New extension: Fully automatic whole-body CT segmentation in 2 minutes using TotalSegmentator

The TotalSegmentator AI model is now available as an extension for 3D Slicer version 5.2 and above (see installation instructions here).

A large number of AI segmentation models have been developed over the past few years, but TotalSegmentator stands out in several aspects:

  • it can segment many structures: 104 anatomical structures (all abdominal organs, bones, larger vessels, muscles)
  • it is very robust: it can segment any whole-body, abdominal, chest CT images, regardless of image resolution and field of view
  • fast: computation time at full resolution is 1-2 minutes on a CUDA-capable GPU; and about 1-minute at low-resolution mode on CPU

While it is not perfect (there can be a couple of few-millimeter segmentation errors), the segmentation is accurate enough for most purposes - 3D visualization, quantification, specifying region of interest for segmentation, registration, or further analysis.

TotalSegmentator extension can be installed by a few clicks in the extensions manager. It does not require a GPU, it can segment a whole-body CT in about a minute using just the CPU, but a CUDA-capable GPU is recommended for full-resolution segmentation (which takes 1-2 minutes on GPU but it would take 40-50 minutes on CPU).

Demo and tutorial video:

The TotalSegmentator segmentation engine used in this extension was created at the department of Research and Analysis at University Hospital Basel using the nnU-Net framework developed at DKFZ. If you use this tool then please cite: Wasserthal J., Meyer M., Breit H., Cyriac J., Yang S., Segeroth M. TotalSegmentator: robust segmentation of 104 anatomical structures in CT images, 2022. https://arxiv.org/abs/2208.05868. arXiv: 2208.05868

22 Likes

11 posts were split to a new topic: TotalSegmentator error at first run: “Command ‘pip’, ‘install’, ‘git+https://github.com/wasserth/TotalSegmentator.git’, ‘–no-deps’ returned non-zero exit status”

4 posts were split to a new topic: TotalSegmentator for only segmenting the spine

Dear Andras, as I have said in an other post where you replied to a question, you have done an incredible job and I received it as my prefered X’mas gift.
Thanks again and season greeting.

3 Likes

3 posts were split to a new topic: Offline installation of TotalSegmentator

Wow, this is really amazing! Excellent work. As Pellerin said, great Xmas present!!

2 Likes

Wow that is awesome!

2 Likes

Hmm. Does the module require any special CUDA drivers, or it must work on standard Game-ready Nvidia drivers?

I tried module, and it ignored my 2080ti. :smiling_face_with_tear:

You must use one of the CUDA versions listed on pytorch website as “Compute platform” for your system, which is currently CUDA 11.6 or 11.7 for Windows and Linux. All other CUDA versions are ignored. Gaming cards (GeForce RTX) are fine. See documentation for some more details.

2 Likes

This is extremely beautifull!!! Cant wait to try it out! Im amazed!!! <3

4 Likes

3 posts were split to a new topic: Use TotalSegmentator with atlasess

Hei, thank you so much, this looks amazing, but not able to find it in extensions manager. Using 5.0.3 ?

Please use the extension from Slicer 5.2.1 stable, it is not compatible with previous Slicer versions.

1 Like

haha, let us know if it works! :dog2:

Needs a little refining for canine data sets :grinning:
Picture1

. What is the lights extension, I have tried to find that but can’t?
Picture4

1 Like

The “Lights” module is in the “Sandbox” extension.

1 Like

Hi,

I’ve been following and using Slicer for a while. Today I’m giving a try to this magnific new tool. It really works well with the Sample data, but I get a wrong segmentation when working with my own DICOM file.

I add the file, then open TotalSegmentator with the configs you can see there. What can be happening? Thanks again for you huge contribution for this field.

That result looks reasonable. There’s a big segment called ‘face’ at the front of the head. My understanding is that this can be used to remove features that might otherwise identify the individual subject. Removing these features makes it easier to share 3D data.

4 Likes

Thanks for your reply, Pieper!

I guess that CMF structures can’t be segmented due to data protection on the training process. I’m right?
After reading your comment I have loaded different body CT scans and the result was good.

Hats off to the development team.

Right now there are no CMF-specific substructures included in the TotalSegmentator model. There are dedicated models in development to subdivide the head into relevant anatomical regions. Some of that work will be discussed during the upcoming Project Week.

2 Likes