Extraction of brain regions for image diagnosis of Alzheimer-type Dementia based on atrophy progress speeds

We constructed an image diagnosis support system for Alzheimer-type Dementia that extracts temporal lobe regions and an intracranial region as regions of interest (ROI) from a T2-weighted MR frontal image and uses the cerebral atrophy rates at the ROI. In this paper, we specifically discuss extraction of brain regions and diagnosis support information based on atrophy speeds of the ROI. The proposed method comprises of three steps. Step 1: A first contour that approximates a shape of the temporal lobe region to a triangle is set and Balloon model is applied. Step 2: A temporal lobe AAM is constructed and it is applied to the result obtained in Step 1. Step 3: Intracranial region is extracted using temporal lobe regions detected in Step 2. We demonstrate the potential of our method using actual diagnosis images. Additionally, we calculate atrophy rates of the ROI to consider a possibility for diagnosis of ATD using atrophy progress speeds of the ROI.