Understanding Calibration of Deep Neural Networks for Medical Image Classification

TL;DR

This paper empirically investigates how different training regimes affect the calibration of deep neural networks in medical image classification, highlighting the benefits of self-supervised learning for better calibration and comparable accuracy.

Contribution

It provides a comprehensive empirical analysis of model calibration in medical imaging, comparing supervised and self-supervised training methods across various datasets and architectures.

Findings

Self-supervised pretrained models show better calibration than fully supervised models.

Calibration correlates with weight distributions and learned representation similarity.

Self-supervised learning improves calibration without sacrificing accuracy.

Abstract

In the field of medical image analysis, achieving high accuracy is not enough; ensuring well-calibrated predictions is also crucial. Confidence scores of a deep neural network play a pivotal role in explainability by providing insights into the model's certainty, identifying cases that require attention, and establishing trust in its predictions. Consequently, the significance of a well-calibrated model becomes paramount in the medical imaging domain, where accurate and reliable predictions are of utmost importance. While there has been a significant effort towards training modern deep neural networks to achieve high accuracy on medical imaging tasks, model calibration and factors that affect it remain under-explored. To address this, we conducted a comprehensive empirical study that explores model performance and calibration under different training regimes. We considered fully supervised training, which is the prevailing approach in the community, as well as rotation-based self-supervised method with and without transfer learning, across various datasets and architecture sizes. Multiple calibration metrics were employed to gain a holistic understanding of model calibration. Our study reveals that factors such as weight distributions and the similarity of learned representations correlate with the calibration trends observed in the models. Notably, models trained using rotation-based self-supervised pretrained regime exhibit significantly better calibration while achieving comparable or even superior performance compared to fully supervised models across different medical imaging datasets. These findings shed light on the importance of model calibration in medical image analysis and highlight the benefits of incorporating self-supervised learning approach to improve both performance and calibration.