Detecting hip fractures with radiologist-level performance using deep neural networks

TL;DR

This paper presents a deep learning system that detects hip fractures from pelvic x-rays with accuracy comparable to radiologists, trained on extensive clinical data, promising to enhance diagnostic efficiency and patient care.

Contribution

The study introduces a deep neural network trained on a large dataset that achieves radiologist-level performance in hip fracture detection from x-rays.

Findings

Achieved an AUC of 0.994 in fracture detection

System performs at radiologist-level accuracy

Potential to improve clinical workflow and patient outcomes

Abstract

We developed an automated deep learning system to detect hip fractures from frontal pelvic x-rays, an important and common radiological task. Our system was trained on a decade of clinical x-rays (~53,000 studies) and can be applied to clinical data, automatically excluding inappropriate and technically unsatisfactory studies. We demonstrate diagnostic performance equivalent to a human radiologist and an area under the ROC curve of 0.994. Translated to clinical practice, such a system has the potential to increase the efficiency of diagnosis, reduce the need for expensive additional testing, expand access to expert level medical image interpretation, and improve overall patient outcomes.