Improving the Reliability of Semantic Segmentation of Medical Images by Uncertainty Modeling with Bayesian Deep Networks and Curriculum Learning

In this paper we propose a novel method which leverages the uncertainty measures provided by Bayesian deep networks through curriculum learning so that the uncertainty estimates are fed back to the system to resample the training data more densely in areas where uncertainty is high. We show in the concrete setting of a semantic segmentation task (iPS cell colony segmentation) that the proposed system is able to increase significantly the reliability of the model.

Sora Iwamoto, Bisser Raytchev, Toru Tamaki, Kazufumi Kaneda · 2021