The General Hospital Corporation

The Brigham and Women's Hospital, Inc.

Ge Precision Healthcare LLC

Partners Healthcare System, Inc.

Charles J Lu

John Francis Kalafut

Bernardo Canedo Bizzo

Michael Lev

Christopher P Bridge

Markus Daniel Herrmann

James Hillis

Systems and techniques that facilitate automated localization of large vessel occlusions are provided. In various embodiments, an input component can receive computed tomography angiogram (CTA) images of a patient's brain. In various embodiments, a localization component can determine, via a machine learning algorithm, a location of a large vessel occlusion (LVO) in the patient's brain based on the CTA images. In various instances, the location of the LVO can comprise a laterality and an occlusion site. In various aspects, the laterality can indicate a right side or a left side of the patient's brain, and the occlusion site can indicate an internal carotid artery (ICA), an M1 segment of a middle cerebral artery (MCA) or an M2 segment of an MCA. In various cases, a visualization component can generate and display to a user a three-dimensional maximum intensity projection (MIP) reconstruction of the patient's brain based on the CTA images to facilitate visual verification of the LVO by the user.

CTA large vessel occlusion model

Growing community of inventors

Cambridge, MA, United States of America

Charles J Lu