Improving Uncertainty-Error Correspondence in Deep Bayesian Medical Image Segmentation
Not on the map. Why?
Abstract (arXiv)
Increased usage of automated tools like deep learning in medical image segmentation has alleviated the bottleneck of manual contouring. This has shifted manual labour to quality assessment (QA) of automated contours which involves detecting errors and correcting them. A potential solution to semi-automated QA is to use deep Bayesian uncertainty to recommend potentially erroneous regions, thus reducing time spent on error detection. Previous work has investigated the correspondence between uncertainty and error, however, no work has been done on improving the "utility" of Bayesian uncertainty maps such that it is only present in inaccurate regions and not in the accurate ones. Our work trains the FlipOut model with the Accuracy-vs-Uncertainty (AvU) loss which promotes uncertainty to be present only in inaccurate regions. We apply this method on datasets of two radiotherapy body sites, c.f. head-and-neck CT and prostate MR scans. Uncertainty heatmaps (i.e. predictive entropy) are evaluated against voxel inaccuracies using Receiver Operating Characteristic (ROC) and Precision-Recall (PR) curves. Numerical results show that when compared to the Bayesian baseline the proposed method successfully suppresses uncertainty for accurate voxels, with similar presence of uncertainty for inaccurate voxels. Code to reproduce experiments is available at https://github.com/prerakmody/bayesuncertainty-error-correspondence
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 42 of its 71 references that are in the map. First posted on arXiv 5 Sep 2024.
Builds on
42 of 71 references.
References · 42
- 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
- 2017On Calibration of Modern Neural Networkscited by 4,860
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
- 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
- 2019When Does Label Smoothing Help?cited by 985
- 2021The Medical Segmentation Decathloncited by 620
- 2017Regularizing Neural Networks by Penalizing Confident Output Distributionscited by 461
- 2019Measuring Calibration in Deep Learningcited by 443
- 2020Calibrating Deep Neural Networks using Focal Losscited by 353
- 2019Verified Uncertainty Calibrationcited by 307
- 2019On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networkscited by 304
- 2018Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networkscited by 278
30 more
- 2020Mix-n-Match: Ensemble and Compositional Methods for Uncertainty Calibration in Deep Learningcited by 190
- 2019Confidence Calibration and Predictive Uncertainty Estimation for Deep Medical Image Segmentationcited by 162
- 2018Exploring Uncertainty Measures in Deep Networks for Multiple Sclerosis Lesion Detection and Segmentationcited by 146
- 2018Evaluating Bayesian Deep Learning Methods for Semantic Segmentationcited by 143
- 2018Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batchescited by 133
- 2020Improving model calibration with accuracy versus uncertainty optimizationcited by 123
- 2020Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertaintycited by 100
- 2020Local Temperature Scaling for Probability Calibrationcited by 95
- 2021The Devil is in the Margin: Margin-based Label Smoothing for Network Calibrationcited by 91
- 2021Unified Focal loss: Generalising Dice and cross entropy-based losses to handle class imbalanced medical image segmentationcited by 88
- 2018Combo Loss: Handling Input and Output Imbalance in Multi-Organ Segmentationcited by 76
- 2022Better Uncertainty Calibration via Proper Scores for Classification and Beyondcited by 65
- 2019Supervised Uncertainty Quantification for Segmentation with Multiple Annotationscited by 42
- 2019Well-calibrated Model Uncertainty with Temperature Scaling for Dropout Variational Inferencecited by 35
- 2021Spatially Varying Label Smoothing: Capturing Uncertainty from Expert Annotationscited by 31
- 2020Estimating Uncertainty in Neural Networks for Cardiac MRI Segmentation: A Benchmark Studycited by 19
- 2020Uncertainty-Guided Efficient Interactive Refinement of Fetal Brain Segmentation from Stacks of MRI Slicescited by 16
- 2022Class Adaptive Network Calibrationcited by 13
- 2023DeepEdit: Deep Editable Learning for Interactive Segmentation of 3D Medical Imagescited by 13
- 2023Trust your neighbours: Penalty-based constraints for model calibrationcited by 12
- 2020Automatic segmentation with detection of local segmentation failures in cardiac MRIcited by 10
- 2021A Quantitative Comparison of Epistemic Uncertainty Maps Applied to Multi-Class Segmentationcited by 9
- 2018Uncertainty in multitask learning: joint representations for probabilistic MR-only radiotherapy planningcited by 8
- 2021A Novel Hybrid Convolutional Neural Network for Accurate Organ Segmentation in 3D Head and Neck CT Imagescited by 7
- 2022On Calibrated Model Uncertainty in Deep Learningcited by 7
- 2021Improving the Reliability of Semantic Segmentation of Medical Images by Uncertainty Modeling with Bayesian Deep Networks and Curriculum Learningcited by 6
- 2022Improved post-hoc probability calibration for out-of-domain MRI segmentationcited by 5
- 2022Influence of uncertainty estimation techniques on false-positive reduction in liver lesion detectioncited by 3
- 2020Anisotropic 3D Multi-Stream CNN for Accurate Prostate Segmentation from Multi-Planar MRIcited by 2
- 2021Comparing Bayesian Models for Organ Contouring in Head and Neck Radiotherapycited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.