Hi Patricia, I used WEKA segmentation for your Cell2 image and it worked well. I suggest trying that. I had 3 classes, class 1 = spheroid, class 2 = shadow of the week and class 3 = in between the wells (white area).
I've attached a PNG version of the classified image and the probability maps looked good. If the spheroids become more dense (darker), you may have to have 2 separate classifiers but I think it's worth a try. Kind regards, Jacqui Jacqueline Ross Lead Technologist Optical Microscopy & Image Analysis Biomedical Imaging Research Unit (BIRU) Faculty of Medical & Health Sciences Waipapa Taumata Rau | The University of Auckland Private Bag 92019 Auckland 1142, NEW ZEALAND Telephone: Ext 87438; DDI: +64 9 923 7438 Website: Biomedical Imaging Research Unit - The University of Auckland<https://www.fmhs.auckland.ac.nz/en/sms/about/our-departments/biomedical-imaging-research-unit.html> SHIPPING ADDRESS Waipapa Taumata Rau | The University of Auckland M&HS BUILDING 505 - Bldg 505 Level B, Room B36 85 PARK RD/Loading Dock, Park Avenue Grafton, Auckland 1023 NEW ZEALAND ORCID ID https://orcid.org/0000-0001-5578-6651 From: OBEID Patricia <[email protected]> Sent: Monday, March 4, 2024 9:36 PM To: [email protected] Subject: help to segment spheroids Sensitivity: Confidential Hello, I would like to segment spheroids that are in microcavities. For the first cell, all is ok. Here are a few lines from my macro: run("Duplicate...", " "); run("Invert LUT"); setAutoThreshold("Moments dark"); setOption("BlackBackground", true); run("Convert to Mask"); run("Invert LUT"); run("Analyze Particles...", "size=6000-80000 display summarize add"); For the second cell, my problem is that I'm working in white light and the edges of the wells are also detected .... One solution might be to do a threshold on the edges of the wells and the outside and remove these areas, then do a new threshold to detect spheroids, but I don't know how to write these lines of code ... :-( Thanks for any help and/or suggestions you can give me. Good day to all Patricia The images are here : https://filesender.renater.fr/?s=download&token=f580e06e-6f9a-4e4b-8696-b99037472bdc<https://filesender.renater.fr/?s=download&token=f580e06e-6f9a-4e4b-8696-b99037472bdc> [230227_signature-mail] Toute notre actualité sur https://www.cea.fr/drf/irig<https://www.cea.fr/drf/irig> et sur Biomics<https://www.bge-lab.fr/Biomics<https://www.bge-lab.fr/Biomics>> Et sur https://twitter.com/BiomicsLab<https://twitter.com/BiomicsLab> [Facebook]<https://fr-fr.facebook.com/cea.pageofficielle<https://fr-fr.facebook.com/cea.pageofficielle>> [Youtube] <https://www.youtube.com/channel/UCpTMWY8NRQby8zXUKhHznfg<https://www.youtube.com/channel/UCpTMWY8NRQby8zXUKhHznfg>> [Twitter] <https://twitter.com/CEA_Officiel<https://twitter.com/CEA_Officiel>> [LinkedIn] <https://fr.linkedin.com/company/cea<https://fr.linkedin.com/company/cea>> [Instagram] <https://www.instagram.com/cea_officiel/<https://www.instagram.com/cea_officiel>> -- ImageJ mailing list: http://imagej.nih.gov/ij/list.html<http://imagej.nih.gov/ij/list.html> -- ImageJ mailing list: http://imagej.nih.gov/ij/list.html
