Open dfgdgdfgd opened 1 year ago
Hi Mario, by "a few layers" do you mean a few z-slices? If yes, then surely we can implement that function.
Do you think it should also have a minimum area threshold? I was thinking that some objects made of three z-slices might be legit if they are big enough, right?
Did you try filtering by minimum size? You can test this in the GUI from the menu in the top menu bar Segment --> Segmentation post-processing...
and then you play with the sliders and numeric controls.
Anyway, we can add a "minimum number of z-slices" numeric control in that window, what do you think?
Cheers, Francesco
Hi Francesco,
yes, i meant a few z-slices. And yes, indeed, you´re right, a minimum area would certainly make sense, since the thickness of the z-slices is variable.
Filtering by minimum size is a really useful option, but sometimes wrong segmented structures exceed the adjusted minimum size, but they have only a fraction of the volume of a whole nucleus. A slider for "minimum number of z-slices" would be great, since that would give the user more flexibility to delete over-segmented nuclei.
Thanks and best regards, Mario
Hi Mario,
I just release v1.2.4rc56
with the feature that we discussed.
There is now a new slider in the post-processing parameters to set the minimum number of z-slices per object. This can also be set when you segment multiple positions at once with the segmentation module.
To update, activate the acdc environment and then run the command pip install --upgrade cellacdc
.
Let me know if it works, thanks!
Have a good Christmas break and a happy new year!
Cheers, Francesco
Salve Francesco,
great, mille grazie, provo domani.
Buon natale anche a te é un buon anno nuovo!!
Saluti Mario
Am Tue, 20 Dec 2022 11:20:07 -0800 schrieb Francesco Padovani :
Hi Mario,
I just release v1.2.4rc56 with the feature that we discussed.
There is now a new slider in the post-processing parameters to set the minimum number of z-slices per object. This can also be set when you segment multiple positions at once with the segmentation module.
To update, activate the acdc environment and then run the command pip install --upgrade cellacdc.
Let me know if it works, thanks!
Have a good Christmas break and a happy new year!
Cheers,Francesco
—Reply to this email directly, view it on GitHub https://github.com/SchmollerLab/Cell_ACDC/issues/224#issuecomment-1360046742 , or unsubscribe https://github.com/notifications/unsubscribe-auth/A3XFA7JSUGMYZIIGHEHZR2LWOIBGPANCNFSM6AAAAAAS5H7UVM .You are receiving this because you authored the thread. [img] Message ID: @.***>
Mit freundlichen Grüßen Mario Vitacolonna
Dr. Mario Vitacolonna Dipl. -Ing. Biotechnologie Innovationspartnerschaft M²Aind
Hochschule Mannheim Fakultät für Biotechnologie Institut für Molekular- und Zellbiologie (IMZ) Gebäude K, Raum 215 Paul-Wittsack-Strasse 10 68163 Mannheim
E-Mail: @.***
Telefon: +49-(0)621-292-6538
www.m2aind.hs-mannheim.de http://www.m2aind.hs-mannheim.de/
Faculty of Biotechnology Mannheim University of Applied Sciences Institute of Molecular and Cell Biology Paul-Wittsack-Strasse 10 68163 Mannheim Germany
[img]
Haftungsausschluss: Die in dieser E-Mail und den dazugehoerigen Anhaengen (zusammen die "Nachricht") enthaltenen Informationen sind nur fuer den Adressaten bestimmt und koennen vertrauliche oder rechtlich geschuetzte Informationen enthalten. Sollten Sie die Nachricht irrtuemlich erhalten haben, loeschen Sie die Nachricht bitte und benachrichtigen Sie den Absender. Die unbefugte Weitergabe, das Anfertigen von Kopien und jede Veraenderung der E-Mail ist untersagt. Wir schließen jegliche Haftung fuer Verluste oder Schaeden aus, die durch Inhalte veraenderter Nachrichten oder virenbefallene Software verursacht werden. Disclaimer: The information contained in this e-mail and any attachments (together the "message") is intended for the addressee only and may contain confidential or privileged information. If you have received the message by mistake please delete it and notify the sender. The unauthorized dissemination, copying and change of this e-mail are strictly forbidden. We accept no liability for any loss or damage caused by changes of the original message or software viruses.
Hi there, I'm the Cell-ACDC bot :wave:. This issue had no activity for more than 180 days. For now, we have marked it as "inactive" until there is some new activity. If this issue was not solved yet, unfortunately we haven't had the time to implement it or it requires more discussion. Note that it doesn't mean it has been ignored, but a little reminder from your side would help :D. Feel free to reach out to us here or on our forum. If you think that this issue is no longer relevant, you may close it by yourself. In any case, we apologise for the inconvenience and we thank you for your patience and contributions so far!
Description:
Hi Francesco, i noticed that when segmenting 3D data with Cellpose, it is often the case that labels end after only 1-3 layers and the rest of the nuclei are assigned to a new label. Do you think there might be a possibility to implement a function to delete 3D labels with only a few layers?
Thanks and best regards Mario