Bayesian Statistics Guided Label Refurbishment Mechanism: Mitigating Label Noise in Medical Image Classification

TL;DR

This paper introduces a Bayesian statistics-guided label refurbishment mechanism (BLRM) that effectively mitigates label noise in medical image classification, enhancing model robustness and accuracy across various datasets and noise levels.

Contribution

The paper presents a novel BLRM method that uses Bayesian MAP and exponential weighting to selectively correct noisy labels during training, improving robustness in medical image classification.

Findings

BLRM effectively refurbishes noisy labels in synthetic and real-world datasets.

BLRM improves classification accuracy across different noise ratios and DNN architectures.

BLRM outperforms state-of-the-art anti-noise methods in experiments.

Abstract

Purpose: Deep neural networks (DNNs) have been widely applied in medical image classification, benefiting from its powerful mapping capability among medical images. However, these existing deep learning-based methods depend on an enormous amount of carefully labeled images. Meanwhile, noise is inevitably introduced in the labeling process, degrading the performance of models. Hence, it's significant to devise robust training strategies to mitigate label noise in the medical image classification tasks. Methods: In this work, we propose a novel Bayesian statistics guided label refurbishment mechanism (BLRM) for DNNs to prevent overfitting noisy images. BLRM utilizes maximum a posteriori probability (MAP) in the Bayesian statistics and the exponentially time-weighted technique to selectively correct the labels of noisy images. The training images are purified gradually with the training epochs when BLRM is activated, further improving classification performance. Results: Comprehensive experiments on both synthetic noisy images (public OCT & Messidor datasets) and real-world noisy images (ANIMAL-10N) demonstrate that BLRM refurbishes the noisy labels selectively, curbing the adverse effects of noisy data. Also, the anti-noise BLRM integrated with DNNs are effective at different noise ratio and are independent of backbone DNN architectures. In addition, BLRM is superior to state-of-the-art comparative methods of anti-noise. Conclusions: These investigations indicate that the proposed BLRM is well capable of mitigating label noise in medical image classification tasks.