Excited to share our new paper (CVPR 2026 🚀): "MuViT: Multi-Resolution Vision Transformers for Learning Across Scales in Microscopy" which enables local predictions to use global context.
Great work led by @albertdm.bsky.social & another fun collab w @gioelelamanno.bsky.social! @scadsai.bsky.social
It was such a creative supporting environment. Big thank you to all our speakers, Dr. Riccardo Massei, Dr. @fraukeb.bsky.social, @michaelaun.bsky.social and Ronny Gey for the great discussion! And to Dr. Cornelia Wetzker who was giving invaluable input during the preparation of this discussion. 2/3
Super grateful that the @ymia.gerbi-gmb.de and especially @enicolay.bsky.social helped me to bring the vision of this panel discussion to life. 🚀⭐ It was an incredible experience to moderate this event. I truly hope that this panel discussion gives some new & different insights. Enjoy listening! 1/3
Would have been impossible without you Elan! 🫶
Happy New Year YMIA! Another full year has come to an end: we hosted microscopy watchparties, joined key imaging conferences & organized a panel on Open Data in Bioimage Analysis (available soon on YouTube) In 2026, expect invited talks on practical image analysis & more opportunities to connect🍀🥂🔬🎉
Lea Kabjesz, Lea Gihlein, @marabuuuu.bsky.social and Luisa Götze led a workshop at @scadsai.bsky.social General Assembly, titled “Coding Effectively with AI: Getting Started with Cursor and Copilot”. The slides are free and suitable for beginners.
👉 https://f.mtr.cool/ajbildzipj
#SmartPrompts
Poster for the panel discussion: The Power of Sharing: Open Data in Bio-image Analysis on October 24, 2025 starting 1:30 pm on site at the KUBUS Hall 1A, UFZ Leipzig or online starting at 2:00 pm. In the lower part of the poster the experts are listed with pictures and names, as well as the moderation.
Save the date for the panel discussion “The Power of Sharing: Open Data in Bioimage Analysis” on October 24, 2025. 🤝
The discussion with experts from various fields related to imaging is organized by Young Microscopists and Image Analysts (YMIA).
Register here:
👉 gerbi-gmb.de/machform/vie...
Oh yes-the one and only Robert Haase @haesleinhuepf.bsky.social
From #GrandTheftAuto to the impact AI is having on #bioimaging.
+the challenges of creating AI courses for bioimage analysis, & his unique perspective as a programmer-turned-biologist.
Stream- bit.ly/microscopist...
@globias.bsky.social
⭕ This week at @scadsai.bsky.social :
We held the 2nd General Assembly in 2025 in Leipzig. The program included talks, workshops, and a poster session. We awarded the "Best PhD Poster Award" to Lea Gihlein, Lea Kabjesz, and Maja Schneider.👏
👉 https://scads.ai/2nd-general-assembly-2025-in-leipzig/
(1/14) I’m happy and proud to introduce: SpinePy – a framework to detect the "spine" of gastruloids and measure biological and physical signals in a local dynamic 3D coordinate system. www.biorxiv.org/content/10.1...
Ensuring reproducibility in GUI-based bio-image analysis tools can be tricky, so I wrote this new blog post on @focalplane.bsky.social. It highlights features in Napari, Fiji, QuPath, Galaxy, CellProfiler and JIPipe that support workflow saving and sharing. Hope it helps! 🤗🔬👩💻Feedback 💛ly welcome!
I finally managed to upload the first version of the napari-czitools plugin (still in alpha - expect issues...)
- open complete CZI images or subsets
- read CZI metadata
pypi.org/project/napa...
or
github.com/sebi06/napar...
Hot off the press!!! Proudly presenting our lab's new review on how do cells communicate to control organ size :) We focus specially on dynamic connections that operate at different timescales to regulate organ growth and morphogenesis. #devbio #SizeandShape www.sciencedirect.com/science/arti...
Ensuring reproducibility in GUI-based bio-image analysis tools can be tricky, so I wrote this new blog post on @focalplane.bsky.social. It highlights features in Napari, Fiji, QuPath, Galaxy, CellProfiler and JIPipe that support workflow saving and sharing. Hope it helps! 🤗🔬👩💻Feedback 💛ly welcome!
And we are students after all 🤷♀️🤣
truly one hour of debugging can save you five minutes of reading documentation
If you seek for an AI coding buddy to review your code and provide umprompted feedback, try out _unprompted_! I hope it helps to identify issues in code early! 🖥️🤖💫
pip install unprompted
github.com/haesleinhuep...
Michele Bortolomeazzi, Christian Schmidt and Jan-Philipp Mallm at @nfdi4bioimage.bsky.social have developed a new OMERO-web plugin: OMERO-vitessce. It enables the visualization of datasets hosted in #OMERO with the #Vitessce multimodal data viewer.
Find the poster here:
👉 zenodo.org/records/1483...
New ‘How to’ post on FocalPlane 🔬💻
Lea Kabjesz shares a step-by-step guide to get you started annotating 2D and 3D images in Cellpose, including video tutorials.
focalplane.biologists.com/2025/06/05/a...
#bioimageanalysis #cellpose #imaging #HowTo
Example of why I think current LLMs are enough to change lots of work even if they don’t get better, once we start integrating them with other systems
GPT-4 (now obsolete) went from 30% accuracy to 87% accuracy in clinical oncology decisions when given access to tools www.nature.com/articles/s43...
Who does microscopy and has never heard of Bio-Formats? You probably used it anyway
Help! Let’s say I have 200 scientific papers in my digital to-read pile
I could stay in denial, or I could ask AI for help.
Any workflows/tools to group them in some meaningful way? This alone would help mental load as I at least read abstracts
And/or any good summary tools?
For discovering relations between papers "connected papers" and "research rabbits" are tools that I like using. If you want to dive deeper into the content of one specific paper "notebookLM" as already suggested above might help.
I regularly point collaborators at this segmentation quality assurance blog post by @marabuuuu.bsky.social , because some scientists get trapped in a segmentation-improvement-loop without ever measuring how good an algorithm actually is. focalplane.biologists.com/2023/04/13/q...
If you use ML for pixel classification, e.g. using sckit-learn, you can use SHAP analysis for explaining how relevant the feature images are you provided.
I just added a Notebook demonstrating how to do this to the #BioImageAnalysisNotebooks 🔬🖥️📈
haesleinhuepf.github.io/BioImageAnal...
Glad that it helps, thanks for sharing! 🌻
Thanks for reading and sharing!😇
Image normalization: trivial enough to automate, impactful enough to quietly sabotage your results.
Here’s a Jupyter notebook I wrote on how, why & when normalization matters, feedback 💛ly welcome.
👇
haesleinhuepf.github.io/BioImageAnal...
The YMIA would like to invite everyone interested in microscopy and image analysis to our weekly watch-parties.
This Tuesday we cover how to choose the right microscope for your experiment as well as learning how to minimize damage to samples during light microscopy.
