Addressing Deep Learning Model Calibration Using Evidential Neural Networks and Uncertainty-Aware Training

• Published in: 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI) Vol. 34; pp. 1 - 5
• Main Authors: Dawood, Tareen, Chan, Emily, Razavi, Reza, King, Andrew P., Puyol-Anton, Esther
• Format: Conference Proceeding Journal Article
• Language: English
• Published: United States IEEE 18.04.2023
• Subjects: Biological system modeling; Calibration; Deep learning; Evidential Neural Networks; Magnetic resonance; Medical Imaging; Neural networks; Task analysis; Training; Evidential Neural Networks; Calibration; Medical Imaging
• ISSN: 1945-7928; 1945-8452
• DOI: 10.1109/ISBI53787.2023.10230515

In terms of accuracy, deep learning (DL) models have had considerable success in classification problems for medical imaging applications. However, it is well-known that the outputs of such models, which typically utilise the SoftMax function in the final classification layer can be over-confident, i.e. they are poorly calibrated. Two competing solutions to this problem have been proposed: uncertainty-aware training and evidential neural networks (ENNs). In this paper we perform an investigation into the improvements to model calibration that can be achieved by each of these approaches individually, and their combination. We perform experiments on two classification tasks: a simpler MNIST digit classification task and a more complex and realistic medical imaging artefact detection task using Phase Contrast Cardiac Magnetic Resonance images. The experimental results demonstrate that model calibration can suffer when the task becomes challenging enough to require a higher capacity model. However, in our complex artefact detection task we saw an improvement in calibration for both a low and higher capacity model when implementing both the ENN and uncertainty-aware training together, indicating that this approach can offer a promising way to improve calibration in such settings. The findings highlight the potential use of these approaches to improve model calibration in a complex application, which would in turn improve clinician trust in DL models.