Advanced search
Start date
Betweenand

Development of feature engineering and deep learning techniques applied to the classification of magnetic resonance images in healthy cognitive aging, mild cognitive impairment and Alzheimer's Disease

Grant number: 18/08826-9
Support type:Regular Research Grants
Duration: October 01, 2018 - September 30, 2020
Field of knowledge:Physical Sciences and Mathematics - Computer Science
Principal Investigator:Ricardo José Ferrari
Grantee:Ricardo José Ferrari
Home Institution: Centro de Ciências Exatas e de Tecnologia (CCET). Universidade Federal de São Carlos (UFSCAR). São Carlos , SP, Brazil
Assoc. researchers: Roger Tam

Abstract

With the population aging, dementia has become one of the most relevant global public health problems. Among the different types of dementia, Alzheimer's disease (AD) is the most frequent, accounting for almost 60% of the cases. The World Health Organization estimated the number of people with dementia at 35.6 million in 2010, which is expected to double by 2030 (65.7 million) and again by 2050 (115.4 million). In Brazil, the number of people with dementia is estimated at one million. However, even when patients report symptoms and have apparent cognitive impairments, dementia may not be diagnosed. Up to 75% of patients with dementia and up to 97% of patients with a mild cognitive impairment may not be diagnosed. New proposals for diagnostic criteria for AD and prospects for pre-dementia therapies require the identification of biomarkers that provide an early and accurate diagnosis. Therefore, this project proposes the study of feature engineering and deep learning techniques for use in automatic classification of 3D magnetic resonance imaging in the classes healthy cognitive aging, mild cognitive impairment and Alzheimer's disease. All development will be carried out using public domain images databases, and the final developed techniques will be available for use by researchers from the Department of Medicine of the Federal University of São Carlos (UFSCar). (AU)