Graph learning for MRI semantic segmentation

• Grant number: 19/16112-9
• Support Opportunities: Scholarships abroad - Research Internship - Master's degree
• Start date: December 01, 2019
• End date: March 29, 2020
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: Roberto Marcondes Cesar Junior
• Grantee: Larissa de Oliveira Penteado Dias
• Supervisor: Isabelle Bloch
• Host Institution: Instituto de Matemática e Estatística (IME). Universidade de São Paulo (USP). São Paulo , SP, Brazil
• Institution abroad: ParisTech, France
• Associated to the scholarship: 18/07386-5 - Segmentation of neonatal magnetic resonance imaging: a structural approach, BP.MS

Abstract

The semantic segmentation of Magnetic Resonance Imaging (MRI) plays an important role in diseases diagnosis, treatment and development follow-up. The manual analysis of such exams is time-consuming and prone to user variability. Therefore, over the years different automatic and semi-automatic methods have been developed. Most of them were created to deal with adult data. Because of intrinsic image differences of these volumes to neonates and infants ones, such methods tend to fail for these patients. So, in this project, we aim to develop a robust algorithm to perform the semantic segmentation of brain MRI of children and neonates, by using Graphs and Graph Neural Networks. (AU)

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

OLIVEIRA, HUGO; PENTEADO, LARISSA; MACIEL, JOSE LUIZ; FERRACIOLLI, SUELY FAZIO; TAKAHASHI, MARCELO STRAUS; BLOCH, ISABELLE; CESAR JUNIOR, ROBERTO; IEEE COMP SOC. Automatic Segmentation of Posterior Fossa Structures in Pediatric Brain MRIs. 2021 34TH SIBGRAPI CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI 2021), v. N/A, p. 8-pg., 2021-01-01. (19/16112-9, 15/22308-2, 18/07386-5, 20/06744-5, 17/50236-1)