im-browser Activity
MIB is a high-performance software package for image segmentation
Brought to you by:
ajaxel
Activity for im-browser
-
Ilya Belevich posted a comment on ticket #19
All I'd like to do is select features inside the image, without the centre of the brush tool being within the image. ok, now I finally got the point. I need to check how easy it can be done, but I agree, it it nice thing to have. Will the new boundary dimensions apply when I reload a model? or do I need to re-load the image, add a frame with dX/dY, then load the model? The only requirement is that physical sizes (width/height/depth) of the image dataset and models should match. When you add frame,...
-
Ben Padman posted a comment on ticket #19
Thank you for the workaround Ilya. I should clarify further though; I do not need a model to be larger than the image and I actually need to avoid that. I am segmenting correlative data (confocal + FIBSEM) and I am constantly switching modalities. Everything has already been aligned to a coordinate system, so I'm trying to avoid adjustments to image coordinates. All I'd like to do is select features inside the image, without the centre of the brush tool being within the image. I like the dX/dY method,...
-
thank you for clarification. I am specifically referring to case 1. by default it is not possible. The reason is that the model takes the same physical size (in pixels) as the underlying data image, having models of different from the image size is technically possible, but it requires additional logic. Also, normally we can't model the structures that we can't see. There is, however, a solution to that problem. What you need to do is to extend the width/height of your dataset to the desired value....
-
Thank you Ilya, I am specifically referring to case 1. Using the MIB splash screen as an example; A 12px radius brush located at (1;256) should select a 226px^2 area region that extends 12px from the image border; and it does (first attached image). A 12px radius brush located at (0;256) should select a 202px^2 area region that extends 11px from the image border; but it does not, because the tool cannot activate (second attached image). Also, I noticed some very unusual behaviour in the coordinate...
-
Hi Ben, the clipping of the brush tool occurs in two situations: 1. when the brush is at the physical edge of the dataset (Pixel Info: has negative values, as in case1.jpg) 2. when the brush is at the edge of the viewing window(for example when zoomed-in, case2.jpg) to make sure that I understand the problem correctly, which of these cases you are referring?
-
Feature Request: Brush tool operation outside of bounding box
-
great! I bumped myself few times into the similar issues, so those "obvious" ones are just obvious for me :]
-
julien gaillard posted a comment on ticket #18
Hello Ilya and thank you : your first answer was the good one ! I had checked parameters and options but not the most obvious one Thank you again (and ok, i will use the forum if i need support later) Best regards Julien
-
Hello Julien, there may be multiple reasons for that, here the two most obvious ones: 1. the transparency slider for the selection later is set to complete transparency. Please try to move it (it is in the View settings panel at the bottom) 2. Another reason could be due to the Disable Selection combo box is set to "yes" in the preferences window: http://mib.helsinki.fi/help/main2/ug_gui_menu_file_preferences.html Let me know if it does not help. Also, I encourage you to use https://forum.image.sc/...
-
selection doesn't appear
-
Thank you for all your help! Everything is now working as expected. I will have a look at Ilastik as well. All the best
-
Hello Ben, thank you for the datasets! I was able to load the images (tif stack) and the classifier. In my case the prediction worked quite well. I have not noticed any issues (please note that I was using the Matlab version of MIB). However, I noticed a possible problem with your *.fm files. The FM-files contain variable features used by the classifier for the prediction; these files should roughly be the same size. In my case, all fm-files were about 448Mb. The files that you've send me were 452...
-
I have identified a work around for the issue: I was able to segment beyond image number 8 after isolating the data into a new folder, with its own RF_Temp directory. All images processed without an error. See attached screenshots. I think its related to the unusual activity shown in Bug3b.png above, where membranes from an unrelated dataset were being segmented in the current dataset. The issue is much less urgent now, but do you need any more information from me to determine why the membrane detection...
-
Thanks Ilya, I keep trying to post the files but Sourceforge keeps failing. Sorry about the delay. I'll see if there is another way for me to send. I want to send you: The first 10 images from the stack The classifier file generated after training The successful FM output for slice 7 and the failed output for 8 I generated the training model in the middle of my stack, so I'll need to find a way to reduce the filesize to one slice.
-
Hello Ben, I just quickly tested on a small stack and there were no problems. Would you be able to send me (http://www.biocenter.helsinki.fi/~ibelev/) the first part of that dataset and the model used for training, I can test it then? Best regards, Ilya On Sat, Jan 19, 2019 at 10:47 AM Ben Padman bpadman@users.sourceforge.net wrote: [tickets:#17] https://sourceforge.net/p/im-browser/tickets/17/ Erronious activity on "Membrane Detection" classifier tool* Status: New Labels: membrane detection stall...
