On May 5, at 1:00 pm, the "Priberam Machine Learning Lunch Seminar" will take place, featuring João Santinha. The seminar is free to attend, subject to prior registration, and will be held in lecture hall PA2, in the Mathematics building, at the Alameda campus.

About the speaker

João Santinha, PhD, is a researcher specializing in medical imaging, biomarkers, and artificial intelligence. He co-leads the Digital Surgery Lab. Dr. Santinha completed his PhD at Instituto de Telecomunicações – Instituto Superior Técnico, University of Lisbon. He is also an Invited Assistant Professor at the Faculty of Medicine of the University of Lisbon.
His work focuses on developing AI-driven tools to enhance surgical precision and personalize screening, diagnosis, treatments, and follow-up through imaging and non-imaging data.

Abstract

Medical imaging is a cornerstone of healthcare, supporting screening, diagnosis, treatment planning, assessment, and follow-up. However, due to changes in acquisition systems, data scarcity caused by privacy concerns, among other factors, developed machine learning models often lack generalizability. In this talk, we will explore how the invariance property of causal structures can be used to improve generalization, covering applications in tabular data derived from images, deep learning approaches, and the use of generative AI to promote such invariance.

Priberam is part of the Técnico Spin-Off Community.

Find out more information and register via the website.

News and image: Técnico