Andras Lasso

@szabotomi01 Let's discuss this on the Slicer forum. Please post the question there and copy the link here. Thank you!

@lassoan any eay you could help with a research project about measuring the thickness of acetabular region and presenting it on a 3d heatmap model. Saw a tutorial in the community about model-to-model-distance extension but can’t seem to get it to work, also…

@szabotomi01 This should be feasible, please ask on the Slicer forum - discourse.slicer.org

… bone thickness measurement tool doesn’t seem to do much. Any idea of how I can achive this 3d heatmap thickness model? Thank you for your help!

@jerome_esteves @raimcsantos @3DSlicerApp Here are the 3D image files of a liver CT and the fully automatic segmentation results (obtained in 2 minutes): github.com/lassoan/Public…. Source CT image: Medical Decathlon data set - Task03_Liver - imagesTr/liver_100.nii.gz

@raimcsantos @3DSlicerApp @lassoan Would you have a demonstrative anonymized dicom to propose? Let me know in PM?

#3D total #segmentation GPU - Wonderful #anatomy - relative anatomy - proper surgical programming. It can be performed on tomography without contrast(Fantastic). #Aortic #aneurysm. @3DSlicerApp #AortaEd #MedTwitter @lassoan #VascularSurgery #Endovascular

@jerome_esteves @raimcsantos @3DSlicerApp Not a lot of time and pain to save here. You can get this segmentation in 3D Slicer with TotalSegmentator extension within 2 minutes, fully automatically. It is completely free and comes without any licensing restrictions. The data does not leave your computer. No GPU required.

@raimcsantos @3DSlicerApp @lassoan Have you tried the D2P software for #segmentation and #meshing ? Quite sure you would save time and pain here ;-)

@ayomi4_adebayo @3DSlicerApp Yes, sure. You can ask for more details on the Slicer forum: discourse.slicer.org

@lassoan @3DSlicerApp I got the python script for brain tumor 3D segmentation with MONAI using gliomas..can I use the deploy these codes for my meningioma (T1 and T2) dataset?

A small new feature in @3DSlicerApp for painting segmentations into 3D images at higher quality. Developed for #SlicerHeart but has many other applications. More info: discourse.slicer.org/t/new-feature-…

@ayomi4_adebayo @3DSlicerApp Segment Comparison module is provided by SlicerRT extension.

@lassoan @3DSlicerApp I just discovered that one of the tools (segment comparison) I used to evaluate my segmentation methods (dice coefficient and Hausdorff distance) is missing. Please is there an available tool/ extension to calculate this in 3D-Slicer?

@ayomi4_adebayo @3DSlicerApp In general, you run the server in a separate Python environment outside Slicer. After you started the server, Slicer can connect to it.

@lassoan @3DSlicerApp Thanks @lassoan , I have tried working with the MONAI label app from 3d-slicer but I couldn't upload my dataset and the server isn't working. I read that I need to install the radiology app. Would this be done via the python console. Can you please help.

@ayomi4_adebayo @3DSlicerApp Check out MONAILabel extension. I think it's radiology application has brain tumor segmentation model.

@lassoan @3DSlicerApp Oh, okay... Can you please recommend which of the extensions I could use for the brain tumour segmentation in 3d-slicer?

@ayomi4_adebayo @3DSlicerApp NVIDIA-AIAA developers stopped working on the project and moved on to develop MONAILabel, so we gave up on maintaining a public NVIDIA-AIAA server.

@lassoan @3DSlicerApp Hello @lassoan, I am currently working on the segmentation of brain tumors MRIs using the 3d-slicer software. I recently used NVidia as an extension for the segmentation process but it's not going anymore. It keeps saying server error. What might the issue?

@MarkLikesTrauma TotalSegmentator is trained on a wide variety of data, so that should work on pediatric cases, too. There are several MONAILabel segmentation tutorials and examples and you can ask the @ProjectMONAI community if you need help with any specific questions.

@lassoan Have found 3D slicer very helpful in mapping vasculature and anatomy for pediatric solid organ tumors. Any tips/tutorials for training MONAI and other AI-based apps on pediatric anatomy? This is an example of a large renal tumor that was invading the liver:

@medslicer @3DSlicerApp You don't need to develop any new code but you have to find and follow tutorials and documentation to run the training scripts. You also need powerful GPU for training.

