Leveraging Uncertainty Estimates for Predicting Segmentation Quality

Abstract

The use of deep learning for medical imaging has seen tremendous growth in the research community. One reason for the slow uptake of these systems in the clinical setting is that they are complex, opaque and tend to fail silently. Outside of the medical imaging domain, the machine learning community has recently proposed several techniques for quantifying model uncertainty (i.e.~a model knowing when it has failed). This is important in practical settings, as we can refer such cases to manual inspection or correction by humans. In this paper, we aim to bring these recent results on estimating uncertainty to bear on two important outputs in deep learning-based segmentation. The first is producing spatial uncertainty maps, from which a clinician can observe where and why a system thinks it is failing. The second is quantifying an image-level prediction of failure, which is useful for isolating specific cases and removing them from automated pipelines. We also show that reasoning about spatial uncertainty, the first output, is a useful intermediate representation for generating segmentation quality predictions, the second output. We propose a two-stage architecture for producing these measures of uncertainty, which can accommodate any deep learning-based medical segmentation pipeline.

References in corpus (9)

• A Survey on Deep Learning in Medical Image Analysis
• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
• A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
• Detecting Cancer Metastases on Gigapixel Pathology Images
• Semantic Segmentation using Adversarial Networks
• Learning Confidence for Out-of-Distribution Detection in Neural Networks
• Deep Generative Adversarial Networks for Compressed Sensing Automates MRI
• Adversarial Networks for the Detection of Aggressive Prostate Cancer
• Adversarial training and dilated convolutions for brain MRI segmentation

Cited by in corpus (21)

• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• Deep neural network models for computational histopathology: A survey
• Estimating Uncertainty in Neural Networks for Cardiac MRI Segmentation: A Benchmark Study
• Did You Miss the Sign? A False Negative Alarm System for Traffic Sign Detectors
• Time-Dynamic Estimates of the Reliability of Deep Semantic Segmentation Networks
• EigenRank by Committee: A Data Subset Selection and Failure Prediction paradigm for Robust Deep Learning based Medical Image Segmentation
• Hyperparameter-Free Out-of-Distribution Detection Using Softmax of Scaled Cosine Similarity
• Robust Mutual Learning for Semi-supervised Semantic Segmentation
• Reducing Uncertainty in Undersampled MRI Reconstruction with Active Acquisition
• Improving Video Instance Segmentation by Light-weight Temporal Uncertainty Estimates
• Influence of uncertainty estimation techniques on false-positive reduction in liver lesion detection
• Revisiting the Evaluation of Uncertainty Estimation and Its Application to Explore Model Complexity-Uncertainty Trade-Off
• MetaFusion: Controlled False-Negative Reduction of Minority Classes in Semantic Segmentation
• A Decoupled Uncertainty Model for MRI Segmentation Quality Estimation
• Interactive Medical Image Segmentation with Self-Adaptive Confidence Calibration
• False Negative Reduction in Video Instance Segmentation using Uncertainty Estimates
• Evaluating subgroup disparity using epistemic uncertainty in mammography
• Enhanced Isotropy Maximization Loss: Seamless and High-Performance Out-of-Distribution Detection Simply Replacing the SoftMax Loss
• Hierarchical Deep Network with Uncertainty-aware Semi-supervised Learning for Vessel Segmentation
• Improving the Reliability of Semantic Segmentation of Medical Images by Uncertainty Modeling with Bayesian Deep Networks and Curriculum Learning
• Measurement of Hybrid Rocket Solid Fuel Regression Rate for a Slab Burner using Deep Learning