From Single-Hospital to Multi-Centre Applications: Enhancing the Generalisability of Deep Learning Models for Adverse Event Prediction in the ICU

3 code implementations • 27 Mar 2023 • Patrick Rockenschaub, Adam Hilbert, Tabea Kossen, Falk von Dincklage, Vince Istvan Madai, Dietmar Frey

This suggests that as data from more hospitals become available for training, model robustness is likely to increase, lower-bounding robustness with the performance of the most applicable data source in the training data.

Anonymization of labeled TOF-MRA images for brain vessel segmentation using generative adversarial networks

1 code implementation • 9 Sep 2020 • Tabea Kossen, Pooja Subramaniam, Vince I. Madai, Anja Hennemuth, Kristian Hildebrand, Adam Hilbert, Jan Sobesky, Michelle Livne, Ivana Galinovic, Ahmed A. Khalil, Jochen B. Fiebach, Dietmar Frey

Besides, we showed that synthetic patches can be used in a transfer learning approach with independent data.

Medical Image Analysis Transfer Learning