Automating the Koedam Parietal Atrophy Scale in Alzheimer's Disease Using Attributes from T1-weighted Magnetic Resonance Imaging and Clustering Techniques

• Grant number: 23/15916-2
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: March 01, 2024
• End date: November 30, 2025
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Ricardo José Ferrari
• Grantee: Yasmin Victoria Oliveira
• Host Institution: Centro de Ciências Exatas e de Tecnologia (CCET). Universidade Federal de São Carlos (UFSCAR). São Carlos , SP, Brazil

Abstract

The search for imaging biomarkers plays a crucial role in the quest for diagnosing Alzheimer's Disease (AD), offering a non-invasive and potentially early approach to identify brain changes associated with the disease. Such biomarkers also have the potential to provide valuable insights into the progression of AD, enabling the application of more effective treatment strategies. In this context, the Koedam visual scale for parietal atrophy emerges as a particularly relevant tool. By focusing on the parietal region, this scale allows for a specific assessment of the structural changes associated with AD, providing a more detailed understanding of cerebral atrophy in the disease. In this context, this research proposes the automation of the Koedam scale using attributes extracted from T1-weighted magnetic resonance imaging (MRI) and clustering techniques. The first stage of the research will focus on identifying the parietal region in MRI images through image co-registration with an atlas. Subsequently, the parietal region will be segmented into major brain tissues using unsupervised techniques. The quantity of each tissue in the parietal region will be used as an attribute for clustering techniques, simulating the visual categorization of the Koedam scale. This approach aims to automate the assessment of parietal atrophy, providing an effective tool for early AD diagnosis.