Lightning-AI / Lightning-AI/torchmetrics

Implement surface distance/dice scores

Open
#1,900 1 comment 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement New metric
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

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 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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.