Computer Aided Diagnosis in Pre-Clinical Dementia: From Single-Modal Metrics to Multi-Modal Fused Methodologies
This chapter presents an advanced multi-modal fused methodology and its application in pre-clinical dementia. As our population ages, the societal costs of dementia are set to soar. Currently, successful prediction of dementia types in the pre-clinical stage is still problematic. This is mainly due to the co-morbidity and similar etiology with other types of disease commonly seen in aging populations, particularly cardiovascular disease. As a result, understanding the extent to which vascular disease and its risk factors are associated with prodromal dementia, notably Alzheimer’s disease (AD), may enhance predictive accuracy as well as guide early interventions. One promising avenue to determine this relationship consists of looking for reliable and sensitive in-vivo imaging methods capable of characterizing the subtle brain alterations before the clinical manifestations. However, little is known from the imaging perspective about how risk factors such as vascular disease influence AD progression. In this chapter, for the first time, we will introduce an innovative T1 and diffusion tensor imaging (DTI) fusion analysis of 3D brain corpus callosum on subjects with mild cognitive impairment (MCI) – a widely recognized precursor of dementia. The feasibility and sensitivity of the novel T1 and DT-MRI fusion methodology in de-coupling the vascular factor in the prodromal AD stage will be compared with those of traditional single modality based methods.