Building a Benchmark Dataset and Classifiers for Sentence-Level Findings in AP Chest X-rays

TL;DR

This paper introduces a new dataset with detailed sentence-level annotations for AP chest X-rays and demonstrates the feasibility of training classifiers to recognize these detailed findings using deep learning.

Contribution

It provides a rich, annotated benchmark dataset for AP chest X-ray findings and develops classifiers capable of recognizing detailed findings from images.

Findings

Rich sentence-level descriptors for AP chest X-ray findings

Deep learning classifiers can learn to identify detailed findings

Crowdsourcing effectively generates ground truth annotations

Abstract

Chest X-rays are the most common diagnostic exams in emergency rooms and hospitals. There has been a surge of work on automatic interpretation of chest X-rays using deep learning approaches after the availability of large open source chest X-ray dataset from NIH. However, the labels are not sufficiently rich and descriptive for training classification tools. Further, it does not adequately address the findings seen in Chest X-rays taken in anterior-posterior (AP) view which also depict the placement of devices such as central vascular lines and tubes. In this paper, we present a new chest X-ray benchmark database of 73 rich sentence-level descriptors of findings seen in AP chest X-rays. We describe our method of obtaining these findings through a semi-automated ground truth generation process from crowdsourcing of clinician annotations. We also present results of building classifiers for these findings that show that such higher granularity labels can also be learned through the framework of deep learning classifiers.