Automatic computational scheme for the detection, identification and classification of cerebral structural changes in magnetic resonance images to aid the diagnosis of patients with mild cognitive impairment and mild Alzheimer's disease

• Grant number: 18/06049-5
• Support type: Scholarships in Brazil - Doctorate
• Effective date (Start): November 01, 2018
• Effective date (End): March 31, 2021
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: Ricardo José Ferrari
• Grantee: Katia Maria Poloni
• Home Institution: Centro de Ciências Exatas e de Tecnologia (CCET). Universidade Federal de São Carlos (UFSCAR). São Carlos , SP, Brazil

Abstract

Alzheimer's Disease (AD) is the most common cause of dementia in the world population, accounting for about 60% of all cases and affecting 20% of the population over 80 years of age. It is an irreversible degenerative disease that causes loss of mental function due to deterioration of brain tissue. An AD can affect people in different ways, and their symptoms have gradual development. The most common ones include the difficulty of remembering new information, solving simple problems and completing routine tasks at home. Magnetic Resonance Imaging (MRI) has been used in clinical practice to aid in the diagnosis and follow-up of AD because of its excellent contrast between soft tissues and its ability to provide information about the shape and structure of organs, the detection of disease-induced changes in the brain and the determination of its stage. Currently, the primary focus of the research is the detection of AD in its initial stage, since, in this case, treatments to prevent or delay the onset of symptoms are much more effective. However, compared to the detection of AD, the prediction of the disease in the stage of Mild Cognitive Impairment (MCI) implies an even more significant challenge, since the anatomical changes, in this case, are more subtle. Therefore, the research and development of automatic computational techniques for the classification of MR images in Cognitively Normal (CN), MCI and AD are essential for reducing the diagnostic time and accelerating the development of new therapies to help to delay or prevent the development of AD. In this scenario, this research proposal has as primary objective to develop an automatic computational technique capable of detecting structural changes in MR images and using them to classify the images into one of the following classes: CN, MCI or mild-AD. (AU)