#11 Deployed MIB on Windows Java path issue w/ OMERO

[Damir Sudar]

I just installed Deployed MIB on Windows and downloaded the OMERO Matlab 5.4.1 package. After setting the External Dirs in Preferences to point to the OMERO libs, I get in the console window "No class omero.client can be located on the Java class path". However, when I run "MIB in Matlab" and follow the path instructions, I have no problem connecting to the OMERO server. Is there an issue with the Java class path setting in the deployed version?
Thanks.

[Ilya Belevich]

Hi Damir,
use of the Java classes may be a bit messy in the deployed version. Since I am not using the deployed version (I am not currently using the connection to Omero either), so it is easy to miss those things. I need to check it out.
Best regards,
Ilya

[Damir Sudar]

Hi Ilya,
Thanks for the quick reply. Great if MIB/deployed can be made to work w/ OMERO. We are considering to use MIB to have multiple remote people help with segmenting EM images that we will host on a Cloud-hosted OMERO server. The remote people will unlikely have Matlab licenses. If I can do anything to help, please let me know.
Cheers,
- Damir

[Ilya Belevich]

Hi Damir,
the Omero connection was done years ago as a test because I was thinking to use the server for our purposes. But it was not that much useful for large 3D EM volumes, so the project was freezed. In the current form I only added a possibility to import the datasets from Omero and there is no possibility to send the datasets back. I think in general this part can be addressed again to add methods for sending the filtered images/segmentations back to the Omero server.
This however, would require description of good practices on the matter.
Best regards,
Ilya

[Damir Sudar]

Hi Ilya,
Yes, I noticed that the traffic is currently "one-way only" and that is already extremely useful. Thanks for having implemented that. And indeed, directly submitting processed image data back is one possible and very useful extension. However, we are considering a workflow where the remote users do the manual segmentation and submit the "model" files (in one of the formats supported by MIB) back by some other method, e.g. email or upload to a simple submission server. We will then aggregate the multiple submissions and calculate some kind of consensus model. The idea behind this is a crowdsourcing method of segmentation of complex EM images. If this concept is of interest to you, we can look at collaboration options.
Cheers,
- Damir

[Ilya Belevich]

Hi Damir,
this is quite workable approach. In our case, we usually use the Chop mode to chop large datasets into smaller volume and distribute further for segmentation, but I think Omero should also work nicely.
I recompiled MIB; on my system the compiled version opens the Omero files from the demo server (version 5.4.1).
Here the executables for tests:
www.biocenter.helsinki.fi/~ibelev/temp/MIB2_Win_221.exe

Please note that you still have to download Omero package for matlab (http://www.openmicroscopy.org/omero/downloads/) and specify that path in MIB->Menu->File->Preferences->External dirs

Ilya