ConRad: Efficient Conformal Prediction for Radiomics
For clinical imaging pipelines relying on radiomic features, ConRad provides more reliable uncertainty quantification by leveraging test-time covariates, addressing the problem of overconfident segmentation models.
ConRad uses conformal prediction to construct adaptive prediction intervals for radiomic features derived from predicted segmentation masks, improving efficiency across five 2D medical imaging datasets and 171 radiomic targets while maintaining near-nominal coverage.
Radiomic features derived from medical images and segmentation masks are used to support decision making in clinical imaging pipelines. In practice, these features are often computed from predicted masks, but segmentation models can be overconfident or poorly calibrated, making derived measurements appear more reliable than they are. Conformal prediction (CP) provides distribution-free prediction intervals with finite-sample marginal coverage guarantees, but black-box intervals for segmentation-derived radiomics can be inefficient because they ignore test-time information about image appearance, mask geometry, and segmentation uncertainty. We propose ConRad, a conformal framework for scalar radiomic targets that uses covariates derived from the predicted mask, input image, predicted radiomics, and boundary uncertainty to construct adaptive intervals while maintaining coverage. Across five 2D medical imaging datasets and 171 retained radiomic targets, we show that ConRad improves feature-level efficiency compared to baselines while maintaining near-nominal empirical coverage. Ablation results further indicate that segmentation boundary uncertainty features are the largest contributors to interval efficiency.