Early prognosis of Alzheimer's disease using images from fundus camera

Alzheimer's disease (AD) is the most common form of senile dementia affecting the growing aging population. Clinically, it was proved that there is a progressive decline in cognition, memory, and social functioning due to deposition of different types of protein in the brain. Traditional decision making systems are more manual in nature and ultimate conclusion in terms of exact prognosis is remote. Recently, under certain investigations neurological degradation occurs in the retina of the eye as well as the brain. Also it is clearly investigated that are some parameter changes on the retina of the eye of the AD patients. Therefore eye provides a transparent medium to neuropathology which initiated the development of ocular biomarkers for AD. Retinal imaging and visual testing potentially improves disease management and quality of life for AD patients as they are non invasive methods. Any disease modifying treatments which are developed are most possibly to be achieving success if initiated early in the process, and this needs that we tend to develop reliable, validated and economical ways to diagnose AD. Profiling of human body parameter using computers can be utilized for the early prognosis of AD. There are several imaging techniques used in clinical practice for the prognosis of Alzheimer's type pathology. In this paper we have focused on the fundus imaging, a type of retinal imaging that can be used for the early prognosis of AD. For that we have proposed a new scheme based on Fixed-Grid Wavelet Networks (FGWN) for the segmentation of fundus retinal images that can be used for diagnosing AD.