[PW41] Add MRSegmentator Model

[FJDorfner]

Pull Request to add the MRSegmentator model to mhub.

[LennyN95]

Great Work!!

I suggested some minor changes. I'll update segdb and once we have that we can continue with the test routine. Thx @FJDorfner, very clean and to the point :)

[LennyN95]

I'll add SPINE to SegDB. I can lookup the codes, but feel free to add SCT code's if you already have them ;))

[LennyN95]

@FJDorfner We're adding a quite broad label here, can you explain weather the model delineates the entire spine or the bone-structure of the spine?

[FJDorfner]

Hi @LennyN95, the model segments the bodies of the vertebrae individually. The disk between is not included in the label. This would be the yellow label in the attached Screenshot as a visual:)

[LennyN95]

• TODO @LennyN95: Add support for multi-modality inputs. Dash separation is a good idea and in line with DTQ syntax.

[LennyN95]

@FJDorfner since all comments from the previous review are now implemented, we can continue with the testing procedure.

[FJDorfner]

@LennyN95 Thanks! I will continue with the testing.

[LennyN95]

Please note, we updated our base image. All mhub dependencies are now installed in a virtual environment under /app/.venv running Python 3.11. Python, virtual environment and dependencies are now managed with uv. If required, you can create custom virtual environments, e.g., uv venv -p 3.8 .venv38 and use uv pip install -p .venv38 packge-name to install dependencies and uv run -p .venv3.8 python script.py to run a python script.

We also simplified our test routine. Sample and reference data now have to be uploaded to Zenodo and provided in a mhub.tom file at the project root. The process how to create and provide these sample data is explained in the updated testing phase article of our documentation. Under doi.org/10.5281/zenodo.13785615 we provide sample data as a reference.

[LennyN95]

Thank you @FJDorfner for fixing the issues. Looks good!
I started the testing on this PR ;)

[LennyN95]

Test Results

id: e458deff-2799-47a1-9ac9-90f40b6e7573
name: MHub Test Report (default)
date: '2025-03-25 11:45:30'
checked_files:
- file: MRSegmentator.seg.dcm
  path: /app/data/output_data/1.3.6.1.4.1.14519.5.2.1.1.34685322639756871092106477180544961507/MRSegmentator.seg.dcm
  checks:
  - checker: DicomsegContentCheck
    notes:
    - label: Segment Count
      description: The number of segments identified in the inspected dicomseg file.
      info: 32
summary:
  files_missing: 0
  files_extra: 0
  checks:
    DicomsegContentCheck:
      files: 1
conclusion: true

[FJDorfner]

Hey @LennyN95, thank you for your help with the contribution process!

[LennyN95]

@FJDorfner Do you have any preferred preview images for the website? Feel free to upload them here and I'll add them :)

[FJDorfner]

Tagging @hhaentze, who built the MRSegmentator here. Do you have preferred preview images?

@FJDorfner Do you have any preferred preview images for the website? Feel free to upload them here and I'll add them :)

[hhaentze]

We can use the same figures as in the paper.

[FJDorfner]

Thank you @hhaentze for the images and thank you @LennyN95 for completing the contribution!