Welcome back to Beyond the Patterns.

So today I have the great pleasure to announce a guest from Japan.

Dr. Esam Rashad received his bachelor's in scientific computing in 1998 and his master's

in computer science in 2002, both from Swiss Canal University, Ismailia, Egypt.

He received a PhD in computer science from the University of Tsukuba, Japan in 2010.

From 2010 to 2012 he was a research fellow of the Japan Society for the Promotion of

Science, JSPS, at the University of Tsukuba.

He served as assistant professor of computer science at the Department of Mathematics,

Faculty of Science, Swiss Canal University from 2012 to 2016.

Since then he was promoted to associate professor at Swiss Canal University, Egypt and worked

at the Faculty of Informatics and Computer Science of the British University in Egypt

on secondment.

Currently he is a research associate professor at Nagoya Institute of Technology.

His research interests include medical image processing, data analysis and visualization,

deep learning and pattern recognition.

Dr. Rashad is an IEEE senior member and associate editor of IEEE Access.

He is also a recipient of the Egyptian National Doctorate Scholarship in 2006, JSPS Postdoctoral

Fellowship in 2010, J.A.

MIT BEST Presentation Awards in 2008 and 2012 and the Chairman Award of the Department of

Computer Science, University of Tsukuba in 2010.

He participated also as PI and co-PI for several externally funded projects.

So today I have the great pleasure to have him as a speaker and his presentation is entitled

Human Head Models with Deep Learning Enabled Dialectic Properties.

So Isham, I'm really glad to have you here and the stage is yours.

Thank you very much Andrea for the nice presentation and for the invitation to be here.

It's my pleasure to be with your group now and to introduce current research we have

done here in Nagoya Institute of Technology.

As you remember the last time we took about this kind of research about developing head

models and the challenges that we have faced here to actually try to find some solution

based on deep learning.

So today I will briefly discuss the problems and the challenges we have with this application

and then I will discuss some solutions that we have proposed as long as the past one and

a half year.

So thank you again for the invitation and let's start.

So actually the talk today is about the generation of the human head models by using the deep

learning technology and I'll start with the basic idea about this problem.

So the main application here is related to electromagnetic to zoometech application.

So we assume that we would like to sense some physical properties such as doing a brain

stimulation of some patient and to do this the main application is actually based on

some electromagnetic signals.

To do so we would like to understand how the stimulation is affecting the different tissues

especially in the head or let's say especially in the brain.

So this application is actually commonly used for the diagnosis, rehabilitation and also

for the surgery mapping assuming that we have some patient and that's question that it has

some tumor in some specific place and we would like to sense the location where we would

like to do the resection or something.

So in some cases the brain stimulation is used to do the brain mapping and detection

where the exact position to do the surgery.

So the problem or actually or the main challenge here that as you know that we have a real

challenge when the anatomy is different from one person to another.