US 11,900,593 B2
Identifying blood vessels in ultrasound images
Davinder S. Dhatt, Bothell, WA (US); Christopher Aleksandr White, Bothell, WA (US); Adam Benjamin Pely, Bothell, WA (US); Thomas Michael Duffy, Bothell, WA (US); Paul Tomotaro Danset, Bothell, WA (US); and Diku Pranav Mandavia, Bothell, WA (US)
Assigned to FUJIFILM SONOSITE, INC., Bothell, WA (US)
Filed by FUJIFILM SONOSITE, INC., Bothell, WA (US)
Filed on Apr. 23, 2021, as Appl. No. 17/239,314.
Prior Publication US 2022/0343494 A1, Oct. 27, 2022
Int. Cl. G06K 9/00 (2022.01); G06T 7/00 (2017.01); A61B 8/08 (2006.01)
CPC G06T 7/0012 (2013.01) [A61B 8/085 (2013.01); G06T 2207/10016 (2013.01); G06T 2207/10024 (2013.01); G06T 2207/10132 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30101 (2013.01)] 15 Claims
OG exemplary drawing
 
1. A method implemented by a computing device for blood vessel identification, the method comprising:
assigning, with a neural network implemented at least partially in hardware of the computing device, one of a vein classification and an artery classification to one or more blood vessels in ultrasound images;
determining a misclassification for one blood vessel of the one or more blood vessels, the misclassification denoting the neural network assigning the one of the vein classification and the artery classification to the one blood vessel in one ultrasound image of the ultrasound images and the other of the vein classification and the artery classification to the one blood vessel in additional ultrasound images of the ultrasound images; and
displaying, in the one ultrasound image, an indication of the other of the vein classification and the artery classification for the one blood vessel, wherein the one ultrasound image and the additional ultrasound images represent frames in an ultrasound video, and the one ultrasound image represents a later frame in the ultrasound video than previous frames represented by the additional ultrasound images, wherein the assigning the one of the vein classification and the artery classification in the one ultrasound image is based on the one ultrasound image and at least one of the additional ultrasound images, and wherein the one ultrasound image and the at least one of the additional ultrasound images are greyscale images, and the assigning the one of the vein classification and the artery classification in the one ultrasound image includes receiving the greyscale images on separate color channels of the neural network.