Anatomically plausible image registration often requires volumetric preservation. Previous approaches to incompressible image registration have exploited relaxed constraints, ad hoc optimization methods or practically intractable computational schemes. Divergence-free velocity fields have been used to achieve incompressibility in the continuous domain, although, after discretization, no guarantees have been provided. During this talk, Lucas will introduce stationary velocity fields (SVFs) parameterized by divergence-conforming B-splines in the context of image registration and show how we can use them to impose incompressibility with theoretical guarantees.

About Lucas Fidon

Lucas Fidon is a PhD student in Biomedical Engineering at King’s College London supervised by Prof. Tom Vercauteren. He has a Msc in Applied Mathematics and Computer Science from CentraleSupélec in Paris (2014-2018) where he pursued a specific elite Research Track under the supervision of Prof. Nikos Paragios. He also has a Msc in Applied Mathematics and Computer Science from Ecole Normale Supérieur Paris-Saclay (2017-2018) and a Msc in Core Mathematics from Paris-Sud University (2015-2016).

Curious about our other news? Subscribe to our news feed, calendar, or newsletter, or follow us on social media.