Integration of ERP and fMRI for the early diagnosis of AD

Project: National Science and Technology CouncilNational Science and Technology Council Academic Grants

Project Details


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. Mild cognitive impairment (MCI) is considered a transitional stage between normal aging and dementia. Recent progress in the treatment or prevention of MCI leads to a growing concerns in the early diagnosis. A thorough understanding of the conversion process is, therefore, of clinical interest and importance. It was an attempt to predict the pattern of conversion as the disease progresses either from MCI to AD or from normal to MCI. If MCI can be diagnosed at early stage and effective intervened, then it is possible to reduce the advanced damages. The following questions are generally difficult to answer: (a) if the admitted patient is of AD, (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. Nowadays, in the diagnosis of AD, is mostly limited to the analysis of individual information. However, the information provided by the clinical examination using only, one imaging modality is limited and deficient. Many research reports that electroencephalogram (EEG) provides a convenient means of disclosing the reduced functional couplings between brain regions in AD. Event-related potential (ERP) related to cognitive process and mental function has been widely used for investigating neurological illness related to AD. Functional magnetic resonance imaging (fMRI) can directly observe brain function opens an array of new opportunities to advance our understanding of brain organization, as well as a potential new standard for assessing neurological status and neurosurgical risk. Therefore, a combination of biomarkers, in particular, neuroimaging and physiological electrical signal, can increase diagnostic accuracy. In this project, we plan to develop a comprehensive, integrated image and signal processing platform, which is of easy access to clinicians. By combination the various information contents from EEG/ERP, structural and functional MRI, we can increase the sensitivity and specificity of the early diagnosis of AD. During the next three years, we will collect the EEG, ERP and fMRI data. Through the use of EEG Lab and SPM8, we will analyze these data. Next, we will develop image segmentation technique to calculate the quantitative information of brain ROI images, and establish a correct classification of characteristics as quantitative indicators to improve classified accuracy of MCI group. We will also add these new data to assess the quality of the classifier we proposed. Finally, we hope to develop a more comprehensive AD risk prediction algorithm by combining data from multiple cohorts. This achievement cannot only provide complete and integrated information of the combined image and signal data but decrease the inter- and intro-operator errors, such that it can help neurologists to achieve a more objective and accurate diagnoses of neuro-degenerative and neuro-developmental diseases, as well as cognitive neuroscience.

Project IDs

Project ID:PB10202-1463
External Project ID:NSC101-2221-E182-015-MY3
Effective start/end date01/08/1331/07/14


Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.