Improving Uncertainty-Error Correspondence in Deep Bayesian Medical Image Segmentation

Abstract

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

Accepted for publication at the Journal of Machine Learning for Biomedical Imaging (MELBA) https://melba-journal.org/2024:018

References in corpus (19)

• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• On Calibration of Modern Neural Networks
• The Medical Segmentation Decathlon
• Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift
• Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks
• Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches
• Measuring Calibration in Deep Learning
• Evaluating Bayesian Deep Learning Methods for Semantic Segmentation
• Verified Uncertainty Calibration
• Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty
• Anisotropic 3D Multi-Stream CNN for Accurate Prostate Segmentation from Multi-Planar MRI
• Mix-n-Match: Ensemble and Compositional Methods for Uncertainty Calibration in Deep Learning
• Uncertainty-Guided Efficient Interactive Refinement of Fetal Brain Segmentation from Stacks of MRI Slices
• DeepEdit: Deep Editable Learning for Interactive Segmentation of 3D Medical Images
• Well-calibrated Model Uncertainty with Temperature Scaling for Dropout Variational Inference
• A Quantitative Comparison of Epistemic Uncertainty Maps Applied to Multi-Class Segmentation
• Better Uncertainty Calibration via Proper Scores for Classification and Beyond
• Influence of uncertainty estimation techniques on false-positive reduction in liver lesion detection
• On Calibrated Model Uncertainty in Deep Learning