# COMPASS: Robust Feature Conformal Prediction for Medical Segmentation Metrics

arXiv: https://arxiv.org/abs/2509.22240 · HTML: https://mlsanity.com/paper/2509.22240/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 43 references that are in the map.
- First posted on arXiv 26 Sep 2025.

## Builds on (most cited first, 26 of 26)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges](https://mlsanity.com/paper/2011.06225/) (2020)
- [A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification](https://mlsanity.com/paper/2107.07511/) (2021)
- [Distribution-Free Predictive Inference For Regression](https://mlsanity.com/paper/1604.04173/) (2016)
- [Conformalized Quantile Regression](https://mlsanity.com/paper/1905.03222/) (2019)
- [Kvasir-SEG: A Segmented Polyp Dataset](https://mlsanity.com/paper/1911.07069/) (2019)
- [Conformal Prediction Under Covariate Shift](https://mlsanity.com/paper/1904.06019/) (2019)
- [MONAI: An open-source framework for deep learning in healthcare](https://mlsanity.com/paper/2211.02701/) (2022)
- [Conformal prediction beyond exchangeability](https://mlsanity.com/paper/2202.13415/) (2022)
- [3D MRI brain tumor segmentation using autoencoder regularization](https://mlsanity.com/paper/1810.11654/) (2018)
- [Conformal Risk Control](https://mlsanity.com/paper/2208.02814/) (2022)
- [Tversky loss function for image segmentation using 3D fully convolutional deep networks](https://mlsanity.com/paper/1706.05721/) (2017)
- [Conformal Prediction: a Unified Review of Theory and New Challenges](https://mlsanity.com/paper/2005.07972/) (2020)
- [Regression Conformal Prediction with Nearest Neighbours](https://mlsanity.com/paper/1401.3880/) (2014)
- [Predictive Inference with Feature Conformal Prediction](https://mlsanity.com/paper/2210.00173/) (2022)
- [Principal Uncertainty Quantification with Spatial Correlation for Image Restoration Problems](https://mlsanity.com/paper/2305.10124/) (2023)
- [Conformal Semantic Image Segmentation: Post-hoc Quantification of Predictive Uncertainty](https://mlsanity.com/paper/2405.05145/) (2024)
- [On the use of Mahalanobis distance for out-of-distribution detection with neural networks for medical imaging](https://mlsanity.com/paper/2309.01488/) (2023)
- [Kandinsky Conformal Prediction: Efficient Calibration of Image Segmentation Algorithms](https://mlsanity.com/paper/2311.11837/) (2023)
- [Conformal Prediction for Image Segmentation Using Morphological Prediction Sets](https://mlsanity.com/paper/2503.05618/) (2025)
- [Dimensionality Reduction for Improving Out-of-Distribution Detection in Medical Image Segmentation](https://mlsanity.com/paper/2308.03723/) (2023)
- [Conformal confidence sets for biomedical image segmentation](https://mlsanity.com/paper/2410.03406/) (2024)
- [Robust Conformal Volume Estimation in 3D Medical Images](https://mlsanity.com/paper/2407.19938/) (2024)
- [EBHI:A New Enteroscope Biopsy Histopathological H&E Image Dataset for Image Classification Evaluation](https://mlsanity.com/paper/2202.08552/) (2022)
- [Metric-Guided Conformal Bounds for Probabilistic Image Reconstruction](https://mlsanity.com/paper/2404.15274/) (2024)
- [Predictive Inference With Fast Feature Conformal Prediction](https://mlsanity.com/paper/2412.00653/) (2024)

## Built on by (most cited first, 4 of 4)

- [Efficient Conformal Volumetry for Template-Based Segmentation](https://mlsanity.com/paper/2603.00798/) (2026)
- [ConRad: Efficient Conformal Prediction for Radiomics](https://mlsanity.com/paper/2607.08084/) (2026)
- [Subtype Robustness Is Not Just Accuracy: Calibration Under Unseen Subtype Shift](https://mlsanity.com/paper/2608.00928/) (2026)
- [Bound-Aware Per-Organ Recall Risk Control for Multi-Organ CT Segmentation under Clinical Domain Shift](https://mlsanity.com/paper/2608.18193/) (2026)

## Abstract (arXiv)

In clinical applications, the utility of segmentation models is often based on the accuracy of derived downstream metrics such as organ size, rather than by the pixel-level accuracy of the segmentation masks themselves. Thus, uncertainty quantification for such metrics is crucial for decision-making. Conformal prediction (CP) is a popular framework to derive such principled uncertainty guarantees, but applying CP naively to the final scalar metric is inefficient because it treats the complex, non-linear segmentation-to-metric pipeline as a black box. We introduce COMPASS, a practical framework that generates efficient, metric-based CP intervals for image segmentation models by leveraging the inductive biases of their underlying deep neural networks. COMPASS performs calibration directly in the model's representation space by perturbing intermediate features along low-dimensional subspaces maximally sensitive to the target metric. We prove that COMPASS achieves valid marginal coverage under the assumption of exchangeability. Empirically, we demonstrate that COMPASS produces significantly tighter intervals than traditional CP baselines on four medical image segmentation tasks for area estimation of skin lesions and anatomical structures. Furthermore, we show that leveraging learned internal features to estimate importance weights allows COMPASS to also recover target coverage under covariate shifts. COMPASS paves the way for practical, metric-based uncertainty quantification for medical image segmentation.