Adam Tyson

I don't think there's any such warning. It's clear for cellfinder (CLI) that it needs to be a whole-brain image, which should always have an "empty" corner. For the python...

Renaming this issue to better reflect what needs to be done.

Not sure how to do this without an area we know is outside the tissue, but maybe the mean of the middle plane or something?

cc @davoudian

A bit more background. The code in cellfinder-core was originally part of cellfinder, and wasn't intended as a public API. Now it is used in cellfinder and cellfinder-napari. It can...

No strong feelings either way. For the former, this sounds good: > While this interface is primarily designed to be displayed in the viewer, it can also be used without...

Oh yeah reducing clutter in the widget would be great! At some point it might be worth investigating collapsible/expandable widget sections. @horsto did this in [brainreg-segment](https://github.com/brainglobe/brainreg-segment).

e.g. https://github.com/brainglobe/cellfinder-napari/blob/31428fd6963e277f7dcc786a5e8bca85f9b6a8c2/cellfinder_napari/detect.py#L311-L318

@alessandrofelder these [headers are now in `brainglobe-utils`](https://github.com/brainglobe/brainglobe-utils/blob/main/brainglobe_utils/qtpy/logo.py), so should this issue now be to import them from that package, rather than duplicate in cellfinder?

Closing now we've moved to torch, this issue no longer exists :tada: