Skip to content

Conformalization of Segmentation by Margin expansion. Uncertainty quantification in image segmentation with conformal prediction and mathematical morphology (arXiv:2503.05618)

License

Notifications You must be signed in to change notification settings

deel-ai-papers/consema

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ConSeMa: conformalization of segmentation by margin expansion

Code repository for the paper:

Mossina L. & Friedrich L. (2025). Conformal Prediction for Image Segmentation Using Morphological Prediction Sets. arXiv preprint arXiv:2503.05618.

Idea

Use morphological operations (dilation) to add a margin around a predicted (binary) segmentation mask, such that the ground-truth mask is covered with high probability via conformal prediction.

In the synthetic example below, the red pixels (bold contours) are false negatives, that is, they belong to the ground truth but were not predicted. The animation shows five sequential dilations by a (3X3) cross structuring element, which expand the margin of the predicted mask (darker blue). Three iterations is the minimal number of iterations needed, i.e. the nonconformity score: all missing pixels are recovered (shown in orange).

Dilation Animation

Examples

The directory notebooks contains complete examples for the datasets:

  • WBC and OASIS, using the UniverSeg segmentation model
  • polyps tumors dataset, using PraNet (we use precomputed predictions as distributed by A. Angelopoulos.

References & sources

Starting points for datasets:

Models used:

Citation

@article{Mossina_2025_conformal,
  title={Conformal Prediction for Image Segmentation Using Morphological Prediction Sets},
  author={Mossina, Luca and Friedrich, Corentin},
  journal={arXiv preprint arXiv:2503.05618},
  year={2025}
}

About

Conformalization of Segmentation by Margin expansion. Uncertainty quantification in image segmentation with conformal prediction and mathematical morphology (arXiv:2503.05618)

Topics

Resources

License

Stars

Watchers

Forks

Packages

No packages published