US 11,741,605 B2
Method and system for image registration using an intelligent artificial agent
Rui Liao, Princeton Junction, NJ (US); Shun Miao, Bethesda, MD (US); Pierre de Tournemire, Nancy (FR); Julian Krebs, Moers (DE); Li Zhang, Princeton, NJ (US); Bogdan Georgescu, Princeton, NJ (US); Sasa Grbic, Plainsboro, NJ (US); Florin Cristian Ghesu, Skillman, NJ (US); Vivek Kumar Singh, Princeton, NJ (US); Daguang Xu, Princeton, NJ (US); Tommaso Mansi, Plainsboro, NJ (US); Ali Kamen, Skillman, NJ (US); and Dorin Comaniciu, Princeton, NJ (US)
Assigned to Siemens Healthcare GmbH, Erlangen (DE)
Filed by Siemens Healthcare GmbH, Erlangen (DE)
Filed on Dec. 12, 2022, as Appl. No. 18/64,366.
Application 18/064,366 is a continuation of application No. 15/587,094, filed on May 4, 2017, abandoned.
Application 15/587,094 is a continuation of application No. 16/861,353, filed on Apr. 29, 2020, granted, now 11,557,036.
Application 16/861,353 is a continuation of application No. 15/587,094, filed on May 4, 2017, abandoned.
Claims priority of provisional application 62/338,059, filed on May 18, 2016.
Claims priority of provisional application 62/344,125, filed on Jun. 1, 2016.
Claims priority of provisional application 62/401,977, filed on Sep. 30, 2016.
Prior Publication US 2023/0114934 A1, Apr. 13, 2023
Int. Cl. G06K 9/00 (2022.01); G06T 7/00 (2017.01); G06T 7/30 (2017.01); A61B 5/00 (2006.01)
CPC G06T 7/0012 (2013.01) [A61B 5/7267 (2013.01); G06T 7/30 (2017.01); G06T 2207/20081 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for registration of medical images; comprising:
receiving a first medical image and a second medical image;
performing an initial registration of the first medical image and the second medical image using a first trained deep neural network;
generating higher-resolution patches around anatomical landmarks for the first medical image and the second medical image, the higher-resolution patches having a higher resolution than the first medical image and the second medical image; and
refining the initial registration based on the higher-resolution patches using a second trained deep neural network to register the first medical image and the second medical image.