An enormous "𝐭𝐡𝐚𝐧𝐤 𝐲𝐨𝐮" goes to the fantastic #MicroSplit team... covering contributions from hard-core method development, over research software engineering mastery, to lots and lots of dataset generation and fruitful discussions on results and possible ways to improve.
Thank you all! ❤️
Artifact removal example with MicroSplit.
Oh, and… did I mention you can also remove artifacts (ie., structured noise) from your data?
This #MicroSplit micro-🧵 is meant as a little teaser.
Full story (a massive collaborative effort with a ton of amazing people) will drop next week. 🤩
Example of two cellular structures unmixed with MicroSplit
And as a bonus, #MicroSplit gets rid of noise in your micrographs. (“Input” and “Target” is what was imaged at the 🔬, the predictions are what MicroSplit hands you after seeing only the input.)
👇Here an example for unmixing two rather noisy structures👇
Schematic overview on how MicroSpit operates. It can split superimposed structures in fluorescent image channels by using a suitably trained AI.
Concrete example for how MicroSplit unmixes four superimposed structures.
Immagine you could image two cellular structures in the same fluorescent channel and still reliably get them separated afterwards…
What would you do with this?
Now… what would you do if that also worked with 4 structures at once? 👇 #MicroSplit #preview🧵
