Analysis of Proteins in Microscopic Skin Images Using Machine Vision Techniques as a Tool for Detecting Alzheimer’s Disease

Abstract

Alzheimer’s disease (AD) is a disease characterized by progressive loss of memory, orientation, judgement and language. Its progression is slow and there is no cure for this multifactorial disease, so it is of great importance the discovery of new methods of early diagnosis, as well as the development of more effective treatments. AD is the most common type of dementia. Currently, the incidence of dementia has increased and constitutes a priority health problem worldwide, so urgent measures focused on prevention and reduction of risk factors, as well as early diagnosis, are required. In this work, we proposed computer vision techniques as a tool for histological analysis to support experts in the search for a biochemical marker for early diagnosis of AD. We analized ten samples of skin tissue biopsies (5 controls and 5 AD patients) of microscopic images to find characteristic staining colors to differentiate the images of healthy subjects from Alzheimer’s disease patients. In the immunohistochemistry process, the antibodies that revealed tau protein oligomers antigens were AT22. For lamin A, we used anti-lamin A. Results allowed us to find differences between healthy subjects and subjects with Alzheimer’s disease.