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

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.

6 pages

References in corpus (2)

• Adam: A Method for Stochastic Optimization
• Densely Connected Convolutional Networks

Cited by in corpus (11)

• Confounding variables can degrade generalization performance of radiological deep learning models
• A Review of Challenges and Opportunities in Machine Learning for Health
• Adversarial Attacks Against Medical Deep Learning Systems
• Towards Evaluating the Robustness of Deep Diagnostic Models by Adversarial Attack
• Deep learning in radiology: an overview of the concepts and a survey of the state of the art
• Producing radiologist-quality reports for interpretable artificial intelligence
• Towards generative adversarial networks as a new paradigm for radiology education
• Anatomy-Aware Siamese Network: Exploiting Semantic Asymmetry for Accurate Pelvic Fracture Detection in X-ray Images
• Automating Abnormality Detection in Musculoskeletal Radiographs through Deep Learning
• Individual predictions matter: Assessing the effect of data ordering in training fine-tuned CNNs for medical imaging
• Auto-Classification of Retinal Diseases in the Limit of Sparse Data Using a Two-Streams Machine Learning Model