mlsanityData to 7 Oct 2026

Recalibration of Aleatoric and Epistemic Regression Uncertainty in Medical Imaging

arXiv 2104.12376 ↗First posted 26 Apr 2021eess.IV cs.CVcited by 18

Not on the map. Why?

Abstract (arXiv)

The consideration of predictive uncertainty in medical imaging with deep learning is of utmost importance. We apply estimation of both aleatoric and epistemic uncertainty by variational Bayesian inference with Monte Carlo dropout to regression tasks and show that predictive uncertainty is systematically underestimated. We apply σ scaling with a single scalar value; a simple, yet effective calibration method for both types of uncertainty. The performance of our approach is evaluated on a variety of common medical regression data sets using different state-of-the-art convolutional network architectures. In our experiments, σ scaling is able to reliably recalibrate predictive uncertainty. It is easy to implement and maintains the accuracy. Well-calibrated uncertainty in regression allows robust rejection of unreliable predictions or detection of out-of-distribution samples. Our source code is available at https://github.com/mlaves/well-calibrated-regression-uncertainty

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 20 of its 39 references that are in the map. First posted on arXiv 26 Apr 2021.

Builds on

20 of 39 references.

References · 20

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2016Densely Connected Convolutional Networkscited by 6,691
  4. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  5. 2017On Calibration of Modern Neural Networkscited by 4,860
  6. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  7. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  8. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  9. 2018Accurate Uncertainties for Deep Learning Using Calibrated Regressioncited by 417
  10. 2019Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfacescited by 186
  11. 2019Evaluating and Calibrating Uncertainty Prediction in Regression Taskscited by 85
  12. 2019Integrating Spatial Configuration into Heatmap Regression Based CNNs for Landmark Localizationcited by 77
8 more
  1. 2019Well-calibrated Model Uncertainty with Temperature Scaling for Dropout Variational Inferencecited by 35
  2. 2017Bayesian Image Quality Transfer with CNNs: Exploring Uncertainty in dMRI Super-Resolutioncited by 29
  3. 2018On the Applicability of Registration Uncertaintycited by 15
  4. 2018Stochastic Deep Compressive Sensing for the Reconstruction of Diffusion Tensor Cardiac MRIcited by 9
  5. 2018Calibrating Uncertainties in Object Localization Taskcited by 9
  6. 2018Uncertainty in multitask learning: joint representations for probabilistic MR-only radiotherapy planningcited by 8
  7. 2018Automatic kidney segmentation in ultrasound images using subsequent boundary distance regression and pixelwise classification networkscited by 5
  8. 2018A Deep Learning Approach for Pose Estimation from Volumetric OCT Datacited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 2; 2023: 7; 2024: 3; 2025: 2; 2026: 2.

18 papers.

Sort:

  1. 2023A review of uncertainty quantification in medical image analysis: probabilistic and non-probabilistic methodscited by 39
  2. 2023Uncertainty Estimation and Propagation in Accelerated MRI Reconstructioncited by 10
  3. 2025An Axiomatic Assessment of Entropy- and Variance-based Uncertainty Quantification in Regressioncited by 9
  4. 2023Uncertainty Quantification for Molecular Property Predictions with Graph Neural Architecture Searchcited by 8
  5. 2021Reliable Neural Networks for Regression Uncertainty Estimationcited by 6
  6. 2025CLEAR: Calibrated Learning for Epistemic and Aleatoric Riskcited by 6
  7. 2023Overcoming the Limitations of Localization Uncertainty: Efficient & Exact Non-Linear Post-Processing and Calibrationcited by 5
  8. 2024Bayesian optimized deep ensemble for uncertainty quantification of deep neural networks: a system safety case study on sodium fast reactor thermal stratification modelingcited by 5
  9. 2021Unsupervised Knowledge-Transfer for Learned Image Reconstructioncited by 4
  10. 2023How inter-rater variability relates to aleatoric and epistemic uncertainty: a case study with deep learning-based paraspinal muscle segmentationcited by 4
  11. 2022Posterior temperature optimized Bayesian models for inverse problems in medical imagingcited by 3
  12. 2023Towards Reliable Uncertainty Quantification via Deep Ensembles in Multi-output Regression Taskcited by 3
6 more
  1. 2024Cost-Sensitive Uncertainty-Based Failure Recognition for Object Detectioncited by 3
  2. 2024PULPo: Probabilistic Unsupervised Laplacian Pyramid Registrationcited by 3
  3. 2022Reduced Order Probabilistic Emulation for Physics-Based Thermosphere Modelscited by 1
  4. 2026Probabilistic Feature Imputation and Uncertainty-Aware Multimodal Federated Aggregationcited by 1
  5. 2023Estimation of River Water Surface Elevation Using UAV Photogrammetry and Machine Learningcited by 0
  6. 2026A Calibration Audit of Confidence in Feed-Forward 3D Reconstruction Modelscited by 0