Correcting data imbalance for semi-supervised COVID-19 detection using X-ray chest images

• Published in: Applied soft computing 2021-11, Vol.111, p.107692-107692, Article 107692
• Main Authors: Calderon-Ramirez, Saul, Yang, Shengxiang, Moemeni, Armaghan, Elizondo, David, Colreavy-Donnelly, Simon, Chavarría-Estrada, Luis Fernando, Molina-Cabello, Miguel A.
• Format: Article
• Language: English
• Subjects: Computer aided diagnosis; Coronavirus; COVID-19; Data imbalance; Semi-supervised learning
• ISSN: 1568-4946; 1872-9681
• DOI: 10.1016/j.asoc.2021.107692

A key factor in the fight against viral diseases such as the coronavirus (COVID-19) is the identification of virus carriers as early and quickly as possible, in a cheap and efficient manner. The application of deep learning for image classification of chest X-ray images of COVID-19 patients could become a useful pre-diagnostic detection methodology. However, deep learning architectures require large labelled datasets. This is often a limitation when the subject of research is relatively new as in the case of the virus outbreak, where dealing with small labelled datasets is a challenge. Moreover, in such context, the datasets are also highly imbalanced, with few observations from positive cases of the new disease. In this work we evaluate the performance of the semi-supervised deep learning architecture known as MixMatch with a very limited number of labelled observations and highly imbalanced labelled datasets. We demonstrate the critical impact of data imbalance to the model’s accuracy. Therefore, we propose a simple approach for correcting data imbalance, by re-weighting each observation in the loss function, giving a higher weight to the observations corresponding to the under-represented class. For unlabelled observations, we use the pseudo and augmented labels calculated by MixMatch to choose the appropriate weight. The proposed method improved classification accuracy by up to 18%, with respect to the non balanced MixMatch algorithm. We tested our proposed approach with several available datasets using 10, 15 and 20 labelled observations, for binary classification (COVID-19 positive and normal cases). For multi-class classification (COVID-19 positive, pneumonia and normal cases), we tested 30, 50, 70 and 90 labelled observations. Additionally, a new dataset is included among the tested datasets, composed of chest X-ray images of Costa Rican adult patients. •COVID-19 detection deep learning architectures typically need many labels.•Also the datasets at the beginning of a virus outbreak are highly imbalanced.•Semi supervised data can be used to increase model’s accuracy with few labels.•The effect of data imbalance on semi-supervised learning is under-explored.•A method to correct data imbalance for semi supervised learning is proposed.