Jennifer Steeden

Accelerated MRI techniques have transformed cardiovascular MR and have been investigated in many clinical applications during the last decade to speed up MRI scans. This talk introduces the key components of Compressed Sensing and Low-rank methods, and how these are implemented in MRI. Examples of clinical applications and current challenges of Compressed Sensing and Low-rank methods are discussed. 

Chen Qin

Machine Learning (ML) has shown great potential in improving the medical imaging workflow. Particularly, in recent years, there has been a significant growth in the use of ML algorithms, especially Deep Learning (DL), for medical image reconstruction. The use of DL-based image reconstruction provides promising opportunities to transform the way cardiovascular MRI is acquired and reconstructed. In this talk, we will introduce recent advances in DL-based reconstruction techniques for cardiac imaging, with emphasis on cardiac MRI reconstruction. We will mainly focus on supervised DL methods for the application and will also discuss about their current limitations, challenges and future opportunities.

Video Unavailable

We all know that artificial intelligence (AI) can do marvelous things and that it is currently being incorporated into many industries. Yet, modern AI has an Achilles heel: It seems universally non-robust. That is, it can be unstable to tiny perturbations or generalize in unpredictable ways, both of which can lead to AI generated hallucinations. In this tutorial, we will investigate the many reasons for instabilities, unpredictable generalization and hallucinations in AI based image reconstruction. Furthermore, we will provide guidance on how to reduce the issue of non-robustness and untrustworthy outputs in AI based image reconstruction.

Stefano Buoso

The inference of local cardiac motion requires robust ways of analysing, integrating and processing patient data. Many models are available, both statistical and mechanistic, and they can be deployed to extract prognostic biomarkers from the data. The choice, however, usually falls on one or the other, and rarely both approaches are combined in a synergetic view. This talk will provide an overview on mechanistic models of cardiac motion and how these can be integrated with statistical models to overcome some of the limitations of current processing pipelines in medical images.