Profile Imaging · Aperivue/medsci-skills
Audit medical imaging datasets before training a model
Scans a medical-imaging dataset's acquisition grid, voxel spacing, intensity range, label presence, and target volume, then checks those facts against the stated research plan. Useful before training, to catch missing test-set labels, mismatched grids, or metrics unsuited to a small target.
Good for
- Check voxel spacing and orientation before preprocessing
- Verify a labeled test set actually has ground truth
- Estimate target volume to pick the right evaluation metric
- Source repository
- Aperivue/medsci-skills
- Category
- Medicine
Open-source skills are maintained by their authors and listed as published, with attribution. Results depend on how well the skill fits your task and material.
A good place to start
Profile my NIfTI dataset and tell me if it's ready to train on, including voxel spacing and label issues.
Make your next great thing.
Bring a question, a file, or an idea that’s not quite there yet.