Clinical Measurements with Calibrated Instance-Dependent Confidence Interval

Rotem Nizhar, Lior Frenkel, Jacob Goldberger

Keywords: confidence interval, uncertainty calibration, conformal prediction

TL;DR: We propose an instance based calibration method for a confidence interval of a network prediction

Abstract: Reporting meaningful confidence intervals for the predictions of a regression neural network is critical in medical imaging applications since clinical decisions are based on network predictions. We expect to obtain larger intervals for difficult examples and smaller ones for easier examples to predict. A recently proposed calibration procedure suggests predicting the mean and the variance and scaling the variance on a validation set. Another calibration approach is based on applying conformal prediction to quantile regression. We show that assuming a Gaussian distribution to predict the variance followed by a non-parametric Conformal Prediction technique to scale the estimated variance is the most effective way of achieving a small confidence interval with a coverage guarantee. We report extensive experimental results on various medical imaging datasets and network architectures.

Primary Subject Area: Uncertainty Estimation

Secondary Subject Area: Interpretability and Explainable AI

Paper Type: Both

Registration Requirement: Yes

Reproducibility: https://github.com/rotem1023/Calibrated-Instance-Dependent

Midl Latex Submission Checklist: Ensure no LaTeX errors during compilation., Created a single midl25_NNN.zip file with midl25_NNN.tex, midl25_NNN.bib, all necessary figures and files., Includes \documentclass{midl}, \jmlryear{2025}, \jmlrworkshop, \jmlrvolume, \editors, and correct \bibliography command., Did not override options of the hyperref package, Did not use the times package., All authors and co-authors are correctly listed with proper spelling and avoid Unicode characters., Author and institution details are de-anonymized where needed. All author names, affiliations, and paper title are correctly spelled and capitalized in the biography section., References must use the .bib file. Did not override the bibliographystyle defined in midl.cls. Did not use \begin{thebibliography} directly to insert references., Tables and figures do not overflow margins; avoid using \scalebox; used \resizebox when needed., Included all necessary figures and removed *unused* files in the zip archive., Removed special formatting, visual annotations, and highlights used during rebuttal., All special characters in the paper and .bib file use LaTeX commands (e.g., \'e for é)., Appendices and supplementary material are included in the same PDF after references., Main paper does not exceed 9 pages; acknowledgements, references, and appendix start on page 10 or later.

Submission Number: 164