2020/12/16 by Jintai Chen, Hongyun Yu, Ruiwei Feng +3 · 16 citations
Computer Science · Engineering · Medicine · #Abnormality #Annotation #Artificial intelligence #COVID-19 diagnosis using AI #Computer science #Computer vision #Deep learning #Image (mathematics) #Interpretation (philosophy) #Machine Learning in Healthcare #Machine learning #Medical imaging #Pattern recognition (psychology) #Radiomics and Machine Learning in Medical Imaging #Regularization (linguistics) #cs.CV #cs.LG #eess.IV
paper · pdf · doi:10.1109/bibm49941.2020.9313408
published as 2020 IEEE International Conference on Bioinformatics and Biomedicine
openalex publication_date 2020/12/16 · arxiv created 2021/02/09 · arxiv updated 2021/02/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
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 expertlevel 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, FlowMixup 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 FlowMixup is effective and insensitive to corrupted labels.