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

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