About IQUANA¶
Intelligent QUantification, ANnotation and Analysis.
IQUANA is a research tool built at DFKI in partnership with HIFMB, for AI-assisted segmentation, annotation and quantification of scientific image datasets.
The name¶
The letters map onto the words like this, and the capitalisation is part of the name rather than decoration:
| Letters | Word |
|---|---|
| I | Intelligent — also read as Interactive or Imaging |
| QU | QUantification |
| AN | ANnotation |
| A | Analysis |
The I is deliberately more than one word. The tool is intelligent in that it puts models behind the work, interactive in that a human stays in the loop around every prediction, and about imaging because that is what it measures — and none of the three is the whole story on its own. The landing page turns the reading over on purpose.
When writing it out, keep the split as I · QU · AN · A. Writing it as QUANtification, Annotation is wrong: it borrows the AN from the wrong word and leaves annotation unaccounted for.
Where it came from¶
It was built with marine biologists at HIFMB to segment and measure corals and polyps in reef survey photography — thousands of objects per survey, where hand-drawing every contour was never going to scale.
The pipeline is general, but it was shaped against a real dataset and a real measurement question. That is why it insists on things other annotation tools treat as optional: physical units, provenance, and a review loop around every model prediction.
Beyond images¶
IQUANA is built around image datasets today. The annotation, quantification and review machinery is not inherently two-dimensional, and we are actively exploring what it takes to bring the same loop to other scientific modalities.
If you have a dataset that needs annotation and quantification, or you are interested in a research collaboration, get in touch: robert.leist@dfki.de.
We would rather generalise the tool against a real problem than guess at one.