GraphX$^{NET}-$ Chest X-Ray Classification Under Extreme Minimal Supervision
This addresses the critical issue of data scarcity in medical imaging classification, which is important for clinical applications, though it is incremental in applying graph-based methods to a new domain.
The paper tackles the problem of classifying chest X-rays with extremely limited labeled data by introducing a novel semi-supervised graph-based framework, achieving highly competitive results on the ChestX-ray14 dataset while drastically reducing annotation needs.
The task of classifying X-ray data is a problem of both theoretical and clinical interest. Whilst supervised deep learning methods rely upon huge amounts of labelled data, the critical problem of achieving a good classification accuracy when an extremely small amount of labelled data is available has yet to be tackled. In this work, we introduce a novel semi-supervised framework for X-ray classification which is based on a graph-based optimisation model. To the best of our knowledge, this is the first method that exploits graph-based semi-supervised learning for X-ray data classification. Furthermore, we introduce a new multi-class classification functional with carefully selected class priors which allows for a smooth solution that strengthens the synergy between the limited number of labels and the huge amount of unlabelled data. We demonstrate, through a set of numerical and visual experiments, that our method produces highly competitive results on the ChestX-ray14 data set whilst drastically reducing the need for annotated data.