Hannah Marienwald
Hannah Marienwald
Doctoral Researcher
Affiliation: BIFOLD
Hannah Marienwald is a doctoral researcher under supervision of Prof. Dr. K.-R. Müller and is receiving a BIFOLD stipend. Before that, she was a member of the BIFOLD Graduate School and worked as a research associate at the Institute of Mathematics, Mathematical Statistics and Machine Learning, at Universität Potsdam in cooperation with BZML and the Data Engineering Systems group at the Hasso-Plattner Institute. She obtained her B.Sc. and M.Sc. degree in computer science with strong focus on ML, statistics, and probability theory at the Technische Universität Berlin. During her studies, she gained teaching experience as student teaching assistant of the Machine Learning Group (TU Berlin) for numerous courses.
PhD Title: Theoretical Analysis of Learning Multiple Problems
Computational Pathology, Clever Hans Learning, Foundation Models, Kernel Methods, Kernel Mean Embeddings
Jonah Kömen, Edwin D. de Jong, Julius Hense, Hannah Marienwald, Jonas Dippel, Philip Naumann, Eric Marcus, Lukas Ruff, Maximilian Alber, Jonas Teuwen, Frederick Klauschen, Klaus-Robert Müller
Towards Robust Foundation Models for Digital Pathology
Jonah Kömen, Hannah Marienwald, Jonas Dippel, Julius Hense
Do Histopathological Foundation Models Eliminate Batch Effects? A Comparative Study
Gilles Blanchard, Jean-Baptiste Fermanian, Hannah Marienwald
Estimation of multiple mean vectors in high dimension
A benchmark for trustworthy clinical AI
A new study published in Nature Communications shows that today's pathology foundation models can be influenced by the origin of a tissue sample. Researchers at BIFOLD and Aignostics developed PathoROB, a first-of-its-kind benchmark to measure and reduce this bias, shaping how the next generation of pathology AI is built.