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.
Artificial Intelligence in Chest Radiography: Growing pains and Interpretability
May 30, 2023
1:00 pm
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 TECSeminários
Últimos seminários
Unlocking Latent Discourse Translation in LLMs Through Quality-Aware Decoding
June 17, 2025Large language models (LLMs) have emerged as strong contenders in machine translation. Yet, they often fall behind specialized neural machine…
Speech as a Biomarker for Disease Detection
May 20, 2025Today’s overburdened health systems face numerous challenges, exacerbated by an aging population. Speech emerges as a ubiquitous biomarker with strong…
Enhancing Uncertainty Estimation in Neural Networks
May 6, 2025Neural networks are often overconfident about their predictions, which undermines their reliability and trustworthiness. In this presentation, I will present…
Improving Evaluation Metrics for Vision-and-Language Models
April 22, 2025Evaluating image captions is essential for ensuring both linguistic fluency and accurate semantic alignment with visual content. While reference-free metrics…