OpenwaterHealth / OpenwaterHealth/openlifu-python
Add the MRI segmentation method for the Sonication Planning
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 27
- Forks
- 21
- Avg merge
- 1d 20m
- Merged PRs (30d)
- 6
Description
Currently in https://github.com/OpenwaterHealth/OpenLIFU-python/issues/126, we are computing a default simulation grid full of water with ref_params, if a volume is provided we segment it as water with seg_params. With the coordinates defined by parameters from sim_setup in example_protocol.json.
The goal is to instead take into account the physical properties of the brain (tissues, g/w matter, air, bone), by fully segmenting the MRI head. Then each voxel has different physical properties depending on the detected instance.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reading the referenced code in src/openlifu/sim/sim_setup.py and the coordinate parameters in tests/resources/example_db/protocols/example_protocol/example_protocol.json. Review issue #126 to understand the current default and volume segmentation behavior. Done means replacing the water-only treatment with MRI head segmentation that assigns physical properties to detected tissues, including gray and white matter, air, and bone.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100