Priberam

Artificial Intelligence in Chest Radiography: Growing pains and Interpretability

Chest radiography is one of the most ubiquitous medical imaging modalities. Nevertheless, the interpretation of chest radiography images is time-consuming and complex meaning that the field is ripe for a takeover from artificial intelligence systems. The high image throughput has allowed for the creation of large annotated datasets which have in turn been used to train deep learning systems that can obtain near-human performance. But are these systems ready for the clinic? In this presentation, the main challenges in the development and application of deep learning systems in chest radiography will be presented with a focus on interpretability and a case study on the COVID-19 pandemic.

João Pedrosa

João Pedrosa was born in Figueira da Foz, Portugal, in 1990. He received the M.Sc. degree in biomedical engineering from the University of Porto, Porto, Portugal, in 2013 and the Ph.D. degree in biomedical sciences with KU Leuven, Leuven, Belgium, in 2018 where he focused on the development of a framework for segmentation of the left ventricle in 3D echocardiography. He joined INESC TEC (Porto, Portugal) in 2018 as a postdoctoral researcher and is an invited assistant professor at the Faculty of Engineering of the University of Porto since 2020. His research interests include medical imaging acquisition and processing, machine/deep learning and applied research for improved patient care.INESC TEC