Welcome back to Beyond the Patterns. So today I have the great pleasure to welcome back

one of our former graduates of the lab, Professor Matthias Unberald. So he is now an assistant

professor in the Department of Computer Science at Johns Hopkins University with affiliations

to the Laboratory for Computational Sensing and Robotics and the Malone Center for Engineering

in Healthcare. He has created and is leading the Advanced Robotics and Computationally

Augmented Environments Lab, Arcade, that conducts research at the intersection of computer vision,

machine learning, augmented reality, robotics and medical imaging to develop collaborative

systems that assist clinical professionals across the healthcare spectrum. Previously,

Matthias was an assistant research professor in computer science and postdoctoral fellow

in the Laboratory for Computational Sensing and Robotics at Hopkins and completed his

PhD in computer science at the Friedrich-Alexander-Universität in Nuremberg in Germany from which he graduated

summa cum laude in 2017. While completing a bachelor's in physics and a master's in

optical technologies at FAU, Matthias studied at the University of Eastern Finland as an

Erasmus scholar in 2011 and joined Stanford University as a DAAD fellow throughout 2014.

Matthias has published more than 80 journal and conference articles and has received numerous

awards, grants and fellowships including the NIH NIBIB R21 Trey Blazer Award. It's a great

pleasure to have him back here at our university and today he will be presenting Bridging Domains

in Medical Imaging – Differential Mappings between Two- and Three-dimensional Data Domains.

Matthias, it's a great pleasure to have you back and the stage is yours.

Thank you, Andreas, for the kind introduction and more importantly for the wonderful invitation.

It's always a pleasure to be back in Erlangen this year. Unfortunately, virtually I would

have loved to visit you in person and appreciate the Christmas spirit that is, it just feels

so much more like Christmas if you're in Germany, not in Baltimore, although they tried

to emulate it here in the inner harbor as well with the Christmas market. It just doesn't

feel the same. So I've decided today to talk about some of our recent work that plays a

role in between 2D and 3D data domains because we all know that medical imaging data lives

in between these domains. We have 2D data, we have 3D data and connecting these domains

seems to play an important role and I will give you a better introduction to that topic

in a little bit. It's a pleasure for me to see some of the familiar faces back from the

time when I was with the LME in Erlangen and for everyone else. Matthias, I graduated from

the same lab in 2017 and you have a great advisor Andreas. I'm sure you'll be very successful

in the future. So before starting the actual content of my talk, I want to mention that

this is the work of many people. We have collaborators within my group of course we have collaborators

within the Department of Computer Science, but more importantly also with hospitals,

with the Johns Hopkins Hospital that is a leader in many regards where we get to talk

and inform our method development by the problems that they encounter in their everyday practice.

And working together with them on the problems is great because it allows us to shape a way

forward together so that the solutions that we develop neatly fit into their surgical

workflows. And then there are some collaborations of course also with this group in fact. So

thank you for that. It's always been great. All right. So bridging domains and medical

imaging. Why do we need this? So I think you probably all know that medical imaging is

an enabling technology. And when I say enabling technology, then I mean that quite broadly

because what we're seeing now is that with the medical imaging modalities that are deployed

all across the hospital, we are now able to perform non-invasive diagnosis, which allows

us to investigate certain disease patterns without having to biopsy for example. And

it allows us to perform procedural planning and map out the steps that will need to be

performed intraoperatively. And then we have other modalities that are deployed intraoperatively,

which allow us to rethink surgery and develop less invasive surgical approaches that are

now guided by imaging technology. And this is really the focus of today's talk, which

is image guided interventions. Now, while these approaches now are less invasive, they