News
Notes from the intersection of deep learning and microscopy data — breakthroughs in pathology, new datasets, and results from the group.
-
How reproducible is AI-research in Veterinary Pathology?
Reproducibility in science is not a “nice to have”, but a prerequisite. However, reproducibility depends on accurate reporting of all relevant details of an experiment. This is especially important…
-
Insights from the MIDOG 2025 Challenge Paper
We are happy to share that the first preprint of the MIDOG 2025 challenge paper is now available at this link: http://arxiv.org/abs/2606.07368 The most interesting results from this third iteration…
-
muROMI – Dataset Dashboard
In our muROMI project (funded by the Deutsche Forschungsgemeinschaft (DFG) – German Research Foundation and the Austrian Science Fund FWF ) we are busy creating the world’s biggest and most diverse…
-
(mu)ROMI – Building the biggest and most diverse mitotic figure dataset
Every now and then we like to share some views “behind the scenes” of our research group, covering topics that haven’t seen the light of day yet. This time, we want to share about the progress of our…
-
2nd Flensburg Symposium on AI & Human Factors
We’re happy to be part of the 2nd Flensburg Symposium on AI & Human Factors. We will have a multitude of fascinating talks at the intersection of Artificial Intelligence and Human Factors. The event…
-
Benchmarking Foundation Models for Mitotic Figure Classification
In the rapidly evolving field of computational pathology, foundation models (FMs) have become the new hot topic. These models, trained on millions of unlabeled tissue tiels using self-supervised…
-
DECOMP [WACV26]: A Faster, Smarter Way to Choose What to Label in Dense Prediction Tasks
Training models for dense prediction tasks, such as segmentation, require a large amount of detailed annotation. This burden is even heavier in histopathology, where tissues within the same class can…
-
Jonas Ammeling Secures Third Prize at BayWISS 2025 for Pioneering AI in Digital Pathology
We are pleased to announce that Jonas Ammeling has received the third prize at this year’s Bayerisches Wissenschaftsforum (BayWISS) for his research on “Artificial Intelligence in Digital Pathology:…
-
Research staff position in Robotics and AI
We are currently looking for a talented engineer / researcher to join our team in the RobOdin project. About the project: The RobOdin project is an international project (Germany / Denmark) with lots…
-
Adapting Foundational VLMs to a Histopathology Task Without any Labels [COMPAYL25 paper (oral)]
Vision-Language Models (VLMs) are trained with images in conjunction with text descriptions, which helps them capture complex visual signal. By learning from large datasets with millions of…
-
When Histology Reveals More Than Intended: Patient Re-identification from Digital Slides
The digitization of histopathology slides has transformed how we diagnose and study disease. With the help of powerful deep learning algorithms, computers can now analyze tumor slides at an…
-
Is Self-Supervision Enough? Apparently not for Mitotic Figure Detection. [BVM 2025 paper]
In the fast-moving world of AI in digital pathology, foundation models (FMs) are making big waves. These powerful models, trained on massive amounts of histopathology data, promise to revolutionize…
-
Flensburg Symposium on Human Computer Interaction and Deep Learning
We hereby invite scientists and professionals from the field of deep learning and human computer interaction to participate in our first symposium on these topics to be held at Flensburg University…
-
When Precision Meets Ambiguity: Information Mismatch in PHH3-Assisted Mitosis Annotation Leads to Interpretation Shifts in H&E Slide Analysis
Histopathology is a very important part of diagnosing and understanding tumors, with mitotic figure (MF) counts serving as a cornerstone in assessing tumor aggressiveness. But what happens when the…
-
Using Large Language Models for Tumor Board Procedural Recommendations
Tumor boards are meetings where specialists from many disciplines meet and discuss the potential treatment lines for cancer patients. It is known that these expert conferences contribute to better…
-
Leveraging Image Captions for Streamlining Histopathology Image Annotation [MICCAI 2024 paper]
Counting mitotic figures (MFs) under a microscope is a crucial component for tumor diagnosis and therapy planning. Our research group has been dedicated to automating this task through…
-
PhD/Post-Doc Position in AI-Assisted Tumor Characterization (3 Years)
Join us at Hochschule Flensburg, an innovative campus with 3,200 students and top-tier facilities located along the scenic Baltic Sea coast! Starting on 01.09.2024, we are seeking a passionate PhD…
-
MIDL 2024: Robust mitosis detection in multiple cancer types – learnt solely from animal tissue samples
We have another paper on MIDL 2024, and we want to briefly give you an overview here. It is about the detection of mitotic figures (cells undergoing cell division), which is really important in the…
-
MIDL 2024: Quilt-Cleaner, a pipeline for automatic cleaning of the QUILT-1M dataset.
