Create accountLogin

Recent searches

No recent searches

Search options

Only available when logged in.
mstdn.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
A general-purpose Mastodon server with a 500 character limit. All languages are welcome.

Administered by:

Server stats:

13K
active users

mstdn.social: AboutStatusProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.3.8

#cellpose

0 posts0 participants0 posts today
AI4Life<p>After a day and a half of <a href="https://qoto.org/tags/ImageAnalysis" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ImageAnalysis</span></a> in the cloud with <a href="https://qoto.org/tags/dask" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>dask</span></a> by the IDR team, Damian Dalle Nogare takes over a practical session to apply several <a href="https://qoto.org/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> models for cell segmentation using <a href="https://qoto.org/tags/Cellpose" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Cellpose</span></a></p>
Carsen Stringer (she/her)<p>Despite all their hype in AI, we found that Transformers do not outperform <a href="https://neuromatch.social/tags/Cellpose" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Cellpose</span></a> for cellular segmentation tasks: <a href="https://www.biorxiv.org/content/10.1101/2024.04.06.587952v1" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">biorxiv.org/content/10.1101/20</span><span class="invisible">24.04.06.587952v1</span></a></p><p><a href="https://neuromatch.social/tags/bioinformatics" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>bioinformatics</span></a> <a href="https://neuromatch.social/tags/biology" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>biology</span></a> <a href="https://neuromatch.social/tags/machinelearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>machinelearning</span></a></p>
Carsen Stringer (she/her)<p><a href="https://neuromatch.social/tags/Cellpose" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Cellpose</span></a> 3! Not all images are perfect. Restore your images with Cellpose3 to get better segmentations, w/ <span class="h-card" translate="no"><a href="https://neuromatch.social/@marius10p" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>marius10p</span></a></span> <a href="https://www.biorxiv.org/content/10.1101/2024.02.10.579780v1" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">biorxiv.org/content/10.1101/20</span><span class="invisible">24.02.10.579780v1</span></a></p><p>(click to play gif)</p>
Carsen Stringer (she/her)<p>AI under the microscope: the algorithms powering the search for cells: <a href="https://go.nature.com/3SVdFur" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">go.nature.com/3SVdFur</span><span class="invisible"></span></a>. Nice article by Michael Eisenstein about cellular segmentation, with a shout out to <a href="https://neuromatch.social/tags/cellpose" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>cellpose</span></a> :) <a href="https://neuromatch.social/tags/biology" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>biology</span></a> <a href="https://neuromatch.social/tags/deeplearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>deeplearning</span></a></p>
Carsen Stringer (she/her)<p><span class="h-card" translate="no"><a href="https://hachyderm.io/@ogi" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>ogi</span></a></span> thanks, I did not realize this before, that's great. and yes we use <a href="https://neuromatch.social/tags/pyqtgraph" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>pyqtgraph</span></a> in a bunch of projects, love how fast and flexible it is! <a href="https://neuromatch.social/tags/cellpose" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>cellpose</span></a> is our most popular software tool that uses it: <a href="https://github.com/MouseLand/cellpose" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">github.com/MouseLand/cellpose</span><span class="invisible"></span></a></p>
Michalis Averof<p>Cell/nuclei segmentation by training deep learning models for <a href="https://drosophila.social/tags/CellPose" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>CellPose</span></a> and <a href="https://drosophila.social/tags/StarDist" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>StarDist</span></a> incrementally, using sparse annotations</p><p>Latest work by Ko Sugawara, initiated in our team and completed at RIKEN</p><p><a href="https://www.biorxiv.org/content/10.1101/2023.06.13.544786v1.full.pdf" rel="nofollow noopener noreferrer" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">biorxiv.org/content/10.1101/20</span><span class="invisible">23.06.13.544786v1.full.pdf</span></a></p>
DigitalSreeni<p>I tried <a href="https://mstdn.science/tags/CellPose" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>CellPose</span></a> model on materials science data. Looks like cellpose is not just for cells! Got very good results with small data set and 45 min training on Google colab . <a href="https://mstdn.science/tags/python" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>python</span></a> <a href="https://mstdn.science/tags/deeplearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>deeplearning</span></a> <a href="https://mstdn.science/tags/Microscopy" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Microscopy</span></a></p>
DigitalSreeni<p>I tried <a href="https://mstdn.science/tags/CellPose" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>CellPose</span></a> model on materials science data. Looks like cellpose is not just for cells! Got very good results with small data set and 45 min training on Google colab . <a href="https://mstdn.science/tags/python" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>python</span></a> <a href="https://mstdn.science/tags/deeplearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>deeplearning</span></a> <a href="https://mstdn.science/tags/bmicroscopy" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>bmicroscopy</span></a></p>
Carsen Stringer<p>Can chatGPT also answer github issues for me? :ablobpeek: <a href="https://qoto.org/tags/cellpose" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>cellpose</span></a></p>
Joy Franco<p>Figured out how to annotate the <a href="https://mstdn.social/tags/cellpose" class="mention hashtag" rel="tag">#<span>cellpose</span></a> masks with their labels all in <a href="https://mstdn.social/tags/Python" class="mention hashtag" rel="tag">#<span>Python</span></a> </p><p>So ridiculously excited about this :kirbyroll:</p>
ExploreLive feeds
About