Lightning-AI / Lightning-AI/torchmetrics
Implement surface distance/dice scores
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2.5k
- Forks
- 526
- Avg merge
- 6d 11h
- Merged PRs (30d)
- 5
Description
## 🚀 Feature
Hi! It would be great to include surface distance/dice scores from https://github.com/deepmind/surface-distance ( https://docs.monai.io/en/stable/metrics.html#average-surface-distance, https://docs.monai.io/en/stable/metrics.html#surface-dice).
### Motivation
NSD (Normalized Surface DICE) is quite present in the medical image segmentation community.
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 DeepMind surface-distance project and the MONAI documentation for average surface distance and surface Dice. Then inspect the repository's existing segmentation metric entry points and tests, which the issue does not name. Done means both requested scores are exposed as usable TorchMetrics metrics with appropriate coverage.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100