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, opens an external URL in a new window 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): 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): 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.