Project-MONAI / Project-MONAI/model-zoo
PRE-PROCESSING QUESTION ABOUT Wholebrainseg large unest segmentation
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 338
- Forks
- 106
- PR merge metrics
- No merged PRs in 30d
Description
I have followed the pre-processing scheme as indicated in the paper Huo et.all; and when executing inference the output is not as expected, so: What is the order and steps I should apply to images in order to obtain the masks provided in the description???????
This is my actual pre-processing pipeline: Skull stripping > Bias field correction > Registration to MNI305 > Intensity rescaling [-1,1] > Random cropping 96x96x96. (Of course input images to this pre-processing pipeline have 240x240x155 (dimensions) and 1x1x1 (voxel size)
I have removed histogram matching (after proving it) since it does not make sense (I am just executing inference with T1 weighted images).
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 Huo et al. paper and comparing its preprocessing scheme with the reported pipeline: skull stripping, bias field correction, MNI305 registration, intensity rescaling, and random cropping. Done means establishing and documenting the preprocessing order and steps that reproduce the masks described for the Wholebrainseg model.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100