Project-MONAI / Project-MONAI/tutorials

Data preparation for MAISI tutorial is wrong for non-RAS data

Open
#2,012 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Jupyter Notebook
Stars
2.5k
Forks
803
Avg merge
6d 22h
Merged PRs (30d)
3

Description

https://github.com/Project-MONAI/tutorials/blob/8b90a16d82a463551d81dd4da200f3d406c6843e/generation/maisi/scripts/diff_model_create_training_data.py#L199

In the data preparation, the plain_transforms uses monai.transforms.Orientationd(keys="image", axcodes="RAS"), to reorient the image, but the new dimension is set using plain_transforms({"image": os.path.join(args.data_base_dir, filepath)})["image"].meta["dim"][_i] which has the original dimension, not the new dimension.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start at generation/maisi/scripts/diff_model_create_training_data.py around line 199 and inspect how plain_transforms reorients non-RAS images before the dimension is recorded. Verify that the dimension used for training-data preparation reflects the reoriented image, then run the tutorial's available data-preparation checks to confirm non-RAS inputs produce correct dimensions.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Clearly specified
Newbie friendliness
55/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.