US 12,456,162 B2
System for and method of real-time nonrigid mosaicking of laparoscopy images
Haoyin Zhou, Boston, MA (US); and Jayender Jagadeesan, Boston, MA (US)
Assigned to The Brigham and Women's Hospital, Inc., Boston, MA (US)
Appl. No. 18/281,050
Filed by The Brigham and Women's Hospital, Inc., Boston, MA (US)
PCT Filed Mar. 10, 2022, PCT No. PCT/US2022/019753
§ 371(c)(1), (2) Date Sep. 8, 2023,
PCT Pub. No. WO2022/192540, PCT Pub. Date Sep. 15, 2022.
Claims priority of provisional application 63/159,393, filed on Mar. 10, 2021.
Prior Publication US 2024/0153031 A1, May 9, 2024
Int. Cl. G06K 9/00 (2022.01); A61B 1/00 (2006.01); A61B 1/313 (2006.01); G06T 3/18 (2024.01); G06T 3/4038 (2024.01); G06T 7/246 (2017.01); G06T 7/33 (2017.01)
CPC G06T 3/4038 (2013.01) [A61B 1/00009 (2013.01); A61B 1/3132 (2013.01); G06T 3/18 (2024.01); G06T 7/248 (2017.01); G06T 7/33 (2017.01); G06T 2200/32 (2013.01); G06T 2207/10021 (2013.01); G06T 2207/10068 (2013.01); G06T 2207/20072 (2013.01); G06T 2207/20221 (2013.01); G06T 2207/30004 (2013.01); G06T 2207/30244 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method for nonrigid mosaicking of images, comprising:
obtaining, using a processor, a plurality of images including a first image and a second image of a sample,
the first image and the second image containing information from partially overlapping portions of the sample;
identifying, using the processor, at least one feature match between the first image and the second image;
estimating, using the processor, a deformation of the sample between the first image and the second image based on identifying the at least one feature match, the estimating comprising:
generating a deformation field comprising an array of deformation nodes,
adjusting, using an expectation maximization and dual quaternion (EMDQ) procedure, the array of deformation nodes based on a first position of the at least one feature match in the first image and a second position of the at least one feature match in the second image, and
warping a position of each of a plurality of pixels of the second image based on the adjusted array of deformation nodes; and
combining, using the processor, the first image and the second image based on estimating the deformation between the first image and the second image.