Apparatus and method for determining measure of similarity between images
First Claim
1. A method in image-guided surgery for determining the measure of similarity of a first image of an object and a second image of said object, the method comprising:
- a. forming a difference image by subtracting the corresponding pixel values of the second image from each pixel value of the first image;
wherein said first image is an x-ray image of said object generated in near real time, and said second image is a DRR (digitally reconstructed radiograph) synthesized from previously generated 3D scan data of said object; and
b. forming a pattern intensity function by summing asymptotic functions of the gradients of said difference image over all the pixels within a neighborhood R;
wherein said neighborhood R is defined so that said gradients of said difference image can be considered in at least four directions.
11 Assignments
0 Petitions
Accused Products
Abstract
A method and system is presented in image-guided radiosurgery for determining the measure of similarity of two digital images, for example a 2D x-ray image and a 2D DRR synthesized from 3D scan data. A two-dimensional array of pixel values of a difference image is formed by subtracting each pixel value of the second image from the corresponding pixel value of the first image. The pattern intensity function is constructed by taking the summation of asymptotic functions of the gradients of the difference image. The neighborhood R is defined so as to allow the gradients of the difference image to be considered in at least four directions.
-
Citations
17 Claims
-
1. A method in image-guided surgery for determining the measure of similarity of a first image of an object and a second image of said object, the method comprising:
-
a. forming a difference image by subtracting the corresponding pixel values of the second image from each pixel value of the first image; wherein said first image is an x-ray image of said object generated in near real time, and said second image is a DRR (digitally reconstructed radiograph) synthesized from previously generated 3D scan data of said object; and b. forming a pattern intensity function by summing asymptotic functions of the gradients of said difference image over all the pixels within a neighborhood R; wherein said neighborhood R is defined so that said gradients of said difference image can be considered in at least four directions. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14)
-
-
15. A system for determining the measure of similarity of a 2D x-ray image of an object and a 2D DRR of said object generated from previously obtained 3D scan data, said x-ray image and said DRR being discretized images characterized by a first and second 2D array of pixel values, the system comprising:
-
a. means for generating 3D scan data of said object; b. an x-ray source for generating at least one imaging beam; c. imaging means for generating a 2D radiographic image of said object in near real time, by directing said imaging beam towards and through said object from a known location and angle and at a known intensity, and detecting said imaging beam after said beam has passed through said object; d. a controller, including; i) software for generating a set of 2D DRR images of said object, using said 3D scan data and said known location, angle, and intensity of said imaging beam; and ii) software for determining the measure of similarity between said 2D x-ray image and said 2D DRR, by subtracting each pixel value of said second image from a corresponding pixel value of said first image to form a difference image, by adding the asymptotic functions of the gradients of the difference image over all the pixels within a neighborhood R; wherein said pattern intensity function is an asymptotic function of the gradients of said difference image; and wherein said neighborhood R is defined so that said gradients of said difference image can be considered in at least four directions. - View Dependent Claims (16, 17)
-
Specification