Add KonfAI extension

[vboussot]

New extension

Tier 1

Any extension that is listed in the Extensions Catalog must fulfill these requirements.

• Extension has a reasonable name (not too general, not too narrow, suggests what the extension is for). The extension name should not start with Slicer (unless it explicitly provides a bridge between Slicer and a tool or library), because it would make it more difficult to find extensions if the name of many started with the same word.
• Repository name is Slicer+ExtensionName (except if the repository that hosts the extension can be also used without Slicer)
• Repository is associated with 3d-slicer-extension GitHub topic so that it is listed here. To edit topics, click the settings icon in the right side of "About" section header and enter 3d-slicer-extension in "Topics" and click "Save changes". To learn more about topics, read https://help.github.com/en/articles/about-topics
• Extension description summarizes in 1-2 sentences what the extension is usable (should be understandable for non-experts)
• Any known related patents must be mentioned in the extension description.
• LICENSE.txt is present in the repository root and the name of the license is mentioned in extension homepage. We suggest you use a permissive license that includes patent and contribution clauses. This will help protect developers and ensure the code remains freely available. MIT (https://choosealicense.com/licenses/mit/) or Apache (https://choosealicense.com/licenses/apache-2.0/) license is recommended. Read here to learn more about licenses. If source code license is more restrictive for users than MIT, BSD, Apache, or 3D Slicer license then describe the reason for the license choice and include the name of the used license in the extension description.
• Extension URL and revision (scmurl, scmrevision) is correct, consider using a branch name (main, release, ...) instead of a specific git hash to avoid re-submitting pull request whenever the extension is updated
• Extension icon URL is correct (do not use the icon's webpage but the raw data download URL that you get from the download button - it should look something like this: https://raw.githubusercontent.com/user/repo/main/SomeIcon.png)
• Screenshot URLs (screenshoturls) are correct, contains at least one
• Content of submitted json file is consistent with the top-level CMakeLists.txt file in the repository (dependencies, etc. are the same)
• Homepage URL points to valid webpage containing the following:
  • Extension name
  • Short description: 1-2 sentences, which summarizes what the extension is usable for
  • At least one nice, informative image, that illustrates what the extension can do. It may be a screenshot.
  • Description of contained modules: at one sentence for each module
  • Publication: link to publication and/or to PubMed reference (if available)
• Hide unused github features (such as Wiki, Projects, and Discussions, Releases, Packages) in the repository to reduce noise/irrelevant information:
  • Click Settings and in repository settings uncheck Wiki, Projects, and Discussions (if they are currently not used).
  • Click the settings icon next to About in the top-right corner of the repository main page and uncheck Releases and Packages (if they are currently not used)
• The extension is safe:
  • Does not include or download binaries from unreliable sources
  • Does not send any information anywhere without user consent (explicit opt-in is required)

Tier 3

Community-supported extensions.

• Documentation, tutorial, and test data are provided for most modules. A tutorial provides step-by-step description of at least the most typical use case, include a few screenshots. Any sample data sets that is used in tutorials must be registered with the Sample Data module to provide easy access to the user.
• Follows programming and user interface conventions of 3D Slicer (e.g., GUI and logic are separated, usage of popups is minimized, no unnecessary custom GUI styling, etc.)
• The extension can be successfully built and packaged on all supported platforms (Windows, macOS, Linux)
• Maintainers respond to issues and pull request submitted to the extension's repository.
• Maintainers respond to questions directly addressed to him/her via @mention on the Slicer Forum.
• Permissive license is used for the main functions of the extension (recommended Apache or MIT). The extension can provide additional functionality in optional components that are distributed with non-permissive license, but the user has to explicitly approve those before using them (e.g., a pop-up can be displayed that explains the licensing terms and the user has to acknowledge them to proceed).
• All requirements of tiers < 3.

Tier 5

Critically important extensions, supported by Slicer core developers. New Slicer Stable Release is released only if all Tier 5 extension packages are successfully created on all supported platforms.

• Slicer core developers accept the responsibility of fixing any issues caused by Slicer core changes; at least one Slicer core developer (anyone who has commit right to Slicer core) must be granted commit right to the extension's repository.
• Automated tests for all critical features.
• Maintainers respond to questions related to the extension on the Slicer Forum.
• All requirements of tiers < 5.

---

This PR adds SlicerKonfAI, a new extension providing a graphical interface in 3D Slicer to run KonfAI Apps for medical image segmentation, synthetic CT generation, and related deep learning tasks.

SlicerKonfAI serves as the backend architecture for upcoming tools, including:

• ImpactSynth – MR-to-CT and CBCT-to-CT medical image synthesis
• ImpactReg – multimodal deformable registration

These applications will be packaged as KonfAI Apps and executed seamlessly within SlicerKonfAI.

