Towards safe deep learning: accurately quantifying biomarker uncertainty in neural network predictions
This addresses safety concerns in clinical applications by enabling reliable uncertainty estimates, though it is incremental as it builds on existing Bayesian methods.
The paper tackles the problem of uncertainty quantification in deep learning for medical image segmentation, proposing Bayesian neural networks to provide well-calibrated error-bars for tumor volume estimates, making systems safer for clinical use.
Automated medical image segmentation, specifically using deep learning, has shown outstanding performance in semantic segmentation tasks. However, these methods rarely quantify their uncertainty, which may lead to errors in downstream analysis. In this work we propose to use Bayesian neural networks to quantify uncertainty within the domain of semantic segmentation. We also propose a method to convert voxel-wise segmentation uncertainty into volumetric uncertainty, and calibrate the accuracy and reliability of confidence intervals of derived measurements. When applied to a tumour volume estimation application, we demonstrate that by using such modelling of uncertainty, deep learning systems can be made to report volume estimates with well-calibrated error-bars, making them safer for clinical use. We also show that the uncertainty estimates extrapolate to unseen data, and that the confidence intervals are robust in the presence of artificial noise. This could be used to provide a form of quality control and quality assurance, and may permit further adoption of deep learning tools in the clinic.