Project-MONAI / Project-MONAI/monai-deploy-app-sdk
[IMP] Enhancing Series Selection Operation
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 138
- Forks
- 70
- PR merge metrics
- No merged PRs in 30d
Description
Is your enhancement request related to a problem? Please describe.
For MONAI Deploy. noninformative and ever changing and often misleading series description, we need to have a better series selection mechanism in addition to regex based searches. This might include
- Passing known dicom tags to the series selector
- Ability to perform logical AND/OR operations on the series selection parameters.
- In addition, it will be also awesome to confirm that appropriate series is selected through some image fingerprinting.
Image fingerprinting is a mechanism to identify the anatomical structure present in the image as well as the imaging modality used. Total Segmentator has an implementation which we can borrow. In that they extract characteristics of the image like
- foreground to background ratio
- mean intensity and standard deviation on the intensities
- slice thickness
- image size (rows X columns)
- radiomics features.
We can come up with an operator where we can leverage this implementation to confirm/identify the appropriate images in the image series.
Additional context
I have done some work on series renaming. Need to add more functionality into it.
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 series-renaming work in the linked SeriesNaming project and the referenced TotalSegmentator statistics.py implementation. Clarify how known DICOM tags, logical selection operations, and image fingerprinting should fit the series selector. Done requires an agreed scope and working support for the selected enhancement criteria.
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
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100