Learning Invariant Feature Representation to Improve Generalization across Chest X-ray Datasets
This work addresses generalization issues in medical imaging for radiologists and healthcare systems, but it is incremental as it builds on existing adversarial methods for domain adaptation.
The authors tackled the problem of deep learning models performing poorly on chest X-ray datasets from different sources by forcing networks to learn source-invariant representations using adversarial training, which improved classification accuracy for pneumonia across multi-source datasets.
Chest radiography is the most common medical image examination for screening and diagnosis in hospitals. Automatic interpretation of chest X-rays at the level of an entry-level radiologist can greatly benefit work prioritization and assist in analyzing a larger population. Subsequently, several datasets and deep learning-based solutions have been proposed to identify diseases based on chest X-ray images. However, these methods are shown to be vulnerable to shift in the source of data: a deep learning model performing well when tested on the same dataset as training data, starts to perform poorly when it is tested on a dataset from a different source. In this work, we address this challenge of generalization to a new source by forcing the network to learn a source-invariant representation. By employing an adversarial training strategy, we show that a network can be forced to learn a source-invariant representation. Through pneumonia-classification experiments on multi-source chest X-ray datasets, we show that this algorithm helps in improving classification accuracy on a new source of X-ray dataset.