quick test with SAM3 - impressed with how well it seems to track long protrusions? prompted for "cell", does not find anything when looking for "fibroblast" or "nucleus"

Last-minute advert for the Convpaint workshop at I2K by Roman Schwob! Interactive segmentation in @napari.org. Today 2:00 PM CET. Free registration:
www.i2kconference.org/workshops

Automated optogenetic control of hundreds of cells in parallel. Each cell is individually steered, collectively acting as a "tissue printer". Preprint & code out! www.biorxiv.org/content/10.1...

for MCF10A also seems to be dependent a lot on density! looks very different compared to this (over)confluent epithelia i imaged some time ago on confocal. +1 for zarr+dask, has been working great for us with on data 👌 any tricks on how to convert .czi to .zarr without loosing compression?

look how flat they are??? 🥞 nuclear marker is H2B