline scans or in the follow-up classification, achieving, for instance, more than 82.0% accuracy in the discrimination between AD and Mild Cognitive Impairment (MCI). Finally, in a multi-class classification task, the proposed CAD system attains 59.0% accuracy at baseline and goes up to 69.4% in the follow-up.