US 11,806,189 B2
Three-dimensional segmentation from two-dimensional intracardiac echocardiography imaging
Gareth Funka-Lea, Princeton, NJ (US); Haofu Liao, Rochester, NY (US); Shaohua Kevin Zhou, Princeton, NJ (US); Yefeng Zheng, Princeton Junction, NJ (US); and Yucheng Tang, Nashville, TN (US)
Assigned to Siemens Medical Solutions USA, Inc., Malvern, PA (US)
Filed by Siemens Medical Solutions USA, Inc., Malvern, PA (US)
Filed on Nov. 28, 2022, as Appl. No. 18/059,042.
Application 18/059,042 is a continuation of application No. 16/130,320, filed on Sep. 13, 2018, granted, now 11,534,136.
Claims priority of provisional application 62/634,935, filed on Feb. 26, 2018.
Prior Publication US 2023/0113154 A1, Apr. 13, 2023
Int. Cl. G06K 9/00 (2022.01); A61B 8/08 (2006.01); A61B 8/12 (2006.01); A61B 8/14 (2006.01); A61B 90/00 (2016.01); A61B 8/13 (2006.01); G06T 15/20 (2011.01); A61B 18/14 (2006.01); G06T 7/12 (2017.01); G06T 7/33 (2017.01); G06T 13/20 (2011.01); A61B 5/055 (2006.01); A61B 8/00 (2006.01); A61B 18/00 (2006.01)
CPC A61B 8/0883 (2013.01) [A61B 8/12 (2013.01); A61B 8/13 (2013.01); A61B 8/145 (2013.01); A61B 8/483 (2013.01); A61B 8/5207 (2013.01); A61B 8/5215 (2013.01); A61B 8/5261 (2013.01); A61B 90/37 (2016.02); G06T 15/205 (2013.01); A61B 5/055 (2013.01); A61B 8/0891 (2013.01); A61B 8/4245 (2013.01); A61B 8/4254 (2013.01); A61B 8/4483 (2013.01); A61B 8/466 (2013.01); A61B 18/1492 (2013.01); A61B 2018/00357 (2013.01); A61B 2018/00577 (2013.01); A61B 2090/363 (2016.02); A61B 2090/367 (2016.02); A61B 2090/378 (2016.02); A61B 2090/3762 (2016.02); G06T 7/12 (2017.01); G06T 7/344 (2017.01); G06T 13/20 (2013.01); G06T 2200/08 (2013.01); G06T 2207/10132 (2013.01); G06T 2207/10136 (2013.01); G06T 2207/20004 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30048 (2013.01)] 4 Claims
OG exemplary drawing
 
1. A system for generating a three-dimensional segmentation mask, the system comprising:
an ultrasound imager configured to generate two-dimensional intracardiac echocardiography (ICE) images of a part of a cardiac system of a patient with an ICE transducer;
an image processor configured to generate the three-dimensional segmentation mask from the two-dimensional ICE images using a machine-learned multi-task generative adversarial network; and
a display configured to display ablation guidance relative to an image of the three-dimensional segmentation mask.