Pneumothorax and chest tube classification on chest x-rays for detection of missed pneumothorax

TL;DR

This paper introduces a multi-stage image classification pipeline that detects pneumothorax and chest tubes in chest x-rays, achieving state-of-the-art accuracy and improved clinical utility, including identifying missed cases in large datasets.

Contribution

The study presents a novel multi-stage algorithm for pneumothorax detection that performs well on data with and without chest tubes, enhancing clinical applicability.

Findings

Achieves state-of-the-art pneumothorax classification accuracy.

Performs consistently on data with and without chest tubes.

Successfully identifies missed pneumothorax cases in large datasets.

Abstract

Chest x-ray imaging is widely used for the diagnosis of pneumothorax and there has been significant interest in developing automated methods to assist in image interpretation. We present an image classification pipeline which detects pneumothorax as well as the various types of chest tubes that are commonly used to treat pneumothorax. Our multi-stage algorithm is based on lung segmentation followed by pneumothorax classification, including classification of patches that are most likely to contain pneumothorax. This algorithm achieves state of the art performance for pneumothorax classification on an open-source benchmark dataset. Unlike previous work, this algorithm shows comparable performance on data with and without chest tubes and thus has an improved clinical utility. To evaluate these algorithms in a realistic clinical scenario, we demonstrate the ability to identify real cases of missed pneumothorax in a large dataset of chest x-ray studies.