Improved Trainable Calibration Method for Neural Networks on Medical Imaging Classification

Gongbo Liang, Yu Zhang, Xiaoqin Wang, Nathan Jacobs

Research output: Working paperPreprint

79 Downloads (Pure)

Abstract

Recent works have shown that deep neural networks can achieve super-human performance in a wide range of image classification tasks in the medical imaging domain. However, these works have primarily focused on classification accuracy, ignoring the important role of uncertainty quantification. Empirically, neural networks are often miscalibrated and overconfident in their predictions. This miscalibration could be problematic in any automatic decision-making system, but we focus on the medical field in which neural network miscalibration has the potential to lead to significant treatment errors. We propose a novel calibration approach that maintains the overall classification accuracy while significantly improving model calibration. The proposed approach is based on expected calibration error, which is a common metric for quantifying miscalibration. Our approach can be easily integrated into any classification task as an auxiliary loss term, thus not requiring an explicit training round for calibration. We show that our approach reduces calibration error significantly across various architectures and datasets.
Original languageUndefined/Unknown
StatePublished - Sep 9 2020

Bibliographical note

Accepted to the 31th British Machine Vision Conference (BMVC 2020)

Keywords

  • cs.CV
  • cs.LG
  • eess.IV

Fingerprint

Dive into the research topics of 'Improved Trainable Calibration Method for Neural Networks on Medical Imaging Classification'. Together they form a unique fingerprint.

Cite this