Flow-Mixup: Classifying Multi-labeled Medical Images with Corrupted Labels

TL;DR

Flow-Mixup is a novel regularization technique designed to improve multi-labeled medical image classification accuracy in the presence of corrupted labels, enabling more reliable automatic annotation.

Contribution

This paper introduces Flow-Mixup, a new regularization method that decouples features to handle corrupted labels in multi-labeled medical image classification.

Findings

Flow-Mixup outperforms existing regularization methods in stability and effectiveness.

It effectively handles corrupted labels in ECG and chest X-ray datasets.

Flow-Mixup enables more accurate automatic annotation in medical imaging.

Abstract

In clinical practice, medical image interpretation often involves multi-labeled classification, since the affected parts of a patient tend to present multiple symptoms or comorbidities. Recently, deep learning based frameworks have attained expert-level performance on medical image interpretation, which can be attributed partially to large amounts of accurate annotations. However, manually annotating massive amounts of medical images is impractical, while automatic annotation is fast but imprecise (possibly introducing corrupted labels). In this work, we propose a new regularization approach, called Flow-Mixup, for multi-labeled medical image classification with corrupted labels. Flow-Mixup guides the models to capture robust features for each abnormality, thus helping handle corrupted labels effectively and making it possible to apply automatic annotation. Specifically, Flow-Mixup decouples the extracted features by adding constraints to the hidden states of the models. Also, Flow-Mixup is more stable and effective comparing to other known regularization methods, as shown by theoretical and empirical analyses. Experiments on two electrocardiogram datasets and a chest X-ray dataset containing corrupted labels verify that Flow-Mixup is effective and insensitive to corrupted labels.