Flow-Mixup: Classifying Multi-labeled Medical Images with Corrupted Labels
This work is significant for medical image analysis, particularly for researchers and practitioners dealing with large, automatically annotated datasets where label corruption is a concern, by providing a method to improve model robustness. It is an incremental improvement to existing regularization methods.
The paper addresses the challenge of multi-labeled medical image classification when labels are corrupted, a common issue with automatic annotation. They propose Flow-Mixup, a regularization approach that guides models to capture robust features for each abnormality, enabling effective handling of corrupted labels. The method is validated on two electrocardiogram datasets and one chest X-ray dataset, demonstrating its effectiveness and insensitivity to label corruption.
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.