Welcome everybody to a new episode of Beyond the Patterns.

Today I have the great pleasure to have Ivana Iskum from the University of Amsterdam as

guest.

So she will present today an invited presentation entitled Deep Learning for Automatic Detection

of Cardiovascular Disease in CT and MR Exams.

Ivana is a professor of AI and Medical Imaging at the Amsterdam University Medical Center

at the University of Amsterdam.

In Fall 2018 she started as scientific lead of the company Quantibu.

Ivana Iskum graduated in Mathematics at the University of Zagreb, Croatia in 1999.

She obtained her PhD degree at the Image Science Institute in 2007 with a thesis entitled

Computer Aided Detection and Quantification of Arterial Calcifications with CT.

She was a postdoc at the Laboratory for Clinical and Experimental Image Processing in Leiden

University Medical Center and subsequently assistant and associate professor at UMC

Utrecht where she was leading the Quantitative Medical Image Analysis Group at the Image

Sciences Institute.

In 2019 Ivana was appointed full professor and moved with her group to University of

Amsterdam.

Her group is focusing on the development of algorithms for quantitative analysis of medical

images to enable automatic patient risk profiling, diagnosis and prognosis using AI techniques.

Ivana is the recipient of several large grants, has presented extensively in the medical imaging

conferences and published in scientific peer-reviewed journals and is also a very active member

of our Micae community.

So it is a great pleasure to have her here in this series and Ivana, the stage is yours.

Thank you for a very kind introduction.

So I am university professor of AI medical imaging which means that I work at the university

not in faculties and my task is to develop AI methods that can be implemented in clinic

in a responsible, socially responsible way.

But as my background is in image analysis my group is located at the Department of Medical

Engineering and Physics at the University Hospital in Amsterdam.

And very important topic in my research is analysis of cardiovascular images and today

I will present as just introduced work that we have done or that we are doing on CT and

MR.

So in this presentation I have divided it in two parts, these are relatively independent.

So I will first I would like to start with analysis in CT.

So very short introduction, cardiovascular disease is leading cause of death and disability

worldwide and fatal cardiovascular events like heart infection or stroke are often the

first manifestation of the disease.

At the same time subclinical signs of the presence of the disease, so in the stage when

the disease doesn't give any symptoms are visible in medical images often as requested

or unrequested findings.

So in some images which are made for any other reasons these signs are often visible.

However, current workflow in clinic that requires a lot of manual analysis and manual interaction

with images doesn't allow very detailed identification or detection of these signs when they are

not clinically relevant yet.

And this is especially the case or maybe I'm not sure this is especially the case but this

is also often case in coronary artery disease.

Coronary artery disease is a type of cardiovascular disease caused by plaque buildup.

This plaque can be calcified and non-calcified in the wall of the coronary arteries.

And here you see a slice from a CT scan which shows this white bright area that resembles

the bone in the coronary artery.