mlsanityData to 14 Oct 2026

Maximum Entropy on Erroneous Predictions (MEEP): Improving model calibration for medical image segmentation

arXiv 2112.12218 ↗First posted 22 Dec 2021cs.CV cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

Modern deep neural networks achieved remarkable progress in medical image segmentation tasks. However, it has recently been observed that they tend to produce overconfident estimates, even in situations of high uncertainty, leading to poorly calibrated and unreliable models. In this work we introduce Maximum Entropy on Erroneous Predictions (MEEP), a training strategy for segmentation networks which selectively penalizes overconfident predictions, focusing only on misclassified pixels. Our method is agnostic to the neural architecture, does not increase model complexity and can be coupled with multiple segmentation loss functions. We benchmark the proposed strategy in two challenging segmentation tasks: white matter hyperintensity lesions in magnetic resonance images (MRI) of the brain, and atrial segmentation in cardiac MRI. The experimental results demonstrate that coupling MEEP with standard segmentation losses leads to improvements not only in terms of model calibration, but also in segmentation quality.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 29 of its 43 references that are in the map. First posted on arXiv 22 Dec 2021.

Builds on

29 of 43 references.

References · 29

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  3. 2017On Calibration of Modern Neural Networkscited by 4,960
  4. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  5. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  6. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,292
  7. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,287
  8. 2019When Does Label Smoothing Help?cited by 988
  9. 2017Regularizing Neural Networks by Penalizing Confident Output Distributionscited by 464
  10. 2019Deep Ensembles: A Loss Landscape Perspectivecited by 443
  11. 2019Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentationcited by 379
  12. 2020BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learningcited by 371
17 more
  1. 2020Calibrating Deep Neural Networks using Focal Losscited by 357
  2. 2017Road Extraction by Deep Residual U-Netcited by 333
  3. 2015Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networkscited by 295
  4. 2015Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understandingcited by 218
  5. 2019Confidence Calibration and Predictive Uncertainty Estimation for Deep Medical Image Segmentationcited by 163
  6. 2020Hyperparameter Ensembles for Robustness and Uncertainty Quantificationcited by 150
  7. 2018Exploring Uncertainty Measures in Deep Networks for Multiple Sclerosis Lesion Detection and Segmentationcited by 146
  8. 2019Standardized Assessment of Automatic Segmentation of White Matter Hyperintensities and Results of the WMH Segmentation Challengecited by 115
  9. 2021The Devil is in the Margin: Margin-based Label Smoothing for Network Calibrationcited by 91
  10. 2021Is segmentation uncertainty useful?cited by 37
  11. 2021Spatially Varying Label Smoothing: Capturing Uncertainty from Expert Annotationscited by 31
  12. 2020Deep Interpretable Classification and Weakly-Supervised Segmentation of Histology Images via Max-Min Uncertaintycited by 26
  13. 2020Diverse Ensembles Improve Calibrationcited by 23
  14. 2018Towards increased trustworthiness of deep learning segmentation methods on cardiac MRIcited by 16
  15. 2021Orthogonal Ensemble Networks for Biomedical Image Segmentationcited by 16
  16. 2020A Global Benchmark of Algorithms for Segmenting Late Gadolinium-Enhanced Cardiac Magnetic Resonance Imagingcited by 8
  17. 2020Improving Calibration and Out-of-Distribution Detection in Medical Image Segmentation with Convolutional Neural Networkscited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 2; 2024: 5; 2025: 3; 2026: 1.

13 papers.

Sort:

  1. 2022Trustworthy clinical AI solutions: a unified review of uncertainty quantification in deep learning models for medical image analysiscited by 63
  2. 2024Robust Calibration of Large Vision-Language Adapterscited by 28
  3. 2024Tyche: Stochastic In-Context Learning for Medical Image Segmentationcited by 20
  4. 2025Uncertainty Quantification for Machine Learning in Healthcare: A Surveycited by 14
  5. 2022Safety and Performance, Why not Both? Bi-Objective Optimized Model Compression toward AI Software Deploymentcited by 8
  6. 2024A Review of Bayesian Uncertainty Quantification in Deep Probabilistic Image Segmentationcited by 6
  7. 2023Understanding Calibration of Deep Neural Networks for Medical Image Classificationcited by 5
  8. 2023Boundary-weighted logit consistency improves calibration of segmentation networkscited by 4
  9. 2024Class and Region-Adaptive Constraints for Network Calibrationcited by 2
  10. 2024Do not trust what you trust: Miscalibration in Semi-supervised Learningcited by 2
  11. 2026Quantile Adaptive Temperature Scaling for Confidence Calibrationcited by 2
  12. 2025UAC: Uncertainty-Aware Calibration of Neural Networks for Gesture Detectioncited by 1
1 more
  1. 2025Tumor-anchored deep feature random forests for out-of-distribution detection in lung cancer segmentationcited by 1