DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to segment CT organs locally with AI and refine the result with Voxenra

Run TotalSegmentator on a CT study inside Voxenra, then check and correct the organ masks before saving.

Who it is forA radiology researcher or imaging analyst who has a CT study and needs organ masks quickly without sending data to a cloud service.

The problemManual organ contouring on CT takes a long time, and automatic masks still need checking before they can be used.

The outcomeOrgan masks for the selected structures overlaid on the MPR views, refined with brush or eraser, and saved in the workspace or exported as SEG or NRRD.

What you need first

  • Python with uv installed, so the README command `uv run voxenra` works
  • Local DICOM, NRRD or PACS-accessible CT, MR or PET/CT data you are allowed to use
  • For AI auto-segmentation: a separately installed TotalSegmentator environment and CT fast model, detected under Settings → AI
  • A desktop OS: macOS Apple Silicon or Windows x64 release builds are listed, or a source checkout run with uv

Steps

  1. Clone the repo from https://github.com/l5769389/voxenra and enter the folder.
  2. Install TotalSegmentator and its CT fast model separately, then open Settings → AI and check that the environment is detected.
  3. Run uv run voxenra, import your CT study, and open it in MPR or 4D.
  4. Search for and tick the organs you need (the default is liver, spleen and both kidneys), then start the local inference on the current phase.
  5. Review the overlay in the three planes, correct errors with the brush or eraser, and use undo where needed.
  6. Save the workspace, or export the segmentation as SEG or NRRD.

Prompt for your agent

Work in the repo l5769389/voxenra. Run `uv run voxenra`, open the CT study at <path to CT study>, and run TotalSegmentator on the liver and spleen. Report the saved file path and confirm the masks appear in the axial, coronal and sagittal views.

Caveat. The README says the demo is a synthetic phantom and does not show model accuracy or compute time, so check AI masks against the images before relying on them.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page