Go to JKU Homepage
Institute for Machine Learning
What's that?

Institutes, schools, other departments, and programs create their own web content and menus.

To help you better navigate the site, see here where you are at the moment.

AI-RI

FWF Project: AI-Based Retinal Image Analysis Research Group (AI-RI)

Term: 06/21 - 05/26 (5 years)

Scientific Advisory Board: Theresa Roland, Fabian Theis, Sotirios Tsaftaris

Partner: Department of Ophthalmology and Optometry, Medical University of Vienna
              Lab for Ophthalmic Image Analysis, Medical University of Vienna

Funding: FWF (Research Groups programme)

Any disease of the retina at the back of the eye directly impacts visual performance and readily puts vision at risk often leading to practical blindness. For this reason, we need better understanding of retinal disease and their progression patterns to find good retinal treatment solutions. Personalized medicine is an emerging approach where medical decisions and therapies are being tailored to the individual patient.

Today, innovations in medical imaging allow an extraordinarily detailed view into one's health condition. The introduction of optical coherence tomography (OCT) imaging provides a view of the retina in three-dimensions and in very fine detail. The analysis of the sheer volume of information about patients, disease progression and OCT images even exceeds the human capabilities.  

In the last decade, artificial intelligence (AI) has revolutionized various fields of science in an unprecedented manner. There is relentless pressure and expectation to deploy AI in medicine, especially in image-intensive branches. In Ophthalmology, it has already achieved super‑human performance in image diagnosis. Nevertheless, despite initial successes, most of AI’s enormous potential is still to be realized, and in ophthalmology it remains heavily under‑exploited.

This Research Group has an overarching goal to identify populations of similar retinal patients and build clinical decision support tools to improve treatment of an individual patient. We focus on developing, improving and applying AI methods to analyze OCT images of retina and we investigate machine learning methods that can provide individual prognosis of disease advance. The Group is composed of four world-class and pioneering researchers from the Medical University of Vienna (Ursula Schmidt-Erfurth, opens an external URL in a new window and Hrvoje Bogunović, opens an external URL in a new window) with expertise in ophthalmology and medical imaging, and the Johannes Kepler University (Sepp Hochreiter and Günter Klambauer, opens an external URL in a new window) with expertise in AI. They are joining their complimentary expertise with the goal of introducing AI-based personalized medicine into the management of the leading eye diseases of modern times.

Publications

Author(s):
Published:
Andreas Fürst, Elisabeth Rumetshofer, Johannes Lehner, Viet T. Tran, Fei Tang, Hubert Ramsauer, David Kreil, Michael Kopp, Günter Klambauer, Angela Bitto, Sepp HochreiterAdvances in Neural Information Processing Systems 35 (2022): 20450-20468
Link:
Andreas Fürst, Elisabeth Rumetshofer, Johannes Lehner, Viet T. Tran, Fei Tang, Hubert Ramsauer, David Kreil, Michael Kopp, Günter Klambauer, Angela Bitto, Sepp HochreiterOfficial Publication (HTML), opens an external URL in a new window
Author(s): Andreas Fürst, Elisabeth Rumetshofer, Johannes Lehner, Viet T. Tran, Fei Tang, Hubert Ramsauer, David Kreil, Michael Kopp, Günter Klambauer, Angela Bitto, Sepp Hochreiter
Published: Advances in Neural Information Processing Systems 35 (2022): 20450-20468
Link: Official Publication (HTML), opens an external URL in a new window

 

Author(s):
Published:
Andreas Mayr, Sebastian Lehner, Arno Mayrhofer, Christoph Kloss, Sepp Hochreiter, Johannes Brandstetter

Proceedings of the AAAI Conference on Artificial Intelligence (2023): 9099-9107

Link:
Andreas Mayr, Sebastian Lehner, Arno Mayrhofer, Christoph Kloss, Sepp Hochreiter, Johannes Brandstetter

Official Publication (HTML), opens an external URL in a new window

Supplementary (HTML), opens an external URL in a new window

Code:
Andreas Mayr, Sebastian Lehner, Arno Mayrhofer, Christoph Kloss, Sepp Hochreiter, Johannes BrandstetterGithub, opens an external URL in a new window
Author(s): Andreas Mayr, Sebastian Lehner, Arno Mayrhofer, Christoph Kloss, Sepp Hochreiter, Johannes Brandstetter
Published:

Proceedings of the AAAI Conference on Artificial Intelligence (2023): 9099-9107

Link:

Official Publication (HTML), opens an external URL in a new window

Supplementary (HTML), opens an external URL in a new window

Code: Github, opens an external URL in a new window

Author(s):
Published:
Bo Qian, Hao Chen, Xiangning Wang, Haoxuan Che, Gitaek Kwon, Jaeyoung Kim, Sungjin Choi, Seoyoung Shin, Felix Krause, Markus Unterdechler, Junlin Hou, Rui Feng, Yihao Li, Mostafa El Habib Daho, Qiang Wu, Ping Zhang, Xiaokang Yang, Yiyu Cai, Weiping Jia, Huating Li, Bin ShengarXiv preprint arXiv:2304.02389
Link:
Bo Qian, Hao Chen, Xiangning Wang, Haoxuan Che, Gitaek Kwon, Jaeyoung Kim, Sungjin Choi, Seoyoung Shin, Felix Krause, Markus Unterdechler, Junlin Hou, Rui Feng, Yihao Li, Mostafa El Habib Daho, Qiang Wu, Ping Zhang, Xiaokang Yang, Yiyu Cai, Weiping Jia, Huating Li, Bin ShengOfficial Publication (HTML), opens an external URL in a new window
Comment:
Bo Qian, Hao Chen, Xiangning Wang, Haoxuan Che, Gitaek Kwon, Jaeyoung Kim, Sungjin Choi, Seoyoung Shin, Felix Krause, Markus Unterdechler, Junlin Hou, Rui Feng, Yihao Li, Mostafa El Habib Daho, Qiang Wu, Ping Zhang, Xiaokang Yang, Yiyu Cai, Weiping Jia, Huating Li, Bin ShengA group of students from Johannes Kepler University Linz worked together with a  member from Medical University Vienna under the supervision of members from both universities on the DRAC 2022 challenge and was ranked nr. 3 in the segmentation task (best university in this task). Official release of final ranking (HTML), opens an external URL in a new window. The two student team leaders were invited to be coauthors on a general "summary, analysis and results"-publication of the challenge.
Author(s): Bo Qian, Hao Chen, Xiangning Wang, Haoxuan Che, Gitaek Kwon, Jaeyoung Kim, Sungjin Choi, Seoyoung Shin, Felix Krause, Markus Unterdechler, Junlin Hou, Rui Feng, Yihao Li, Mostafa El Habib Daho, Qiang Wu, Ping Zhang, Xiaokang Yang, Yiyu Cai, Weiping Jia, Huating Li, Bin Sheng
Published: arXiv preprint arXiv:2304.02389
Link: Official Publication (HTML), opens an external URL in a new window
Comment: A group of students from Johannes Kepler University Linz worked together with a  member from Medical University Vienna under the supervision of members from both universities on the DRAC 2022 challenge and was ranked nr. 3 in the segmentation task (best university in this task). Official release of final ranking (HTML), opens an external URL in a new window. The two student team leaders were invited to be coauthors on a general "summary, analysis and results"-publication of the challenge.

Author(s):
Published:
Emese Sükei, Elisabeth Rumetshofer, Niklas Schmidinger, Ursula Schmidt-Erfurth, Günter Klambauer, Hrvoje BogunovićInternational Conference on Medical Imaging with Deep Learning (MIDL)
Link:
Emese Sükei, Elisabeth Rumetshofer, Niklas Schmidinger, Ursula Schmidt-Erfurth, Günter Klambauer, Hrvoje BogunovićOfficial Publication (HTML), opens an external URL in a new window
Video:
Emese Sükei, Elisabeth Rumetshofer, Niklas Schmidinger, Ursula Schmidt-Erfurth, Günter Klambauer, Hrvoje BogunovićPresentation, opens an external URL in a new window
Author(s): Emese Sükei, Elisabeth Rumetshofer, Niklas Schmidinger, Ursula Schmidt-Erfurth, Günter Klambauer, Hrvoje Bogunović
Published: International Conference on Medical Imaging with Deep Learning (MIDL)
Link: Official Publication (HTML), opens an external URL in a new window
Video: Presentation, opens an external URL in a new window

Author(s):
Published:
Lisa Schneckenreiter, Richard Freinschlag, Florian Sestak, Johannes Brandstetter, Günter Klambauer, Andreas MayrThe Second Tiny Papers Track at ICLR 2024
Link:
Lisa Schneckenreiter, Richard Freinschlag, Florian Sestak, Johannes Brandstetter, Günter Klambauer, Andreas MayrArXiv, opens an external URL in a new window
Official Publication (HTML), opens an external URL in a new window
Code:
Lisa Schneckenreiter, Richard Freinschlag, Florian Sestak, Johannes Brandstetter, Günter Klambauer, Andreas MayrGithub, opens an external URL in a new window
pytorch-geometric, opens an external URL in a new window
Author(s): Lisa Schneckenreiter, Richard Freinschlag, Florian Sestak, Johannes Brandstetter, Günter Klambauer, Andreas Mayr
Published: The Second Tiny Papers Track at ICLR 2024
Link: ArXiv, opens an external URL in a new window
Official Publication (HTML), opens an external URL in a new window
Code: Github, opens an external URL in a new window
pytorch-geometric, opens an external URL in a new window

Author(s):
Published:
Niklas Schmidinger, Lisa Schneckenreiter, Philipp Seidl, Johannes Schimunek, Pieter-Jan Hoedt, Johannes Brandstetter, Andreas Mayr, Sohvi Luukkonen, Sepp Hochreiter, Günter Klambauer

arXiv Preprint arXiv:2411.04165

Link:
Niklas Schmidinger, Lisa Schneckenreiter, Philipp Seidl, Johannes Schimunek, Pieter-Jan Hoedt, Johannes Brandstetter, Andreas Mayr, Sohvi Luukkonen, Sepp Hochreiter, Günter KlambauerArXiv, opens an external URL in a new window
Code:
Niklas Schmidinger, Lisa Schneckenreiter, Philipp Seidl, Johannes Schimunek, Pieter-Jan Hoedt, Johannes Brandstetter, Andreas Mayr, Sohvi Luukkonen, Sepp Hochreiter, Günter Klambauer

Github code for DNA-xLSTM, opens an external URL in a new window
Github code for Prot-xLSTM, opens an external URL in a new window
Github code for Chem-xLSTM, opens an external URL in a new window

Author(s): Niklas Schmidinger, Lisa Schneckenreiter, Philipp Seidl, Johannes Schimunek, Pieter-Jan Hoedt, Johannes Brandstetter, Andreas Mayr, Sohvi Luukkonen, Sepp Hochreiter, Günter Klambauer
Published:

arXiv Preprint arXiv:2411.04165

Link: ArXiv, opens an external URL in a new window
Code:

Github code for DNA-xLSTM, opens an external URL in a new window
Github code for Prot-xLSTM, opens an external URL in a new window
Github code for Chem-xLSTM, opens an external URL in a new window