Meeting Banner
Abstract #2835

Deep Learning with Synthetic Diffusion-Weighted Images for Acute Ischemic Stroke Detection

CHRISTIAN FEDERAU1,2, Javier A. Montoya-Zegarra1, Soren Christensen3, Julian Maclaren3, Johanna Ospel2, Victor Schulze-Zachau2, Maarten Lansberg3, and Sebastian Kozerke1

1Institute for Biomedical Engineering, University and ETH Zurich, Zürich, Switzerland, 2Department of Radiology, University Hospital Basel, Basel, Switzerland, 3Neurology, Stanford University, Palo Alto, CA, United States

We studied the feasibility and accuracy of a deep learning algorithm trained on one million realistic synthetic acute stroke lesion images to detect and segment stroke lesions on clinical MR DW images. We compared this method to a more conventional approach, where a deep learning algorithm was trained on 10’000 human labelled images.

This abstract and the presentation materials are available to members only; a login is required.

Join Here