54 citations · 79 across the 4 of their papers we have counts for
4 papers
Hidden Stratification Causes Clinically Meaningful Failures in Machine Learning for Medical Imaging
Luke Oakden-Rayner, Jared Dunnmon, Gustavo Carneiro +1
Machine learning models for medical image analysis often suffer from poor performance on important subsets of a population that are not identified during training or testing. For e…
Producing radiologist-quality reports for interpretable artificial intelligence
William Gale, Luke Oakden-Rayner, Gustavo Carneiro +2
Current approaches to explaining the decisions of deep learning systems for medical tasks have focused on visualising the elements that have contributed to each decision. We argue…
Detecting hip fractures with radiologist-level performance using deep neural networks
William Gale, Luke Oakden-Rayner, Gustavo Carneiro +2
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…
Automated 5-year Mortality Prediction using Deep Learning and Radiomics Features from Chest Computed Tomography
Gustavo Carneiro, Luke Oakden-Rayner, Andrew P. Bradley +2
We propose new methods for the prediction of 5-year mortality in elderly individuals using chest computed tomography (CT). The methods consist of a classifier that performs this pr…