Recalibration of Aleatoric and Epistemic Regression Uncertainty in Medical Imaging

verfasst von

Max-Heinrich Laves, Sontje Ihler, Jacob F. Fast, Lüder A. Kahrs, Tobias Ortmaier

Abstract

The consideration of predictive uncertainty in medical imaging with deep learning is of utmost importance. We apply estimation of both aleatoric and epistemic uncertainty by variational Bayesian inference with Monte Carlo dropout to regression tasks and show that predictive uncertainty is systematically underestimated. We apply \( \sigma \) scaling with a single scalar value; a simple, yet effective calibration method for both types of uncertainty. The performance of our approach is evaluated on a variety of common medical regression data sets using different state-of-the-art convolutional network architectures. In our experiments, \( \sigma \) scaling is able to reliably recalibrate predictive uncertainty. It is easy to implement and maintains the accuracy. Well-calibrated uncertainty in regression allows robust rejection of unreliable predictions or detection of out-of-distribution samples. Our source code is available at github.com/mlaves/well-calibrated-regression-uncertainty

Organisationseinheit(en)

Institut für Mechatronische Systeme

Externe Organisation(en)

Technische Universität Hamburg (TUHH)
Medizinische Hochschule Hannover (MHH)
University of Toronto

Typ

Artikel

Journal

The Journal of Machine Learning for Biomedical Imaging (MELBA)

Band

MIDL 2020

Seiten

1-26

Anzahl der Seiten

26

ISSN

2766-905X

Publikationsdatum

28.04.2021

Publikationsstatus

Veröffentlicht

Peer-reviewed

Ja

Elektronische Version(en)

https://arxiv.org/abs/2104.12376 (Zugang: Offen)
https://www.melba-journal.org/article/22528 (Zugang: Offen)