Artificial intelligence for brain health assessment using magnetic resonance imaging.

• Grant number: 25/04494-5
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: June 01, 2025
• End date: May 31, 2026
• Field of knowledge: Health Sciences - Medicine - Medical Radiology
• Principal Investigator: Giovanni Guido Cerri
• Grantee: Felipe da Silveira Minuceli
• Host Institution: Faculdade de Medicina (FM). Universidade de São Paulo (USP). São Paulo , SP, Brazil
• Associated research grant: 21/11905-0 - Center of Science, Technology and Development for innovation in Medicine and Health: inLab.iNova, AP.CCD

Abstract

The project investigates Cerebral Small Vessel Disease (SVD), one of the leading causes of vascular dementia and lacunar strokes. SVD is associated with endothelial dysfunction and changes detectable through magnetic resonance imaging (MRI), such as white matter hyperintensities and microbleeds. This study aims to compare visual and automated assessment methods using the Segmentation of Subcortical and Cortical Structures (SAMSEG) tool, which is based on artificial intelligence. SAMSEG allows for precise and efficient identification of neuroanatomical alterations without the need for prior masks. The research will use 500 MRI scans from the Longitudinal Study of Adult Health (ELSA) to correlate SAMSEG findings with clinical scores and cerebrovascular risk factors. This approach seeks to validate the accuracy of the automated method compared to traditional visual analysis, contributing to advancements in the diagnosis and monitoring of subclinical lesions. The work plan includes a literature review, ethics and data processing training, development of scripts for SAMSEG application, comparative analysis between methods, and dissemination of results in articles and conferences. The proposal is part of the FAPESP Thematic Project 2020/09468-9, conducted at the Magnetic Resonance Laboratory in Neuroradiology (LIM/44) at USP. The study is expected to contribute to a deeper understanding of SVD, highlighting the importance of controlling risk factors to preserve brain integrity. The results have the potential to positively impact clinical practice and public health policies.