Academic Journal
Role of calibration in uncertainty-based referral for deep learning.
| Title: | Role of calibration in uncertainty-based referral for deep learning. |
|---|---|
| Authors: | Zhang, Ruotao, Gatsonis, Constantine, Steingrimsson, Jon Arni |
| Source: | Statistical Methods in Medical Research; May2023, Vol. 32 Issue 5, p927-943, 17p |
| Abstract: | The uncertainty in predictions from deep neural network analysis of medical imaging is challenging to assess but potentially important to include in subsequent decision-making. Using data from diabetic retinopathy detection, we present an empirical evaluation of the role of model calibration in uncertainty-based referral, an approach that prioritizes referral of observations based on the magnitude of a measure of uncertainty. We consider several configurations of network architecture, methods for uncertainty estimation, and training data size. We identify a strong relationship between the effectiveness of uncertainty-based referral and having a well-calibrated model. This is especially relevant as complex deep neural networks tend to have high calibration errors. Finally, we show that post-calibration of the neural network helps uncertainty-based referral with identifying hard-to-classify observations. [ABSTRACT FROM AUTHOR] |
| Subject Terms: | DEEP learning, ARTIFICIAL neural networks, CALIBRATION, DIABETIC retinopathy, IMAGE analysis |
| Copyright of Statistical Methods in Medical Research is the property of Sage Publications Inc. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| ISSN: | 09622802 |
| DOI: | 10.1177/09622802231158811 |
| Database: | Complementary Index |