# Average Calibration Losses for Reliable Uncertainty in Medical Image Segmentation

arXiv: https://arxiv.org/abs/2506.03942 · HTML: https://mlsanity.com/paper/2506.03942/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 50 references that are in the map.
- First posted on arXiv 4 Jun 2025.

## Builds on (most cited first, 30 of 34)

- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classification](https://mlsanity.com/paper/2107.02314/) (2021)
- [MONAI: An open-source framework for deep learning in healthcare](https://mlsanity.com/paper/2211.02701/) (2022)
- [AMOS: A Large-Scale Abdominal Multi-Organ Benchmark for Versatile Medical Image Segmentation](https://mlsanity.com/paper/2206.08023/) (2022)
- [3D MRI brain tumor segmentation using autoencoder regularization](https://mlsanity.com/paper/1810.11654/) (2018)
- [On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks](https://mlsanity.com/paper/1905.11001/) (2019)
- [A Probabilistic U-Net for Segmentation of Ambiguous Images](https://mlsanity.com/paper/1806.05034/) (2018)
- [nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image Segmentation](https://mlsanity.com/paper/2404.09556/) (2024)
- [The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 Challenge](https://mlsanity.com/paper/1912.01054/) (2019)
- [Confidence Calibration and Predictive Uncertainty Estimation for Deep Medical Image Segmentation](https://mlsanity.com/paper/1911.13273/) (2019)
- [PHiSeg: Capturing Uncertainty in Medical Image Segmentation](https://mlsanity.com/paper/1906.04045/) (2019)
- [Improving model calibration with accuracy versus uncertainty optimization](https://mlsanity.com/paper/2012.07923/) (2020)
- [Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty](https://mlsanity.com/paper/2006.06015/) (2020)
- [Local Temperature Scaling for Probability Calibration](https://mlsanity.com/paper/2008.05105/) (2020)
- [Soft Calibration Objectives for Neural Networks](https://mlsanity.com/paper/2108.00106/) (2021)
- [A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network Calibration](https://mlsanity.com/paper/2203.13834/) (2022)
- [A Consistent and Differentiable Lp Canonical Calibration Error Estimator](https://mlsanity.com/paper/2210.07810/) (2022)
- [Improved Trainable Calibration Method for Neural Networks on Medical Imaging Classification](https://mlsanity.com/paper/2009.04057/) (2020)
- [Meta-Calibration: Learning of Model Calibration Using Differentiable Expected Calibration Error](https://mlsanity.com/paper/2106.09613/) (2021)
- [QU-BraTS: MICCAI BraTS 2020 Challenge on Quantifying Uncertainty in Brain Tumor Segmentation - Analysis of Ranking Scores and Benchmarking Results](https://mlsanity.com/paper/2112.10074/) (2021)
- [Automated 3D Segmentation of Kidneys and Tumors in MICCAI KiTS 2023 Challenge](https://mlsanity.com/paper/2310.04110/) (2023)
- [Calibrating the Dice loss to handle neural network overconfidence for biomedical image segmentation](https://mlsanity.com/paper/2111.00528/) (2021)
- [Trust your neighbours: Penalty-based constraints for model calibration](https://mlsanity.com/paper/2303.06268/) (2023)
- [Reassessing How to Compare and Improve the Calibration of Machine Learning Models](https://mlsanity.com/paper/2406.04068/) (2024)
- [Uncertainty Aware Training to Improve Deep Learning Model Calibration for Classification of Cardiac MR Images](https://mlsanity.com/paper/2308.15141/) (2023)

## Built on by (most cited first, 3 of 3)

- [Uncovering Overconfident Failures in CXR Models via Augmentation-Sensitivity Risk Scoring](https://mlsanity.com/paper/2510.01683/) (2025)
- [Automated Labeling of Intracranial Arteries with Uncertainty Quantification Using Deep Learning](https://mlsanity.com/paper/2509.17726/) (2025)
- [CARD: Calibration via Agreement in Reverse Diffusion for Out-of-Domain MRI Segmentation](https://mlsanity.com/paper/2608.28681/) (2026)

## Abstract (arXiv)

Deep neural networks for medical image segmentation are often overconfident, compromising both reliability and clinical utility. In this work, we propose differentiable formulations of marginal L1 Average Calibration Error (mL1-ACE) as an auxiliary loss that can be computed on a per-image basis. We compare both hard- and soft-binning approaches to directly improve pixel-wise calibration. Our experiments on four datasets (ACDC, AMOS, KiTS, BraTS) demonstrate that incorporating mL1-ACE significantly reduces calibration errors, particularly Average Calibration Error (ACE) and Maximum Calibration Error (MCE), while largely maintaining high Dice Similarity Coefficients (DSCs). We find that the soft-binned variant yields the greatest improvements in calibration over the DSC plus cross-entropy loss baseline but often compromises segmentation performance, with hard-binned mL1-ACE maintaining segmentation performance, albeit with weaker calibration improvement. To gain further insight into calibration performance and its variability across an imaging dataset, we introduce dataset reliability histograms, an aggregation of per-image reliability diagrams. The resulting analysis highlights improved alignment between predicted confidences and true accuracies. Overall, our approach provides practitioners with explicit control over the calibration-accuracy trade-off, enabling more reliable integration of deep learning methods into clinical workflows. We share our code here: https://github.com/cai4cai/Average-Calibration-Losses