Hard Sample Aware Noise Robust Learning for Histopathology Image Classification

TL;DR

This paper presents a novel noise-robust learning method for histopathology image classification that effectively distinguishes hard samples from noisy ones, improving accuracy without requiring a clean dataset.

Contribution

Introduces a hard sample aware noise robust learning framework with an EHN detection model and a self-training architecture for improved histopathology image classification.

Findings

Outperforms state-of-the-art methods on synthetic and real-world noisy datasets.

Effectively reduces noise impact without needing a clean subset.

Enhances model robustness by focusing on hard samples.

Abstract

Deep learning-based histopathology image classification is a key technique to help physicians in improving the accuracy and promptness of cancer diagnosis. However, the noisy labels are often inevitable in the complex manual annotation process, and thus mislead the training of the classification model. In this work, we introduce a novel hard sample aware noise robust learning method for histopathology image classification. To distinguish the informative hard samples from the harmful noisy ones, we build an easy/hard/noisy (EHN) detection model by using the sample training history. Then we integrate the EHN into a self-training architecture to lower the noise rate through gradually label correction. With the obtained almost clean dataset, we further propose a noise suppressing and hard enhancing (NSHE) scheme to train the noise robust model. Compared with the previous works, our method can save more clean samples and can be directly applied to the real-world noisy dataset scenario without using a clean subset. Experimental results demonstrate that the proposed scheme outperforms the current state-of-the-art methods in both the synthetic and real-world noisy datasets. The source code and data are available at https://github.com/bupt-ai-cz/HSA-NRL/.