Boston Scientific Scimed, Inc.

Kevin Bloms

Wenguang Li

Hatice Cinar Akakin

Matthew R Huston

Alexander Shang

A neural network is trained for estimating patient hemodynamic data using a plurality of extravascular imaging data sets and a plurality of intravascular imaging data sets that are each co-registered to a corresponding extravascular imaging data set. A plurality of hemodynamic data sets are provided, each hemodynamic data set co-registered with the corresponding extravascular imaging data set. The neural network learns what hemodynamic data to expect for a given intravascular imaging data set. An intravascular imaging event is subsequently performed in which an intravascular imaging element is translated within a blood vessel of the patient to produce one or more intravascular images. The neural network uses its training to predict hemodynamic values corresponding to the one or more intravascular images from the intravascular imaging event, and the one or more intravascular images are outputted in combination with the predicted hemodynamic values.

Systems and methods for vascular image co-registration

This disclosure provides alternative medical imaging systems and methods for vascular imaging co-registration. Methods include obtaining extravascular imaging data of a portion of a blood vessel including an extravascular image showing an intravascular imaging device disposed within the vessel with an imaging element disposed at a starting location for a translation procedure. The extravascular image also includes an extravascular contrast image showing the portion of the blood vessel with contrast showing a visualized anatomical landmark. Intravascular imaging data is obtained during the translation procedure that includes one or more intravascular images showing a detected anatomical landmark. The starting location and the ending location of the imaging element on the extravascular imaging data is marked, and the predicted location of the detected anatomical landmark on the extravascular imaging data is marked. The predicted location of the detected anatomical landmark is then aligned with the visualized anatomical landmark.

Growing community of inventors

Minneapolis, MN, United States of America

Kevin Bloms