Invited talk by Pedro Ferreira

Abstract:

It is well known that the microstructure of the cardiac muscle changes in disease. Imaging techniques are limited to a scale of millimetres, and assessing this microstructure typically requires biopsy. Diffusion Tensor Cardiac Magnetic Resonance Imaging is a novel non-invasive technique that is beginning to uncover details of the cardiac microstructure at the cellular level, in the living heart.

This technique probes the microstructure by measuring the 3D displacement (diffusion) of water molecules, which will be hindered by cells and other microstructures. Diffusion patterns can therefore reveal details of the microstructure at much finer resolutions than the typical pixel sizes, bridging the gap between microscopy and conventional MRI. Despite the enormous potential, the application of diffusion imaging in the beating heart does not come without many challenges: cardiac and respiratory motion, long scans, low SNR, and complex post-processing. 

This talk will give an overview of the current developments, clinical results, and challenges to clinical translation. It will follow with an overview of the author's personal research in applying AI models to address some of the current challenges.
 

Bio:

Dr. Pedro Ferreira is a senior image processing and data scientist based at the Royal Brompton Hospital / Imperial College London UK. He has a background in Physics and Mathematics, a PhD in cardiac MRI, and since 2012, he has been working closely with a team of physicists and clinicians in Cardiac Diffusion Tensor Imaging.