PhD Student at @bifoldberlin and @ml_tuberlin. Computational Pathology, XAI, Multimodal ML, Representation Learning.
Berlin
Joined June 2012
- Tweets14
- Following140
- Followers54
- Likes34
Pinned Tweet
✨ Our xMIL paper has been accepted at #NeurIPS2024 ✨
arXiv preprint: arxiv.org/abs/2406.04280
Julius Hense retweeted
Original Article by @jdppel et al.: AI-Based Anomaly Detection for Clinical-Grade Histopathological Diagnostics nejm.ai/3YwvUZz
#ArtificialIntelligence
ALT Figure 4. Heatmap Visualization of Anomaly Detection Results (Outlier Exposure Approach).
Julius Hense retweeted
A deep anomaly detection approach for histopathology shows high detection performance for a broad range of diseases (including all cancers) within the long diagnostic tail in gastrointestinal biopsies. Read the full article by @jdppel et al.: nejm.ai/3YwvUZz
ALT Figure 2. Clinical Use Case and Overview of Anomaly Detection Approach.
❓ Do histopathological foundation models eliminate batch effects? ❓
The surprisingly clear answer is: they do not!
Find out more in our new paper that we will present at the AIM-FM Workshop at @NeurIPSConf.
Link: arxiv.org/abs/2411.05489
Big congrats to our shooting star Jonah Kömen, who produced these results in his Bachelor thesis (‼), to my amazing co-advisors Hannah Marienwald and @jdppel, and to everyone involved at @bifoldberlin and @ml_tuberlin.
Julius Hense retweeted
If two models are more similar to each other than a third on ImageNet, will this hold for medical/ satellite images? Our preprint analyzes how vision model similarities generalize across datasets, the factors that influence them, and their link to downstream task behavior. 🧵1/7
Julius Hense retweeted
🎉 Thrilled to announce that our paper MambaLRP has been accepted at #NeurIPS2024!
Explain your Mamba models in a faithful, efficient, and effective way! 🐍
Huge thanks to @EberleOliver, Grégoire Montavon, and Klaus-Robert Müller @bifoldberlin, @ml_tuberlin , @GoogleDeepMind,
Julius Hense retweeted
Our work on historical insights at scale using machine learning is now out in @ScienceAdvances! Very proud of this team effort, bridging disciplines and institutions—@MPIWG @TUBerlin @bifoldberlin @ml_tuberlin
📜science.org/doi/10.1126/scia…
Julius Hense retweeted
🧵I am excited to share that our paper: AI-Based Anomaly Detection for Clinical-Grade Histopathological Diagnostics has now been published in @NEJM_AI .
ai.nejm.org/doi/full/10.1056…
✨ Our paper on Anomaly Detection for Histopathology has been published in @NEJM_AI ✨
Our paper shows how to build AI that detects ANY infrequent disease without training data collection.
Link: ai.nejm.org/doi/full/10.1056…
Massive congrats to the incredibly talented first authors @jdppel and @n_prenissl, as well as to the whole team: Philipp Liznerski, Tobias Winterhoff, Simon Schallenberg, Marius Kloft, Oliver Buchstab, David Horst, Maximilian Alber, @lukasruff, Klaus-Robert Müller, @FKlauschen.
Julius Hense retweeted
🔊
Proud that our lab has four #NeurIPS2024 publications this year! 🎉
Check them out 👇
#MachineLearning #Artificalintelligence
Julius Hense retweeted
🚨 PhD Opportunity! 🚨
Apply your skills in #DeepLearning & #ComputerVision to cancer research! Join us to study B cell dynamics & ECM in melanoma, using cutting-edge imaging & multiomics like #SpatialTranscriptomics.
Apply: colcc.ac.uk/2025-phd-project…
@CRUKCOLcentre @QMBCI
Big thanks to my collaborators and mentors, first and foremost @IdajiMina, as well as @EberleOliver, @thomschnake, @jdppel, @lciernik, Oliver Buchstab, @am0ck, Frederick Klauschen, Klaus-Robert Müller, and all the supporters from @bifoldberlin and @ml_tuberlin.