Spatio temporal analysis of pediatric magnetic resonance images

• Grant number: 17/50236-1
• Support type: Regular Research Grants
• Duration: July 01, 2018 - June 30, 2022
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Cooperation agreement: ANR
• Principal Investigator: Roberto Marcondes Cesar Junior
• Grantee: Roberto Marcondes Cesar Junior
• Principal investigator abroad: Isabelle Bloch
• Institution abroad: ParisTech, France
• Home Institution: Instituto de Matemática e Estatística (IME). Universidade de São Paulo (USP). São Paulo , SP, Brazil

Abstract

The advances in medical image analysis still leave a gap regarding pediatric brain imaging, even though \here is an regarding medical demand. This project aims at contributing to fill this gap, focusing on brain magnetic resonance Imaging (MRI) of infants, newborns and premature babies, which raise specific issues due to the particular grey/white matter contrast related to the physiological myelination process, How to extract and understand meaningful patters from data is a fundamental question scenarios where data are scarce but expert knowledge, continuously enriched, is available. This is typically the case here. We propose to develop structural representations of Knowledge and image information in the form of graphs and hypergraphs, which will be exploited to guide spatio-temporal segmentation, recognition and quantification processes. The aim is to aid diagnosis, pathology analysis and patients' folia -up. Applications will include the analysis of hyperintensities on the white matter, the volumetry of corpus callosum and its evolution, and neuro-oncology with the study of the influence of tumors on surrounding structures over time. The project involves specialists in medical image analysis, structural knowledge representation and pediatric radiology. (AU)