JMIR Publications

ABSTRACT

Background:

Deep neural networks are showing impressive results on different medical image classification tasks. However, for real-world applications there is a need to estimate the network’s uncertainty together with its prediction.

Objective:

With this review we investigate in what form uncertainty estimation has been applied to the task of medical image classification. We also investigate which metrics are used to describe the effectiveness of the applied uncertainty estimation method.

Methods:

Google Scholar, PubMed, IEEE Xplore and ScienceDirect were screened for peer-reviewed studies published between 2016 and 2021 that deal with uncertainty estimation in medical image classification. The search terms uncertainty, uncertainty estimation, network calibration and out-of-distribution detection were used in combination with the terms medical images, medical image analysis and medical image classification.

Results:

Through the systematic review process, 22 papers were chosen for a detailed analysis. This paper provides a table for a systematic comparison of the included works with respect to the applied method for estimating the uncertainty.

Conclusions:

The applied methods for estimating uncertainties are diverse, but the sampling-based methods Monte-Carlo Dropout and Deep Ensembles are used most frequently. We conclude that future works can investigate the benefits of uncertainty estimation in collaborative settings of AI systems and human experts.