no code implementations • 6 Nov 2023 • Michael Gadermayr, Lukas Koller, Maximilian Tschuchnig, Lea Maria Stangassinger, Christina Kreutzer, Sebastien Couillard-Despres, Gertie Janneke Oostingh, Anton Hittmair
Here we conduct a large study incorporating 10 different data set configurations, two different feature extraction approaches (supervised and self-supervised), stain normalization and two multiple instance learning architectures.
no code implementations • 14 Mar 2023 • Petra Tschuchnig, Manfred Mayr, Maximilian Tschuchnig, Peter Haber
To detect the most commons-compatible implementation, the different implementation options through conventional platform intermediators, an open source blockchain with PoW as well as Interlaces' permissioned blockchain approach, are compared.
no code implementations • 13 Mar 2023 • Maximilian Tschuchnig, Petra Tschuchnig, Cornelia Ferner, Michael Gadermayr
Our results demonstrate that a transformer based neural network can outperform classical regression and machine learning models in certain inflation rates and forecasting horizons.
1 code implementation • 10 Nov 2022 • Michael Gadermayr, Lukas Koller, Maximilian Tschuchnig, Lea Maria Stangassinger, Christina Kreutzer, Sebastien Couillard-Despres, Gertie Janneke Oostingh, Anton Hittmair
Multiple instance learning exhibits a powerful approach for whole slide image-based diagnosis in the absence of pixel- or patch-level annotations.
no code implementations • 9 Jun 2022 • Michael Gadermayr, Maximilian Tschuchnig
Multiple instance learning exhibits a powerful tool for learning deep neural networks in a scenario without fully annotated data.
no code implementations • 15 Dec 2020 • Michael Gadermayr, Maximilian Tschuchnig, Lea Maria Stangassinger, Christina Kreutzer, Sebastien Couillard-Despres, Gertie Janneke Oostingh, Anton Hittmair
In contrast to paraffin sections, frozen sections can be quickly generated during surgical interventions.
no code implementations • 23 Apr 2020 • Michael Gadermayr, Maximilian Tschuchnig, Laxmi Gupta, Dorit Merhof, Nils Krämer, Daniel Truhn, Burkhard Gess
Generative adversarial networks using a cycle-consistency loss facilitate unpaired training of image-translation models and thereby exhibit a very high potential in manifold medical applications.