Deep Learning for Chest X-ray Analysis: A Survey

TL;DR

This survey reviews recent deep learning applications in chest X-ray analysis, covering various tasks, datasets, and commercial applications, and discusses current advancements and future research directions.

Contribution

It provides a comprehensive categorization and analysis of deep learning studies on chest X-rays, highlighting trends, datasets, and applications in the field.

Findings

Deep learning has significantly improved chest X-ray analysis performance.

Multiple large datasets have facilitated research and development.

Commercial applications are increasingly available and impactful.

Abstract

Recent advances in deep learning have led to a promising performance in many medical image analysis tasks. As the most commonly performed radiological exam, chest radiographs are a particularly important modality for which a variety of applications have been researched. The release of multiple, large, publicly available chest X-ray datasets in recent years has encouraged research interest and boosted the number of publications. In this paper, we review all studies using deep learning on chest radiographs, categorizing works by task: image-level prediction (classification and regression), segmentation, localization, image generation and domain adaptation. Commercially available applications are detailed, and a comprehensive discussion of the current state of the art and potential future directions are provided.