Project-MONAI / Project-MONAI/monai-deploy-app-sdk
[FEA] Developing applications with non dicom data (Image Reconstruction)
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 138
- Forks
- 70
- PR merge metrics
- No merged PRs in 30d
Description
We should work on developing an example with Image Reconstruction when there is data which do not necessarily have dicom information. One of the interesting things to do will be to develop a sample application for deep learning based MRI reconstruction. I will be keen to build and train such a model. I have identified a dataset. Please let me know if someone is interested in developing such model and then we can package it. If someone is interested in any other dataset please do let me know.
Thanks
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 reviewing the linked fastMRI dataset and the repository's existing application examples; the issue names no specific files, tests, or entry points. Define a sample MRI reconstruction application for non-DICOM data, train a deep-learning model, and package the resulting application as the completed work.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100