-
Erronious activity on "Membrane Detection" classifier tool
-
Loading 16bit images as Amira files into MIB error
-
Hi Jash, I updated today MIB to version 2.5, it was compiled on Windows 10. Also there are two installations available, the standard one done for Matlab R2017a and for the recent one R2018b. http://mib.helsinki.fi/downloads.html I hope that may help you with the start-up issue. Best regards, Ilya On Mon, Nov 12, 2018 at 11:29 AM Ilya Belevich ajaxel@users.sourceforge.net wrote: I do the builds on Win7 and that may cause potential incompatibilities with Win10. Soon we are updating OS to Win10 for...
-
Cannot install MIB windows standalone version
-
Hi Kevin, the network installation should work now, there were some problems at the Mathworks side, which are currently fixed. I also updated MIB to version 2.5, now there are two options: - for release R2017a - for R2018b (the recent release) Best regards, Ilya On Mon, Dec 17, 2018 at 7:16 PM Kevin Loftis loftiskg@users.sourceforge.net wrote: Great! Thank you for you help! [tickets:#16] https://sourceforge.net/p/im-browser/tickets/16/ Cannot install MIB windows standalone version* Status: New Created:...
-
Kevin Loftis posted a comment on ticket #16
Great! Thank you for you help!
-
An update: I tested the installation files on multiple workstations with both Win7 and Win10. In all cases, the installation hangs on the first window with the Next button. Most likely, the problem comes from Matlab side and more specifically due to a problem to download the required libraries. I will check with them possible solution. The only way to go further at this moment is to use installation, where all required libraries are bundled, I put it here: http://www.biocenter.helsinki.fi/bi/em/temp/MIB2_Win_240_mcr.exe...
-
Hi Kevin, thank you for pointing this out! I was able to reproduce the issue on my Win10 workstation for the recent and older versions (2.301 and 2.211). I am confident that those were working fine at least on Win7. This problem is different from the topic you've mentioned, but may be caused by the same reason. I will try to contact Mathworks with this. Meanwhile, probably, the best solution will be to try MIB compiled on Win10. I updated my computer to Win10 few weeks back and I will publish MIB...
-
Cannot install MIB windows standalone version
-
Hi Kevin, thank you for the comment! The next release (in few days) will bring hardware accelerated 3D rendering and automatic feature-based alignment. Segmentation in the virtual mode is in plans, but I can't really say when. From the technical point of view, implementation of the basic segmentation in the virtual mode is rather simple, but checking this mode for conflicts with the current features may take quite some time. Best regards, Ilya On Wed, Dec 12, 2018 at 3:39 AM Kevin Loftis loftiskg@users.sourceforge.net...
-
Segmentation in Virtual Mode
-
impossible to run im_browser
-
I do the builds on Win7 and that may cause potential incompatibilities with Win10. Soon we are updating OS to Win10 for all computers and it will be more stable in this respect. Meanwhile, you can try the beta version compiled for Matlab R2018b, perhaps it will work better: http://www.biocenter.helsinki.fi/~ibelev/temp/MIB2/MIB2_beta_deploy.exe
-
Jash Rai posted a comment on ticket #14
I use windows 10 and the standalone Version 2 MIB I will try anything to fix it, this program is very prudent to my work. Also sometimes clearing the mrc cache by deleting the folder found here works https://gyazo.com/4cfbac8ec153a095edd61a09c0f5b512 it only works half the time though and isn't very consistent. https://www.avast.com/sig-email?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=webmail&utm_term=icon Virus-free. www.avast.com https://www.avast.com/sig-email?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=webmail&utm_term=link...
-
Hi Jash, I have not seen such problem before. The error message indicates that matlabrc.m function can't be found. This function is used during matlab startup and sets some default configuration settings. such as parameters of GUI widgets and figure size. Could you please specify which version of MIB do you use, do you run it under Matlab or as compiled one. What is the operation system? I found one possible solution to the problem for the compiled version was explained here (Answer by Patrick Rollin...
-
MIB not launching, matlab error?
-
here is a compiled beta : http://www.biocenter.helsinki.fi/~ibelev/temp/MIB2/MIB2_beta_deploy.exe here is a demo of automatic alignment: http://www.biocenter.helsinki.fi/~ibelev/temp/MIB2/MIB_brief_AutomaticAlignment.mp4 Ilya
-
X-shift and Y-shift are in units of (whole) pixels yes, that's right. The features in MIB are usually developed for some specific projects, later those parts may be further extended and supplemented with other routines, as, for example, in the alignment tool. Thus in some cases the units may be pixels (as in this case or with the annotations) or in physical units, as with bounding box and 3d-lines. I try to unify these things, but it goes quite slow due because it is boring and I don't really have...
