Estimating Uncertainty in Neural Networks for Cardiac MRI Segmentation: A Benchmark Study

Convolutional neural networks (CNNs) have demonstrated promise in automated cardiac magnetic resonance imaging segmentation. However, when using CNNs in a large real world dataset, it is important to quantify segmentation uncertainty in order to know which segmentations could be problematic. In this work, we performed a systematic study of Bayesian and non-Bayesian methods for estimating uncertainty in segmentation neural networks. We evaluated Bayes by Backprop (BBB), Monte Carlo (MC) Dropout, and Deep Ensembles in terms of segmentation accuracy, probability calibration, uncertainty on out-of-distribution images, and segmentation quality control. We tested these algorithms on datasets with various distortions and observed that Deep Ensembles outperformed the other methods except for images with heavy noise distortions. For segmentation quality control, we showed that segmentation uncertainty is correlated with segmentation accuracy. With the incorporation of uncertainty estimates, we were able to reduce the percentage of poor segmentation to 5% by flagging 31% to 48% of the most uncertain images for manual review, substantially lower than random review of the results without using neural network uncertainty.