Date and time: 20 March 2025, 13:00-14:00 CET
Speaker: Rodrigo Moreno, KTH
Title: Synthetic MRI aging and Magnetic Resonance Elastography
Where: Digital Futures hub, Osquars Backe 5, floor 2 at KTH main campus
Directions: https://www.digitalfutures.kth.se/contact/how-to-get-here/
OR Zoom: https://kth-se.zoom.us/j/69560887455
Host: Martina Scolamiero
Bio: Rodrigo Moreno is a Professor in magnetic resonance imaging at the Division of Biomedical Imaging at the Department of Biomedical Engineering and Health Systems (MTH) at KTH. His research focuses on developing computational tools for medical image analysis, with an emphasis on advanced magnetic resonance imaging (MRI) and artificial intelligence (AI). His work aims to improve early clinical diagnosis and patient monitoring, with a strong focus on translating research into clinics. He is responsible for the MRI facility at KTH.
A key area in his research is magnetic resonance elastography (MRE), where he seeks to unveil the biological processes behind the changes in the mechanical properties of brain tissue observed in patients. He has also projects on brain structural connectivity analysis, synthetic MRI aging, and image analysis for cancer patients. He has secured funding from prestigious funding agencies, including VR, MedTechLabs, Marie Sklodowska-Curie ETN, Hälsa Medicin och Teknik, Digital Futures, Eurostars, and Vinnova.
Abstract: In this seminar, I will summarize the results from two of our current projects. In the first part of the talk, I’ll introduce the methods we have proposed to simulate MRI aging from MRI scans of healthy and Alzheimer’s subjects. Instead of using standard generative AI, we use deep learning-based registration. The advantage of our approach is that the generated images are anatomically plausible by construction. In the second part of the talk, I’ll summarize our preliminary findings in our project on magnetic resonance elastography (MRE).
MRE is a novel modality that is able to estimate the mechanical properties of the brain tissues non-invasively. MRE is promising since previous studies have shown that MRE can detect changes at very early stages of the disease when morphological changes are still not visible. We are currently imaging subjects from different cohorts targeting Parkinson’s disease, Alzheimer’s disease, multiple sclerosis, and cancer, as well as normal aging. Our goal is to develop new methods for extracting such properties targeting both accuracy and speed. Moreover, we are interested in understanding the biological mechanisms behind changes in mechanical parameters due to disease and normal aging. We target this goal by using additional MRI modalities, from which, multidimensional diffusion MRI is so far the most promising.
