Deep Learning Model Provides Rapid Detection of Stroke-causing Blockages (IMAGE)

Radiological Society of North America

Deep Learning Model Provides Rapid Detection of Stroke-causing Blockages

Caption

Images show false-positive finding prediction in a 52-year-old man who presented with acute stroke symptoms to the emergency department. A, Axial arterial phase CT angiography and, B, axial venous phase CT angiography images show no evidence of a large vessel occlusion. Additional noncontrast-enhanced brain CT images (not shown) did not show evidence of acute infarct. C, Diffusion-weighted MRI performed 6 hours after presentation shows an area of restricted diffusion consistent with an acute infarct in the left paramedian pons (arrow). D, Heat map overlay shows focal activity projecting over the central brain.

Credit

Radiological Society of North America

Usage Restrictions

May use with credit.

License

Licensed content

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.