Learn to Estimate Labels Uncertainty for Quality Assurance
This work addresses uncertainty modeling for quality assurance in medical applications, but it appears incremental as it builds on existing methods like Bayesian inference and Monte-Carlo dropout.
The paper tackles the problem of deep learning's lack of robustness in medical applications by introducing labels uncertainty to address inter-observer variability, showing that modeling this alongside epistemic uncertainty is highly beneficial for quality control and referral systems.
Deep Learning sets the state-of-the-art in many challenging tasks showing outstanding performance in a broad range of applications. Despite its success, it still lacks robustness hindering its adoption in medical applications. Modeling uncertainty, through Bayesian Inference and Monte-Carlo dropout, has been successfully introduced for better understanding the underlying deep learning models. Yet, another important source of uncertainty, coming from the inter-observer variability, has not been thoroughly addressed in the literature. In this paper, we introduce labels uncertainty which better suits medical applications and show that modeling such uncertainty together with epistemic uncertainty is of high interest for quality control and referral systems.