---

Pre-included Apps and Models

This initial release already ships with several ready-to-use models:

Medical image synthesis

• MR and CBCT ➜ CT synthesis

Segmentation

• TotalSegmentator and MRSegmentator integrated via KonfAI
  (improved inference performance)

---

Main capabilities

• Load volumes directly from Slicer and run KonfAI Apps
• GPU acceleration when available
• Visualization of predictions as segmentations or volumes
• Optional evaluation and uncertainty estimation workflows
• Automatic download and versioning of Apps hosted on Hugging Face
• Extensible design for adding new KonfAI apps

[lassoan]

Thanks for the submission. There are a few failing checks:

• ❌ Check category failed: Category Deep Learning is unknown. Consider using any of the known extensions instead: Active Learning, Analysis, Auto3dgm, BigImage, Cardiac, Chest Imaging Platform, Conda, Converters, DICOM, DSCI, Developer Tools, Diffusion, Examples, Exporter, FTV Segmentation, Filtering, Filtering.Morphology, Filtering.Vesselness, Holographic Display, Image Synthesis, IGT, Informatics, Netstim, Neuroimaging, Nuclear Medicine, Orthodontics, Osteotomy Planning, Otolaryngology, Photogrammetry, Pipelines, Planning, Printing, Quantification, Radiotherapy, Registration, Remote, Rendering, SPHARM, Segmentation, Sequences, Shape Analysis, Shape Regression, Shape Visualization, Simulation, SlicerCMF, SlicerMorph, Spectral Imaging, Supervisely, Surface Models, SurfaceLearner, Tomographic Reconstruction, Tracking, Tractography, Training, Ultrasound, Utilities, Vascular Modeling Toolkit, Virtual Reality, VisSimTools, Web System Tools, Wizards
• ❌ Check CMakeLists.txt content failed: Extension name in CMakeLists.txt project name 'SlicerKonfAI' does not match extension description file name 'KonfAI'. Please modify project name in CMakeLists.txt to 'KonfAI'
• It is not allowed to run pip_install in the file scope (as it would slow down Slicer application startup, even if the user does not even open your module). You can install konfai when you actually need it (when the user activates the module, but preferably when a konfai feature is needed). Accordingly, all konfai imports should not be at the file scope but in the method that actually needs it.

[vboussot]

Thanks for the review.

The extension category has been updated from Deep Learning to Pipelines, as this is the closest matching category among the allowed ones.

The project name in CMakeLists.txt now matches the extension name (KonfAI).

pip_install calls and konfai imports have been removed from the file scope and are now deferred to runtime when the module is actually used,

[lassoan]

It looks good, thank you!

[lassoan]

The extension is added to the index, thank you for your contribution! Excellent work!

A few improvements that I would recommend to make the extension more user-friendly:

• Include a step-by-step tutorial that shows on a simple example what the extension can do (similar to this)
• In the first few paragraphs of the README.md file, make it more clear that this extension is for clinicians. Currently, the text like "you train and package your models as KonfAI Apps, and SlicerKonfAI lets clinicians load volumes" may suggest that it is a developer tool. The extension is actually usable for clinicians, so when you write "you" then it should refer to the clinicians. You can add a "Developer" section later where you talk to developers and explain concepts that are important for developers.
• Installation of dependencies take a while - especially if someone has slow network connection - and there is no indication that something is happening. There is a risk that a user just force quits the application (leaving some packages half installed), which may be hard to recover from. To avoid this, it could be sufficient to show a popup that "Please wait, installing additional Python packages, this may take severl minutes".
• You currently load the segmentation result as labelmap volume node. It is quite limited what you can do with a labelmap, it would be much better to load it as a segmentation node. You can load the segmentation result directly from nrrd or nifti file as shown here.
• It is essential to have name (but preferably also terminology) specified for each segment. It is really simple to achieve it now: create a .csv file that specifies name, color (optionally also terminology), load that file into Slicer as a color node, and then specify the color node when you load the segmentation.
• Add a "Show 3D" button to show segmentation results in 3D

[jamesobutler]

@vboussot This extension has a build error as seen at https://slicer.cdash.org/builds/4038178/configure:

CMake Error at KonfAI/CMakeLists.txt:35 (add_subdirectory):
  The source directory

    C:/D/P/S-0-E-b/KonfAI/KonfAI/Testing

  does not contain a CMakeLists.txt file.

[vboussot]

@jamesobutler Thank you for pointing this out. I’ve added the missing file.

[vboussot]

@lassoan Thank you for the review and the recommendations, I’ve made the changes.