TY - JOUR T1 - Leveraging uncertainty information from deep neural networks for disease detection JF - bioRxiv DO - 10.1101/084210 SP - 084210 AU - Christian Leibig AU - Vaneeda Allken AU - Philipp Berens AU - Siegfried Wahl Y1 - 2017/01/01 UR - http://biorxiv.org/content/early/2017/08/02/084210.abstract N2 - Deep learning (DL) has revolutionized the field of computer vision and image processing. In medical imaging, algorithmic solutions based on DL have been shown to achieve high performance on tasks that previously required medical experts. However, DL-based solutions for disease detection have been proposed without methods to quantify and control their uncertainty in a decision. In contrast, a physician knows whether she is uncertain about a case and will consult more experienced colleagues if needed. Here we evaluate the uncertainty of DL in medical diagnostics based on a recent theoretical insight on the link between dropout networks and approximate Bayesian inference. Using the example of detecting diabetic retinopathy (DR) from fundus photographs, we show that uncertainty informed decision referral improves diagnostic performance. Experiments across different networks, tasks and datasets showed robust generalization. Depending on network capacity and task/dataset difficulty, we surpass 85% sensitivity and 80% specificity as recommended by the NHS when referring 0% – 20% of the most uncertain decisions for further inspection. We analyse causes of uncertainty by relating intuitions from 2D visualizations to the high-dimensional image space. While uncertainty is sensitive to clinically relevant cases, sensitivity to unfamiliar data samples is task dependent, but can be rendered more robust. ER -