@lassoan @3DSlicerApp Thank you for the answer Andras. What do you mean by "retrain the network yourself"? Is it something i can do without having any skills in python/coding?

This is a game changer. Segment 100+ structures in any whole-body CT image in 2 minutes using TotalSegmentator in @3dslicerapp All free, open-source software. Runs on any computer, no GPU is required. See more information at discourse.slicer.org/t/26710

@medslicer @3DSlicerApp You can submit corrections if you find inaccuracies in the original training data set. For other images, you probably need to retrain the network yourself.

@lassoan @3DSlicerApp This new tool is incredible. With a good GPU, a 1-8 hours manual segmentation work can be done in less than 3 minutes. However, there are sometimes mistakes that need to be corrected manually. Is it possible use these modifications as a feedback to improve ulterior results?

@KTheivendran @pjjenkins80 @Gnomelover1970 @Davembmd @Camnerveblocks @GriOrtho @3DSlicerApp @Blender Cleaning should be all doable in Slicer now. Fill small holes and surface noise using Smoothing effect in Segment Editor. Then simplify the mesh for 3D printing using Surface toolbox module's Uniform remeshing option.

@pjjenkins80 @Gnomelover1970 @Davembmd @Camnerveblocks @GriOrtho @3DSlicerApp @Blender Still require cleaning. But the Total Segmentator AI plug-in can be trained specifically for the shoulder CT scans for segmenting bone. All source code is opensource and can be done. A good project for a AI interested institutions. @lassoan

@Davembmd @Camnerveblocks @pjjenkins80 Does anyone have advice on software for 3D printing from a CT. Absolute beginner.

@basalmind @alexandrecadrin Once you have segmented the vasculature, you can separate the arterial and venous branches by placing a few seed points and growing from those seeds, inside the vessels (using in Segment Editor in 3D Slicer - slicer.org)

@alexandrecadrin Hello Dr. Cadrin, Have you ever tried totalsegmentator? (twitter.com/lassoan/status…) I tried this and generally it's excellent function but I've used it for renovascular anatomy and it doesn't differentiate renal artery and vein. Do you know any better option?

Impressive but imperfect zero-shot generalization in medical imaging for Segment Anything Model (SAM) from FAIR segment-anything.com

@GermanMenRev Please post on the Slicer forum - discourse.slicer.org - where we can discuss this in more detail. Thank you!

And I must be doing something wrong , wright @lassoan ?Because I'm still getting only support structure on the inner space of the pelvic bone (purple arrow) instead of the infill I set up (as per the paper 100% infill , and 5% support density + line support pattern.

Tried my best and give it a try on @3DSlicerApp and installed the amazing "SurfaceWrapSolidify" Extension. I'm sure this will save a lot of time and filament, but still struggling with the surface cracks preservation. Any suggestions ? @lassoan #3dprinting #secot #sogacot

@MikolajBuchwald @szym0nk We have specialized presets for MV, TV, CAVC, LAVV, and a generic valve preset. You can use the generic valve or MV preset for aortic valve. You could also create a new aortic valve quantification preset by specifying reference points and measurements based on them.

@lassoan This is amazing, the Slicer team is unstoppable, good job 👍 Is there also a similar quantification tool for the aortic valve? @szym0nk

We have released a number of tools for cardiac valve modeling, quantification, simulation and we have many more in the pipeline. All free, freely usable, open-source software.

@aigonewrong @3DSlicerApp It would be also nice to see Hausdorff distance results. Dice is widely used (probably because it is easy to compute) but works very poorly for thin, small, or elongated segments.

@lassoan @3DSlicerApp Dice between manual vs TotalSegmentator contours in AMOS22 and Pediatric-CT-SEG (dice drops when age < ~5)

@aigonewrong @3DSlicerApp Interesting results, thanks for sharing. Pediatric CTs were not used for TotalSegmentator training, so some inaccuracy is expected. You could consider adding them to the TotalSegmentator training data set and retrain to see if it can handle pediatric cases, too.