Development of Soft-Computing techniques capable of diagnosing Alzheimers Disease in its pre-clinical stage combining MRI and FDG-PET images

In this paper an intelligent classifier was development, in which information provided from MRI and FDG-PET images are combined in order to obtain an automatic classifier. In the first step was to develop a classification method to tag simultaneously MR and FDG-PET images as either normal or with the Alzheimer’s disease (AD). With the methodology obtained, and using similar features, the next step was the identification and classification in normal subjects, MCI (Middle Cognitive Impairment) patients and AD patients. The last step was the possibility to classify in Middle Cognitive Impairment Converters (MCI-C, i. e. , people that suffer a MCI and in the future will suffer from Alzheimer’s disease within 18 months), and Middle Cognitive Impairment Non Converters (MCI-NC, i. e., people that suffer a MCI and in the future will not suffer from Alzheimer’s disease). It is noteworthy that with this last study we could offer a tool to assist the early diagnosis of dementia.