US 12,080,002 B2
Systems and methods for medical image registration
Sean O'Connor, San Diego, CA (US); Eric Finley, San Diego, CA (US); and Kara Robinson, San Diego, CA (US)
Assigned to NuVasive, Inc., San Diego, CA (US)
Filed by NuVasive, Inc., San Diego, CA (US)
Filed on Jun. 4, 2021, as Appl. No. 17/338,845.
Claims priority of provisional application 63/040,410, filed on Jun. 17, 2020.
Prior Publication US 2021/0398299 A1, Dec. 23, 2021
Int. Cl. G06T 7/32 (2017.01); G06T 7/33 (2017.01)
CPC G06T 7/32 (2017.01) [G06T 7/33 (2017.01); G06T 2200/24 (2013.01); G06T 2207/10116 (2013.01); G06T 2207/20104 (2013.01); G06T 2207/30012 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A method for image registration of medical images, the method comprising: receiving a first image of a subject containing one or more objects there within, the first image taken
with a first radiation dosage;
receiving a second image of the subject containing the one or more objects there within, the second image taken with a second radiation dosage, wherein the second radiation dosage is lower than the first radiation dosage;
receiving a user input from an input device comprising a selection of a location of interest of the one or more objects in the second image, the first image, or both the second image and the first image;
in response to the user input received from the input device, providing an indication of an effect of the selection of the location of interest in the second image, the first image, or both the second image and the first image;
registering the second image and first image of the subject based on the user input thereby generating a registered image, including to score each of a plurality of candidate alignment transforms of the second image and the first image based on the selection of the location of interest in the second image, the first image, or both the second image and the first image;
applying a weight to pixel intensity of one or more pixels in the second image, the first image, or both the second image and the first image, based on the user input, thereby generating a weighted second image, a weighted first image, or both the weighted second image and the weighted first image;
weighing the pixel intensity proportionally to the distance from the center of the spot the user selected, such that the intensity remains unchanged in a small region centered on the selected position, then gradually drops to zero by the edge of the image, the down weighted image is then passed into alignment score search algorithm, wherein the transforms that correspond to irrelevant anatomy are configured with a lower percentage of optimization; and
presenting the registered image on a digital display.