US 11,751,832 B2
CTA large vessel occlusion model
Markus Daniel Herrmann, Boston, MA (US); John Francis Kalafut, Pittsburgh, PA (US); Bernardo Canedo Bizzo, Boston, MA (US); Christopher P. Bridge, Cambridge, MA (US); Michael Lev, Newton, MA (US); Charles J. Lu, Cambridge, MA (US); and James Hillis, Cambridge, MA (US)
Assigned to GE Precision Healthcare LLC, Waukesha, WI (US); Partners HealthCare System, Inc., Boston, MA (US); The General Hospital Corporation, Boston, MA (US); and The Brigham and Women's Hospital, Inc., Boston, MA (US)
Filed by GE Precision Healthcare LLC, Waukesha, WI (US); Partners Healthcare System, Inc., Boston, MA (US); The General Hospital Corporation, Boston, MA (US); and The Brigham and Women's Hospital, Inc., Boston, MA (US)
Filed on Oct. 29, 2020, as Appl. No. 17/83,761.
Claims priority of provisional application 63/086,368, filed on Oct. 1, 2020.
Claims priority of provisional application 62/967,849, filed on Jan. 30, 2020.
Prior Publication US 2021/0236080 A1, Aug. 5, 2021
Int. Cl. A61B 6/00 (2006.01); A61B 6/03 (2006.01); G06T 7/70 (2017.01); G06N 20/20 (2019.01); G16H 30/20 (2018.01)
CPC A61B 6/507 (2013.01) [A61B 6/032 (2013.01); A61B 6/501 (2013.01); A61B 6/504 (2013.01); A61B 6/5217 (2013.01); G06N 20/20 (2019.01); G06T 7/70 (2017.01); G16H 30/20 (2018.01); G06T 2207/10081 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/20132 (2013.01); G06T 2207/30101 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system, comprising:
a memory that stores computer-executable components; and
a processor, operably coupled to the memory, that executes the computer-executable components stored in the memory, wherein the computer-executable components comprise:
an input component that receives at least computed tomography angiogram (CTA) images of a patient's brain; and
a localization component that determines, via a machine learning algorithm, a location of a large vessel occlusion (LVO) in the patient's brain based on the at least CTA images, wherein the location of the LVO comprises a laterality, and wherein the machine learning algorithm comprises a three-dimensional convolutional neural network model that produces at least a first scalar output indicating the laterality.