We will be representing our research again this year at Medical Imaging with Deep Learning (MIDL), to be held in Paris July 3-5th. Here’s a quick summary of one of the research works that we will be…
-
MIDL 2024 – An unofficial peek into the peer review results
The decisions on the MIDL (Medical Imaging with Deep Learning) 2024 conference, which will be held in Paris in July, have just been sent out. Since MIDL uses openreview, it is possible to scrape the…
-
Few Shot Learning for Enhanced Surgical Imaging in Head and Neck Cancer
The advancements in surgical techniques for head and neck cancer have significantly improved patient survival rates. Precision in tumor excision is crucial for successful surgery, and frozen sections…
-
Focus on Content not Noise: Suppressing CycleGAN Steganography for Microscopy Image Generation
Are you tired of painstakingly annotating nuclei in microscopy images for neural network training? Join the club! But here’s the good news – we can generate our own training data without the need of…
-
Insights from the 2022 edition of the MIDOG MICCAI Challenge
At MICCAI 2022, we held the second edition of the MItosis DOmain Generalization (MIDOG) challenge. The challenge was about detecting mitotic figures (depicting cells undergoing cell division) in…
-
Survival Prediction on Tissue Micro Arrays [BVM 2023 paper]
Jonas Ammeling from our group recently presented a paper on the prediction of survival of lung cancer patients from tiny tissue parts (from a tissue micro array) using attention-based multiple…
-
The merits and weaknesses of Average Precision
When you are dealing with the evaluation of machine learning models, and in particular if you are working on object detection, you have come across the Average Precision metric. It is often thought…
-
MIDOG++ – The largest multi-domain mitotic figure dataset
TL; DR: The MIDOG++ multi-domain mitotic figure dataset sets a new benchmark with 503 included cases across 7 domains with 12k annotations in total. MIDOG++ – The largest multi-domain mitotic figure…
-
Reducing the annotation effort for microscopy images [MICCAI 2023 paper]
When working with gigantic images – we’re talking 100,000 by 100,000 pixels here – things can get a little tricky. These are known as Whole Slide Images (WSIs), and are often used in medical…
-
Detection of Atypical Mitotic Figures [BVM2023 Talk]
TLDR: Watch our youtube-video at the end of the post. In our recent work, we dig into the topic of not only detecting mitotic figures in histopathology slides but also of classifying them into…
-
See you at BVM in Braunschweig
Our group will be represented with 8 contributions at the BVM workshop ( https://bvm-workshop.org ). There will be five talks, two of them are short-listed * for the best paper award: Frauke Wilm:…
-
MIDOG 2022 proceedings published
We are happy to report that the proceedings of the Mitosis Domain Generalization Challenge (MIDOG) 2022 have been recently published as a joint volume with the DRAC challenge by Springer. We thank…
-
Mind the Gap: Scanner-induced domain shifts pose challenges for representation learning in histopathology [ISBI23 paper]
Frauke Wilm from our group has presented her latest work on overcoming domain shifts in histopathology on the 2023 IEEE International Symposium on Biomedical Imaging. In brief, our innovative method,…
-
Introducing deepmicroscopy.org
Deepmicroscopy.org is the new home for the projects of the joint research group of Prof. Katharina Breininger (FAU Erlangen-Nürnberg, Germany) and Marc Aubreville (TH Ingolstadt, Germany). We’ve been…
