Uncertainty-driven Sanity Check: Application to Postoperative Brain Tumor Cavity Segmentation

Abstract

Uncertainty estimates of modern neuronal networks provide additional information next to the computed predictions and are thus expected to improve the understanding of the underlying model. Reliable uncertainties are particularly interesting for safety-critical computer-assisted applications in medicine, e.g., neurosurgical interventions and radiotherapy planning. We propose an uncertainty-driven sanity check for the identification of segmentation results that need particular expert review. Our method uses a fully-convolutional neural network and computes uncertainty estimates by the principle of Monte Carlo dropout. We evaluate the performance of the proposed method on a clinical dataset with 30 postoperative brain tumor images. The method can segment the highly inhomogeneous resection cavities accurately (Dice coefficients 0.792 $\pm$ 0.154). Furthermore, the proposed sanity check is able to detect the worst segmentation and three out of the four outliers. The results highlight the potential of using the additional information from the model's parameter uncertainty to validate the segmentation performance of a deep learning model.

arXiv commentAppears in Medical Imaging with Deep Learning (MIDL), 2018

References in corpus (5)

• Adam: A Method for Stochastic Optimization
• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
• Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference
• Implicit Weight Uncertainty in Neural Networks
• Bayesian Image Quality Transfer with CNNs: Exploring Uncertainty in dMRI Super-Resolution

Cited by in corpus (7)

• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• pymia: A Python package for data handling and evaluation in deep learning-based medical image analysis
• Supervised Uncertainty Quantification for Segmentation with Multiple Annotations
• Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation
• Few-shot brain segmentation from weakly labeled data with deep heteroscedastic multi-task networks
• An Alarm System For Segmentation Algorithm Based On Shape Model
• Hardware-aware Real-time Myocardial Segmentation Quality Control in Contrast Echocardiography