-
Grant Myers posted a comment on ticket #13
All right -I appreciate the thorough response, recognizing that what I'm doing isn't necessarily the intended application of the software. Running the compiled windows version of the software: would much prefere to run the Matlab-native version, but unfortunately don't have the image processing toolbox. Yes image pyramids is probably what I want to get to ultimately, and I think that jp2/jpx or hdf5 files could be the way, but I'm still learning how to get there and hoping MIB will help me along....
-
could you specify which version do you use, is it under Matlab or compiled? General note: here, we mostly work with 3d electron microscopy volumes and this mostly defines the logic behind many actions in MIB. Your task is quite different in many way. Developing a tool for your specific task is not difficult, but quite unique and with large rasters it would require implementation of image pyramids (as in google maps) and virtual mode for reading the files without loading them into memory. The latter...
-
Ilya - thanks for the quick response. It would appear to me that it's not as simple as taking the metadata/pixel size from one file or the other. The pixel dimensions of the combined result come from the maximum of the number of pixels in all the images. Then the boundingbox information appears to be taken from the last image file. And the resulting pixel sizes are scaled accordingly. So in the example above, the result of combining the two images is 2873x1617 pixels. 2873 pixels wide because that's...
-
Hi Grant, MIB takes metadata and pixel size from the first file of the series when you combine the datasets. I think the best strategy is to, as you said, resample all datasets to the same pixel size and after that combine them together. Most likely you will need to register the individual images after that. For that you can use the manual multi-point landmarks alignment (from MIB version 2.3) or in the current beta version I have an alignment using automatically detected features, these are located...
-
Combine datasets with different pixel sizes
-
Hi Kevin, let me know if the new functions, fixed the problem. Ilya
-
Installation manual incorrect
-
Membrane Click Tracker Crashes MIB 2.20 Matlab version
-
Hi Kevin, you have quite sofisticated header in the AmiraMesh file. What was the program that generated the file? I modified reading functions for AmiraMesh files: now they can read those fields. But MIB won't use them and the saving of files to the AmiraMesh format won't save them as well. But hopefully, you will be able to read the files. Please update, the following functions attached to this message: 1. MIB2\ImportExportTools\Amira\amiraMesh2bitmap.m 2. MIB2\ImportExportTools\Amira\getAmiraMeshHeader.m...
-
Hi Ilya, Thank you for the quick reply. Here is the header from the file. AmiraMesh BINARY-LITTLE-ENDIAN 2.1 define Lattice 2883 738 1395 Parameters { Units { Coordinates "nm" } HistoryLogHead { HistoryLog { UID:52104d24-2b49-489b-acaf-731eb7834361 { Module:Deblur { Connection:inputImage { UID "a4f4aed5-f882-4383-8664-833811fc6317" } Parameter:interpretation "1", Parameter:sharpeningFactor "2", ResultNumber "0", Label "Deblur", ResourceKey "deblur", ModuleState "create deblur \"Deblur\" \"Deblur\"...
-
Hi Kevin, the problem comes from the amira mesh file header. Could you please open the file in a text editor and send me the header - it is a plain text section in the beginning of the file, before binaries. Thanks! Ilya
-
Loading 16bit images as Amira files into MIB error
-
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/)...
-
Hi Ilya, Thank you for the reply. The new mex-files did the trick. Thank you, Kevin
-
Damir Sudar posted a comment on ticket #11
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...
-
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...
-
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
-
Hi Damir, thank you for noting that, indeed it should state "Matlab R2014b and newer". I will fix that when I am back to Helsinki. Thanks again! Best regards, Ilya On Fri, Dec 1, 2017 at 2:24 AM, Damir Sudar dsudar@users.sf.net wrote: [tickets:#10] Installation manual incorrect Status: New Created: Fri Dec 01, 2017 12:24 AM UTC by Damir Sudar Last Updated: Fri Dec 01, 2017 12:24 AM UTC Owner: nobody The installation manual (http://mib.helsinki.fi/downloads_installation.html) indicates the Matlab...
