mlsanityData to 14 Oct 2026

Conformal Prediction for Image Segmentation Using Morphological Prediction Sets

arXiv 2503.05618 ↗First posted 7 Mar 2025cs.CV cs.LGcited by 14

Not on the map. Why?

Abstract (arXiv)

Image segmentation is a challenging task influenced by multiple sources of uncertainty, such as the data labeling process or the sampling of training data. In this paper we focus on binary segmentation and address these challenges using conformal prediction, a family of model- and data-agnostic methods for uncertainty quantification that provide finite-sample theoretical guarantees and applicable to any pretrained predictor. Our approach involves computing nonconformity scores, a type of prediction residual, on held-out calibration data not used during training. We use dilation, one of the fundamental operations in mathematical morphology, to construct a margin added to the borders of predicted segmentation masks. At inference, the predicted set formed by the mask and its margin contains the ground-truth mask with high probability, at a confidence level specified by the user. The size of the margin serves as an indicator of predictive uncertainty for a given model and dataset. We work in a regime of minimal information as we do not require any feedback from the predictor: only the predicted masks are needed for computing the prediction sets. Hence, our method is applicable to any segmentation model, including those based on deep learning; we evaluate our approach on several medical imaging applications.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 21 of its 36 references that are in the map. First posted on arXiv 7 Mar 2025.

Builds on

21 of 36 references.

References · 21

  1. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 913
  2. 2020PraNet: Parallel Reverse Attention Network for Polyp Segmentationcited by 460
  3. 2022Conformal Risk Controlcited by 299
  4. 2021Distribution-Free, Risk-Controlling Prediction Setscited by 288
  5. 2016A Benchmark for Endoluminal Scene Segmentation of Colonoscopy Imagescited by 221
  6. 2023Conformal Prediction With Conditional Guaranteescited by 152
  7. 2024Theoretical Foundations of Conformal Predictioncited by 101
  8. 2023UniverSeg: Universal Medical Image Segmentationcited by 91
  9. 2019Nested conformal prediction and quantile out-of-bag ensemble methodscited by 89
  10. 2022Trustworthy clinical AI solutions: a unified review of uncertainty quantification in deep learning models for medical image analysiscited by 63
  11. 2023How to Trust Your Diffusion Model: A Convex Optimization Approach to Conformal Risk Controlcited by 50
  12. 2022Learning the Effect of Registration Hyperparameters with HyperMorphcited by 35
9 more
  1. 2023Loss Functions in the Era of Semantic Segmentation: A Survey and Outlookcited by 34
  2. 2024Adaptive Bounding Box Uncertainties via Two-Step Conformal Predictioncited by 23
  3. 2023Confident Object Detection via Conformal Prediction and Conformal Risk Control: an Application to Railway Signalingcited by 22
  4. 2024Conformal Semantic Image Segmentation: Post-hoc Quantification of Predictive Uncertaintycited by 20
  5. 2024Automatically Adaptive Conformal Risk Controlcited by 16
  6. 2022Towards PAC Multi-Object Detection and Trackingcited by 8
  7. 2023Conformal Prediction for Trustworthy Detection of Railway Signalscited by 7
  8. 2024Conformal confidence sets for biomedical image segmentationcited by 6
  9. 2024Spatial-Aware Conformal Prediction for Trustworthy Hyperspectral Image Classificationcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 10.

14 papers.

Sort:

By area:

  1. 2025Conditional Conformal Risk Adaptationcited by 7
  2. 2025COMPASS: Robust Feature Conformal Prediction for Medical Segmentation Metricscited by 4
  3. 2025CONSIGN: Conformal Segmentation Informed by Spatial Groupings via Decompositioncited by 3
  4. 2025Controlling False Positives in Image Segmentation via Conformal Predictioncited by 1
  5. 2026Conformal Prediction Sets for Instance Segmentationcited by 1
  6. 2026Elements of Conformal Predictioncited by 1
  7. 2026Anatomically-aware conformal prediction for medical image segmentation with random walkscited by 0
  8. 2026Trustworthy Endoscopic Super-Resolutioncited by 0
  9. 2026Adaptive Conformal Prediction for Reliable and Explainable Medical Image Classificationcited by 0
  10. 2026When Average Calibration Fails: Site-Conditional Federated Conformal Risk Controlcited by 0
  11. 2026ConRad: Efficient Conformal Prediction for Radiomicscited by 0
  12. 2026VIDS-Seg: Towards Reliable Uncertainty Quantification in Pediatric Cardiac Ultrasound Segmentationcited by 0
2 more
  1. 2026Bound-Aware Per-Organ Recall Risk Control for Multi-Organ CT Segmentation under Clinical Domain Shiftcited by 0
  2. 2026Trust Before Autonomy: Rethinking Agentic Remote Sensing for Crisis Responsecited by 0