Working with 3D Slicer

[santiagooli]

I´m a doctor trying to use 3D Slicer for jaw segmentation. I kew about Nvidia AAIA just recently and installed the plugin. I don´t know how to set the server (too many coding lines that I do not know how to use), and living the space blank does not let me try. I would like to use my own dicom sets but trying to use the module scapes my computer skills. Is there any plug an play way to perform the AI segmetations without the tedious other options slicer provides_

[tangy5]

@santiagooli Thank you for using AIAA, and 3D Slicer for segmentation tasks.

There is a MONAI Label tool for labeling Dicom images with 3D Slicer, if this looks helpful to you:

We have documentation on MONAI Label with 3D Slicer from the beginning.

Please see this page for installation details, this includes a step-by-step guide for setting up the server, plugins, and communicating with 3D Slicer for AI tools. https://docs.monai.io/projects/label/en/latest/installation.html

In addition: the tutorial quickstart page introduces the Radiology App as an example: https://docs.monai.io/projects/label/en/latest/quickstart.html#tutorial-1-radiology

More documentation in the Github can be found here: https://github.com/tangy5/MONAILabel/tree/monailabel_readme_update

Thank you again, let us know if there are further questions, we are appreciative of all user experience and feedback for improving MONAI Label with 3D Slicer!

Yucheng

[diazandr3s]

Thanks for opening this issue, @santiagooli.

Could you please add more information on the jaw segmentation use case? How many images you'd like to annotate? In which format are those images?

In a previous Slicer Hackathon, we has a use case in which we used MONAI Label to perform teeth and jaw segmentation: https://projectweek.na-mic.org/PW36_2022_Virtual/Projects/AutomaticSegmentationofTeethandAlveolarBone/

Is your use case similar to this one?

We assume MONAI Label users are familiar with Slicer. If this is not the case, you may find helpful this demo: https://youtu.be/wtiEe_jiUzg?t=2206

Here is also a video tutorial to start using MONAI Label: https://www.youtube.com/watch?v=8y1OBQs2wis&list=PLtoSVSQ2XzyD4lc-lAacFBzOdv5Ou-9IA

As @tangy5 said, please don't hesitate to post questions in the discussion section here: https://github.com/Project-MONAI/MONAILabel/discussions

Hope this helps,

[santiagooli]

Dear Andres

I use jaw segmentation to produce stl files and later use them in Blender to plan implant treatments. Usually a dicom batch has from 250 to 350 images. I’m new with labelling but usually I just want to isolate the jaw, maxilla and sinuses. One of the problems is to isolate the scattering from metal restorations as it has to be removed by hand slice by slice… hence my interest for this AI technique. All I want is to use my own dicom files with the AI tools. I followed the PyPi install instructions but when I run it to activate the server it fails to find the radiology directory and if I go to slicer, if I try to refresh the server it is denied… My knowledge of python is basically copy and paste… so a little help is needed here…. And yes the example of the Slicer Hackaton is what I need…including sinus segmentation Best Regards Santiago

El El jue, 8 sept 2022 a las 10:10, Andres Diaz-Pinto < @.***> escribió:

Thanks for opening this issue, @santiagooli https://github.com/santiagooli.

Could you please add more information on the jaw segmentation use case? How many images you'd like to annotate? In which format are those images?

In a previous Slicer Hackathon, we has a use case in which we used MONAI Label to perform teeth and jaw segmentation: https://projectweek.na-mic.org/PW36_2022_Virtual/Projects/AutomaticSegmentationofTeethandAlveolarBone/

Is your use case similar to this one?

We assume MONAI Label users are familiar with Slicer. If this is not the case, you may find helpful this demo: https://youtu.be/wtiEe_jiUzg?t=2206

Here is also a video tutorial to start using MONAI Label: https://www.youtube.com/watch?v=8y1OBQs2wis&list=PLtoSVSQ2XzyD4lc-lAacFBzOdv5Ou-9IA

As @tangy5 https://github.com/tangy5 said, please don't hesitate to post questions in the discussion section here: https://github.com/Project-MONAI/MONAILabel/discussions

Hope this helps,

— Reply to this email directly, view it on GitHub https://github.com/NVIDIA/ai-assisted-annotation-client/issues/104#issuecomment-1240443852, or unsubscribe https://github.com/notifications/unsubscribe-auth/A26S4ZX6ZIHNABOEBB3MSZDV5GUR7ANCNFSM6AAAAAAQHCSZVU . You are receiving this because you were mentioned.Message ID: @.***>

[SachidanandAlle]

Please raise any issues/questions related to MONAILabel on corresponding github: https://github.com/Project-MONAI/MONAILabel

[diazandr3s]

Hi @santiagooli

Thanks for sharing the details of the dataset and task.

Have you followed the instructions given in the Readme?

download radiology app and sample dataset

monailabel apps --download --name radiology --output apps monailabel datasets --download --name Task09_Spleen --output datasets

start server using radiology app with deepedit model enabled

monailabel start_server --app apps/radiology --studies datasets/Task09_Spleen/imagesTr --conf models deepedit

Did you follow the step-by-step tutorial explained here?

If yes and you're still facing the same issue, I'd recommend you to please create and issue or open a discussion as @SachidanandAlle recommended: https://github.com/Project-MONAI/MONAILabel/issues - and add the logs or errors you face.

Thanks!

[santiagooli]

Yes I did follow the tutorial. I did struggle some places with the grammar but at the end all was looking like the video screen, just the server never started. I tried to work with Slicer and when I tried to refresh the server a pop up appeared saying it was not possible and the info said the original computer actively refuse it. I will unistall it and will try again... Thanks

[SachidanandAlle]

Closing this issue.. and lets take the discussion in MONAILabel repo instead

[diazandr3s]

Closing this issue.. and lets take the discussion in MONAILabel repo instead

https://github.com/Project-MONAI/MONAILabel