-
Due to change of Matlab API the compilation of some mex functions may be corrupted. I added the '-compatibleArrayDims' to the compiling script (Tools\mib_compile_c_files.m) in order to fix that. The similar problem was also with the affine_transform_2d_double.c function. I will post the update of MIB next week. Best regards, Ilya
-
Errors while trying to render volume with Fiji
-
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
-
Hi Damir, thank you for noting that, indeed it should state "Matlab R2014b and newer". I will fix that when I am back to Helsinki. Thanks again! Best regards, Ilya
-
Dear Kevin, thank you for reporting that. It looks that there is a problem with compiling the mex-files for the function to run. I will try to install MinGW to compile them and check the results. Meanwhile, I suggest to try compiled files from the previous version (I attached the files for Windows 64 bit). Overwrite the current mexw64 in the MIB2\Tools\FastMarching\functions\ and MIB2\Tools\FastMarching\shortestpath\ directories. You may need to restart Matlab. Best regards, Ilya
-
Deployed MIB on Windows Java path issue w/ OMERO
-
Installation manual incorrect
-
Membrane Click Tracker Crashes MIB 2.20 Matlab version
-
Hi Timm, could you send me to ilya.belevich -at- helsinki.fi the .model file? It is big for the attachment, so better to use google drive or dropbox for sharing it. Thanks! Ilya On Thu, Jul 20, 2017 at 12:01 PM, Timm Mohr timmmmmm@users.sf.net wrote: Oh, of course. Please don't respond anymore :) Maybe once you are back you can let me know what way you want me to share the files? So sorry to have disturbed your holiday. On 20 July 2017 at 09:21, Ilya Belevich ajaxel@users.sf.net wrote: Hi Timm, well,...
-
Timm Mohr posted a comment on ticket #8
Oh, of course. Please don't respond anymore :) Maybe once you are back you can let me know what way you want me to share the files? So sorry to have disturbed your holiday. On 20 July 2017 at 09:21, Ilya Belevich ajaxel@users.sf.net wrote: Hi Timm, well, it is a bit difficult to comment. Could you share those model files? I can take a look. However, I am on holidays and will be able to check it only when I am back after about days. But it is strange, because you definitely have something in the model...
-
Hi Timm, well, it is a bit difficult to comment. Could you share those model files? I can take a look. However, I am on holidays and will be able to check it only when I am back after about days. But it is strange, because you definitely have something in the model files. Best regards, Ilya On Jul 20, 2017 9:57 AM, "Timm Mohr" timmmmmm@users.sf.net wrote: Sry I didn't see your next message. I am running the standalone 2.1 version on Windows. I thought I was running in 8 bit but I might be wrong,...
-
Hi Ilya, did you see my first message? My main problem at the moment is that the model is not showing up and appears to be empty although the data seem to be there still. Timm On 20 July 2017 at 08:28, Ilya Belevich ajaxel@users.sf.net wrote: When I then try to load my model again(currently 15 materials) it still shows the squiggles but in a different colour I recommend to save the models in the matlab model format. In this case the colors should stay. In most of other formats it is not possible...
-
Sry I didn't see your next message. I am running the standalone 2.1 version on Windows. I thought I was running in 8 bit but I might be wrong, I did a lot of experimenting. It's really good to know that other formats increase performance. The material statistics are unfortunately empty in both the .model and .nrrd files. On 20 July 2017 at 08:35, Ilya Belevich ajaxel@users.sf.net wrote: Hi Timm, which version of mib do you use, is it matlab or compiled? wundows or mac? So your dataset is in Mrc and...
-
Hi Timm, which version of mib do you use, is it matlab or compiled? wundows or mac? So your dataset is in Mrc and 6.6 gb. The model in nrrd file is 3gb, which indicates that uou are working with 16 bit images. I suggest to load mrc dataset, convert it to 8bit and save in amiramesh or nrrd format.This will improve general performance. Next, the .mask and the .model files are 70 and 20 Mb. When those files are saved Matlab compresses them, and since they are quite big the model and the mask should...
-
When I then try to load my model again(currently 15 materials) it still shows the squiggles but in a different colour I recommend to save the models in the matlab model format. In this case the colors should stay. In most of other formats it is not possible to preserve the colors of materials. When I work with models in mib I use .model format, and only when I need to export the model to another program I resave it in one of other formats. The .model files also take quite a while to load yes, for...
-
An odd thing I just noticed. I made a test model with just some squiggles added to a material. I saved it and it loads up again. When I then try to load my model again(currently 15 materials) it still shows the squiggles but in a different colour (I deleted the first material on my model). The .model files also take quite a while to load.
