Image Embedding and Model Ensembling for Automated Chest X-Ray Interpretation

TL;DR

This paper explores combining CNN-derived image embeddings with model ensembling techniques to improve automated interpretation of chest X-rays, demonstrating promising results for medical imaging analysis.

Contribution

It introduces a methodology of using CNN embeddings and ensembling strategies for CXR diagnosis, highlighting their effectiveness and viability.

Findings

Encouraging performance of combined CNN embeddings and ensembling methods.

Validation of the approach on the CheXpert dataset.

Potential for further research in medical image analysis.

Abstract

Chest X-ray (CXR) is perhaps the most frequently-performed radiological investigation globally. In this work, we present and study several machine learning approaches to develop automated CXR diagnostic models. In particular, we trained several Convolutional Neural Networks (CNN) on the CheXpert dataset, a large collection of more than 200k CXR labeled images. Then, we used the trained CNNs to compute embeddings of the CXR images, in order to train two sets of tree-based classifiers from them. Finally, we described and compared three ensembling strategies to combine together the classifiers trained. Rather than expecting some performance-wise benefits, our goal in this work is showing that the above two methodologies, i.e., the extraction of image embeddings and models ensembling, can be effective and viable to solve tasks that require medical imaging understanding. Our results in that perspective are encouraging and worthy of further investigation.