Multimodal Artificial Intellligence Approach for Myocardial Fibrosis Segmentation and Clinical Decision Support

• Grant number: 26/13159-8
• Support Opportunities: Scholarships in Brazil - Post-Doctoral
• Start date: June 01, 2026
• End date: May 31, 2028
• Field of knowledge: Engineering - Biomedical Engineering
• Principal Investigator: Marco Antonio Gutierrez
• Grantee: Estela Ribeiro
• Host Institution: Instituto do Coração Professor Euryclides de Jesus Zerbini (INCOR). Hospital das Clínicas da Faculdade de Medicina da USP (HCFMUSP). Secretaria da Saúde (São Paulo - Estado). São Paulo , SP, Brazil
• Associated research grant: 25/11759-5 - Deep Learning-Driven 68GaFAPI-04 PET/CT Imaging for Cardiac Fibrosis Assessment (FIBRAI), AP.R

Abstract

The goal of this project is to develop advanced deep learning models for automated multimodal myocardial fibrosis segmentation using PET and CT imaging data. The proposed approach aims to improve diagnostic accuracy and quantitative assessment of myocardial fibrosis through the integration of complementary anatomical, functional, and metabolic imaging information. Particular emphasis will be placed on model robustness, generalizability across heterogeneous datasets, and clinical explainability to ensure reliable translational applicability. In addition, the project will investigate visual analytics strategies and interpretable AI approaches to facilitate physician interaction with model outputs and support clinical decision-making. Ultimately, this work seeks to contribute to precision cardiovascular medicine by enabling more accurate, reproducible, and clinically meaningful fibrosis assessment. (AU)