ICG/Research/Team Pock/Team

Kerstin Hammernik

I received a BSc and MSc in Biomedical Engineering from Graz University of Technology in 2011 and 2015, respectively. Currently, I'm a research assistant and PhD student supervised by Prof. Thomas Pock at the Institute of Computer Graphics and Vision, Graz University of Technology. My current research interests include optimization and learning of variational models with application to medical inverse problems such as magnetic resonance (MR) and photoacoustic image reconstruction. A list of publications can be found here and on my Google scholar page.

News

2018

Jun 22
We were interviewed about our ongoing research at Graz University of Technology in cooperation with NYU School of Medicine on "Learning a variational network for reconstruction of accelerated MRI data"!
Read more on the MRM Highlights Blog
Jun 16
Tensorflow source code for our work "Learning a Variational Network for Reconstruction of Accelerated MRI Data" is now available on github.
Jun 16 - 21
ISMRM 2018 @ Paris, France I was nominated as Young Investigator Award Finalist for our work "Learning a Variational Network for Reconstruction of Accelerated MRI Data". It was a pleasure to give an educational talk about "Role of Machine Learning in Image Acquisition & Reconstruction" in the session "Machine Learning for Cardiovascular Disease". My slides are available here. We received the Summa cum Laude Merit award for our abstract (oral) presented in the session "Scientific Highlights of the Joint Annual Meeting ISMRM-ESMRMB":
Variational Adversarial Networks for Accelerated MR Image Reconstruction
Kerstin Hammernik, Erich Kobler, Thomas Pock, Michael P. Recht, Daniel K. Sodickson, Florian Knoll
Jun 5
Talk at SIAM Conference Imaging Science 2018 in Bologna, Italy
"Challenges in Learning-Based MR Image Reconstruction"
May 17
Our article is published in Magnetic Resonance in Medicine (MRM) (early view)!
Assessment of the generalization of learned image reconstruction and the potential for transfer learning
Florian Knoll, Kerstin Hammernik, Erich Kobler, Thomas Pock, Michael P Recht, Daniel K Sodickson
(read more)


2017

Oct 5
Our article is accepted in Magnetic Resonance in Medicine (MRM)!
Learning a Variational Network for Reconstruction of Accelerated MRI Data
Kerstin Hammernik, Teresa Klatzer, Erich Kobler, Michael P Recht, Daniel K Sodickson, Thomas Pock, Florian Knoll
(read more)
Sep - Dec
Apr 22-27
ISMRM 2017 @ Honolulu It was a pleasure to give an educational talk about "Insights into learning-based MRI reconstruction" at the Junior Fellows Symposium: Machine Learning in Imaging. We presented our three abstracts: On the Influence of Sampling Pattern Design on Deep Learning-Based MRI Reconstruction (oral)
Hammernik, K., Knoll, F., Sodickson, D. K. & Pock, T. L2 or not L2: Impact of Loss Function Design for Deep Learning MRI Reconstruction (oral)
Hammernik, K., Knoll, F., Sodickson, D. K. & Pock, T. Accelerated Knee Imaging Using a Deep Learning Based Reconstruction (power pitch / e-poster)
Knoll, F., Hammernik, K., Garwood, E., Hirschmann, A., Rybak, L., Bruno, M., Block, K. T., Babb, J., Pock, T., Sodickson, D. K. & Recht, M. P.
Mar 13
Talk at the BVM 2017 in Heidelberg on "A Deep Learning Architecture for Limited-Angle Computed Tomography Reconstruction" 
Jan 31
Three abstracts accepted for ISMRM 2017!

2016

Oct 17-19
Aug 25-27
ESMRM - Lectures on MRI: Non-Cartesian MRI in Würzburg
Aug 24
I gave a talk at Friedrich-Alexander-Universität Erlangen-Nürnberg
May 31
I gave a talk at NYU about "Insights into Deep Learning for MRI Reconstruction"
May 23
Talk at the SIAM Conference on Imaging Science in Albuquerque, New Mexico:
Learning Variational Models for Image Reconstruction
Kerstin Hammernik, Florian Knoll, Thomas Pock
Abstracts
May 13
We received the Magna cum Laude Merit Award for our ISMRM 2016 abstract (Oral):
Learning a Variational Model for Compressed Sensing MRI Reconstruction
Kerstin Hammernik, Florian Knoll, Daniel Sodickson, and Thomas Pock
In: Proceedings of the International Society of Magnetic Resonance in Medicine (ISMRM)
, 2016.

Projects

Learning a variational network for
accelerated MRI reconstruction

Cooperation with Florian Knoll and Daniel Sodickson

Fast all-optical photoacoustic
micro-imaging of vasculature

FWF project

More...