Learning Invariant Feature Representation to Improve Generalization across Chest X-ray Datasets

TL;DR

This paper proposes an adversarial training method to learn source-invariant features in chest X-ray classification, significantly enhancing model generalization across datasets from different sources.

Contribution

It introduces a novel adversarial training approach to improve the generalization of deep learning models for chest X-ray analysis across diverse datasets.

Findings

Improved classification accuracy on new X-ray datasets

Demonstrated robustness of source-invariant features

Enhanced generalization compared to standard models

Abstract

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.