Generalisation effects of predictive uncertainty estimation in deep learning for digital pathology. (arXiv:2112.09693v2 [cs.LG] UPDATED)

Deep learning (DL) has shown great potential in digital pathology
applications. The robustness of a diagnostic DL-based solution is essential for
safe clinical deployment. In this work we evaluate if adding uncertainty
estimates for DL predictions in digital pathology could result in increased
value for the clinical applications, by boosting the general predictive
performance or by detecting mispredictions. We compare the effectiveness of
model-integrated methods (MC dropout and Deep ensembles) with a model-agnostic
approach (Test time augmentation, TTA). Moreover, four …

arxiv deep learning digital effects learning predictive uncertainty