-
Hi, I have the exact same problem. I have a .model .nrrd and .mask file. Neither show up, statistics are empty, Exterior seems to occupy the whole volume. I can still render the model in 3D slicer. I attached a picture of the files that I am using. Are the file sizes what you would expect? The .mrc fiel is 6.6GB the .nrrd model 3.3GB and the .model 21MB? Has this been resolved yet? Best wishes, Timm
-
ok, so it seems that the issue was due to singleton limitation of MIB version 2.00-2.01 (only one instance of MIB allowed at the time). In the next update this limitation should be fixed and multiple instances will be allowed. Ilya
-
Connon Thomas posted a comment on ticket #8
Ilya, I use the compiled version; I'm on a computer that doesn't have Matlab. There is another computer I can use that does have the Matlab version, if you want to send me that and see if it works. If not, I think we can try Skype. Thanks!
-
Hi, thank you for the file, I've checked it. I found one bug during import of it from Matlab and fixed it. But I don't think that this bug is causing problems for you. Do you use compiled or matlab version of MIB? I can suggest 2 things: If you are using the Matlab version I can send you the current beta, where I fixed that bug with the import for testing Otherwise, we can have a Skype meeting where you can shere the screen and I will check what might be wrong. Ilya
-
Wow, you're fast. It's not one particular file, I am doing 5 other chunks of data that are also not working. They're all similar in size, maybe a bit large? I've worked with larger though (in previous versions). The stack I'm working with is 79 images at 3584 x 3333 pixels (~9 MB). I'll send it to you. Thanks! Connon
-
Wow, you're fast. It's not one particular file, I am doing 5 other chunks of data that are also not working. They're all similar in size, maybe a bit large? I've worked with larger though (in previous versions). The stack I'm working with is 79 images at 3584 x 3333 pixels (~900 MB). I'll send it to you. Thanks! Connon
-
Wow, you're fast. It's a bit large, maybe? I've worked with larger though (in previous versions). The stack I'm working with is 79 images at 3584 x 3333 pixels (~900 MB). I'll send it to you. Thanks! Connon
-
Hi, Do you have this problem only with some particular model file? is it large .model file? Could you send it to me, so that I can check? Indeed MIB1 can't read the models from MIB2. The other direction MIB1 models in MIB2 is working fine. I probably have to implement saving of models in MIB1 format from MIB2. Ilya On Tue, Apr 25, 2017 at 11:25 PM, Connon Thomas connont@users.sf.net wrote: [tickets:#8] Material doesn't show when loaded in MIB 2.01 Status: New Created: Tue Apr 25, 2017 08:25 PM UTC...
-
Hi, Do you have this problem only with some particular model file? is it large .model file? Could you send it to me, so that I can check? Indeed MIB1 can't read the models from MIB2. The other direction MIB1 models in MIB2 is working fine. I probably have to implement saving of models in MIB1 format from MIB2. Ilya
-
Material doesn't show when loaded in MIB 2.01
-
great! thank you for the update! Best regards, Ilya On Thu, Feb 16, 2017 at 9:28...
-
Tzipi C Hyams posted a comment on ticket #7
Thank you, I had to install java3d and now it works well. Best regards, Tzipi
-
Hi Tzipi, most likely, you did not have correct path to Fiji installation folder...
-
Hello, Thank you for your assistance. I am now using the latest version of MIB stand...
-
Hi Tzipi, which version of MIB do you have? Which version of Matlab do you have?...
-
Hello, I got this error after setting the path as described in the installation instruction....
-
Hi, have added Fiji.app/scripts folder to the Matlab path? check it here: http://mib.helsinki.fi/downloads_systemreq.html#fiji...
-
Errors while trying to render volume with Fiji
-
Problem while compiling the C files with min-GW
-
Tom Boissonnet posted a comment on ticket #6
Curtis Rueden (Fiji) replied : Since you are using the new Fiji bundled with Java...
-
Hi Tom, thank you for reporting that. I reproduced that on a freshly installed Fiji...
-
Trouble with java 1.8
-
Hi Tom, thank you for this; it was interesting to see that in one case double declaration...
-
Hi Ilya, here they are.
-
Error when trying to load models
-
A few queries about using MIB
-
Hi Tom, thank you for reporting this! Unfortunately I don't have minGW installed...
-
Problem while compiling the C files with min-GW
-
Catherine Maclachlan posted a comment on ticket #3
Hi, That update seems to have got it working. Thanks. From: Ilya Belevich [ajaxel@users.sf.net]...
-
Hi again, I fixed use of memory function on Mac and Linux. The Matlab version (but...
-
Hi Catherine, thank you for reporting this! It seems that this function (memory)...
-
Hi, I have been following your tutorials to try and select out the mitochondria of...
-
I was able to reproduce the problem with R2014b. Most likely the problem is in some...
1 >
