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

By William Gale, Luke Oakden-Rayner, Gustavo Carneiro, Andrew P. Bradley, Lyle J. Palmer. 2017

115 citations recorded by the source corpus.

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.

Subfields: Biomedical Engineering, Surgery

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

Citations in the corpus

Deep learning predicts hip fracture using confounding patient and healthcare variables (2018, methodology): “Gale et al. also used a different deep-learning strategy that leveraged multiple CNN models.”
Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: A cross-sectional study (2018, background): “CNN architectures designed specifically to accommodate the higher resolution of radiological imaging have demonstrated promising early results [23,24].”
AI for radiographic COVID-19 detection selects shortcuts over signal (2020, methodology): “This architecture has not only been used in a variety of recent models for COVID-19 classification [4, 5], but has also been used for the diagnosis of non-COVID pneumonia [24, 29], as well as for more general radiographic classification [36].”
Deep learning in radiology: an overview of the concepts and a survey of the state of the art with focus on MRI (2018, result): “Some recent studies [133, 134, 135, 136, 137, 138, 139, 4] indicate performance of these algorithms comparable to expert humans, but these results are only applicable to a very small minority of the tasks that radiologists perform.”
Hidden stratification causes clinically meaningful failures in machine learning for medical imaging (2019, methodology): “We show a similar trend in Adelaide Hip Fracture Schema completion also shows hidden stratification on a large, high quality pelvic x-ray dataset from the Royal Adelaide Hospital [15].”