Robust Medical Image Classification from Noisy Labeled Data with Global and Local Representation Guided Co-training

TL;DR

This paper introduces a robust training framework for medical image classification that effectively handles noisy labels by combining global and local representation learning with a collaborative training strategy, improving accuracy on noisy datasets.

Contribution

The paper proposes a novel co-training approach with global and local representations to improve robustness against noisy labels in medical image classification tasks.

Findings

Outperforms existing noisy label learning methods on four medical datasets.

Effectively filters clean and noisy samples using a self-ensemble model.

Demonstrates robustness across different types of label noise.

Abstract

Deep neural networks have achieved remarkable success in a wide variety of natural image and medical image computing tasks. However, these achievements indispensably rely on accurately annotated training data. If encountering some noisy-labeled images, the network training procedure would suffer from difficulties, leading to a sub-optimal classifier. This problem is even more severe in the medical image analysis field, as the annotation quality of medical images heavily relies on the expertise and experience of annotators. In this paper, we propose a novel collaborative training paradigm with global and local representation learning for robust medical image classification from noisy-labeled data to combat the lack of high quality annotated medical data. Specifically, we employ the self-ensemble model with a noisy label filter to efficiently select the clean and noisy samples. Then, the clean samples are trained by a collaborative training strategy to eliminate the disturbance from imperfect labeled samples. Notably, we further design a novel global and local representation learning scheme to implicitly regularize the networks to utilize noisy samples in a self-supervised manner. We evaluated our proposed robust learning strategy on four public medical image classification datasets with three types of label noise,ie,random noise, computer-generated label noise, and inter-observer variability noise. Our method outperforms other learning from noisy label methods and we also conducted extensive experiments to analyze each component of our method.