🔬 We’re also releasing a massive new dataset — over 600,000 annotated nucleus images — now freely available on the BioImage Archive.

www.ebi.ac.uk/biostudies/b...

All of the segmentation and morphometric analysis was done with the open-source platform QuPath. The scripts I wrote are on Github and the raw images are on the BioImage Archive, because open-source is the way to go!

But seriously, look at these cells! They are so angry.

Thanks for highlighting the MIFA guidelines! We’re excited to see how they’ll help advance AI in bioimage analysis.

@florianjug.bsky.social, @joshmoore.bsky.social, @arratemunoz.bsky.social, @perrinegil.bsky.social, @gnodar.bsky.social, @martinjones.bsky.social, @aybukey.bsky.social, @lucamarconato.bsky.social, @nilsnorlin.bsky.social, @astitchyscientist.bsky.social, @normanrz.com, @virginieuhlmann.bsky.social

MIFA rests on 4 key pillars:
- Clear metadata for annotations
- Incentivise the production of annotated datasets
- Reduce the number of formats used for annotations
- Make data accessible to all

Huge thanks to all collaborators—can’t wait to see MIFA in action!

Such a beautiful (and useful) dataset! 🐟✨

Wonderful! Please keep us in mind 🙂

Mesmerising! Are these images publicly available?