Agenda

Speaker:
Matteo Grazioso, Ca’ Foscari University of Venice

Abstract:
Deep Learning techniques have shown broad applicability across numerous domains, including medicine. Among these, Cardiovascular Magnetic Resonance Imaging stands out as a field where Deep Learning has the potential to transform myocardial tissue characterization through the automated, objective, and reproducible assessment of modern-day quantitative techniques like T1 and T2 mapping images. The clinical implementation of this approach, however, is hindered by several obstacles, including the need for center-specific reference values along with the scarcity of large annotated datasets, class imbalance, and the requirement for transparent and explainable decision-making. This Seminar presents a Deep Learning approach exploiting both supervised and semi-supervised learning, along with model ensembling to address these challenges. It introduces explainability tools to support transparent case-level explanation of model predictions, fostering clinician trust and supports clinical adoption. Experimental results demonstrate that the proposed framework enhances predictive accuracy and reliability while offering actionable insights in Cardiac Imaging.

Bio sketch:
Matteo Grazioso is a Ph.D. Student in Computer Science at Ca’ Foscari University of Venice (Department of Environmental Sciences, Informatics and Statistics). His primary research focuses on Interpretable and Fairness-preserving AI for High-Risk applications, where he explores the design of trustworthy AI systems, ensuring that Machine Learning models in high-stakes domains are both transparent and ethically aligned. Matteo’s research interests lie at the intersection of Computational Intelligence, Machine Learning, Interpretable AI, High-Performance Computing, Evolutionary Drug Discovery, and Optimization Algorithms. He holds a Master’s Degree in Computer Science – Artificial Intelligence and Data Engineering –, graduated summa cum laude from Ca’ Foscari University of Venice, where he also served as a Research Grant Holder. In parallel with his doctoral studies, Matteo serves as a Technological Associate at the Italian National Institute of Nuclear Physics (INFN), Milano Bicocca Division, and is a Visiting Ph.D. Student at the University of Milano-Bicocca (Department of Informatics, Systems and Communication). He is an active member of the IEEE and the IEEE Computational Intelligence Society (CIS), contributing to the CIS Task Force on Advanced Representation in Biological and Medical Search and Optimization.