Early Detection System of Alzheimer's Disease with the Aid of Fusion of Multi-Modality Images and Its Performance Evaluation

Alzheimer's disease (AD) is the most common type of dementia. Clinical signs are characterized by progressive cognitive deterioration, together with declining activities of daily living and by neuropsychiatric symptoms or behavioral changes. The study of Alzeimer’s Disease is potentially challenging because of several reasons. First of all there existed no known biomarkers. The disease usually has an insidious onset, which can be a combination of genetic and environmental factors. It is difficult to differentiate from other types of dementia. In conventional MRI and in nuclear medicine, the images usually showed global atrophy on patients at an advanced stage of AD. Functional assessment can be related to different extent of degeneration associated with the specific region respectively. Image based diagnosis is generally segmental and one-dimensional, which required comprehensive integration from all related information contents. The following questions are generally difficult to answer: (a) if the admitted patient is of Alzheimer’s Disease, (b) if so, at what stage he/she is, (c) after longitudinal follow-up, if the status degenerated or improved. The answer to these questions required a comparison with the normal healthy subjects. Noticeably, among Chinese society such a template is missing. In this project, we plan to develop a comprehensive, integrated image processing platform, that is of easy access to clinicians. By combination the various information contents from MRI and Nuclear Medicine, we can increase the sensitivity and specificity of the early diagnosis of AD. During the next three years, we will build up a Taiwanese specific brain template, and develop various classification methods such as genetic algorithm and support vector machine. The second goal of the project is to provide a standard for the studies of neuron-degenerative and neuro-developmental diseases, as well as cognitive neuroscience

Project ID:PB9902-2195
External Project ID:NSC98-2221-E182-040-MY3