no code implementations • 6 Mar 2024 • Thomas Pinetz, Erich Kobler, Robert Haase, Julian A. Luetkens, Mathias Meetschen, Johannes Haubold, Cornelius Deuschl, Alexander Radbruch, Katerina Deike, Alexander Effland
Recently, deep learning (DL)-based methods have been proposed for the computational reduction of gadolinium-based contrast agents (GBCAs) to mitigate adverse side effects while preserving diagnostic value.
no code implementations • 29 Sep 2023 • Mariana Lindo, Ana Sofia Santos, André Ferreira, Jianning Li, Gijs Luijten, Gustavo Correia, Moon Kim, Benedikt Michael Schaarschmidt, Cornelius Deuschl, Johannes Haubold, Jens Kleesiek, Jan Egger, Victor Alves
In this study, the generation of radiology impressions in different languages was automated by fine-tuning a model, publicly available, based on a multilingual text-to-text Transformer to summarize findings available in English, Portuguese, and German radiology reports.
1 code implementation • 25 Jul 2023 • Alexander Jaus, Constantin Seibold, Kelsey Hermann, Alexandra Walter, Kristina Giske, Johannes Haubold, Jens Kleesiek, Rainer Stiefelhagen
We examine its plausibility and usefulness using three complementary checks: Human expert evaluation which approved the dataset, a Deep Learning usefulness benchmark on the BTCV dataset in which we achieve 85% dice score without using its training dataset, and medical validity checks.
1 code implementation • 30 Jun 2023 • Frederic Jonske, Moon Kim, Enrico Nasca, Janis Evers, Johannes Haubold, René Hosch, Felix Nensa, Michael Kamp, Constantin Seibold, Jan Egger, Jens Kleesiek
It is an open secret that ImageNet is treated as the panacea of pretraining.
no code implementations • 1 May 2023 • Charlie Cowen-Breen, Creston Brooks, Johannes Haubold, Barbara Graziosi
This paper presents machine-learning methods to address various problems in Greek philology.
no code implementations • 19 May 2022 • Moritz Rempe, Florian Mentzel, Kelsey L. Pomykala, Johannes Haubold, Felix Nensa, Kevin Kröninger, Jan Egger, Jens Kleesiek
Results: Both datasets were very similar to the ground truth (DICE scores of 92\%-98\% and Hausdorff distances of under 5. 5 mm).