Visual enhancement of interval changes using temporal subtraction and pattern detector
View Patent ↗A workflow method for temporal nodule review by registering a reference image R with a floating image F, convolving the reference image R and the floating image with the same window function H w to generate R w and F w , generating a subtraction image by performing subtraction R w −F w (g(r)) wherein r represents a voxel (x, y, z) in reference image R, applying a pattern detector to said subtraction image to detect corresponding nodules in reference image R and floating image F and displaying corresponding nodules.
1. A workflow method for nodule detection review comprising:
registering a reference image R with a floating image F,
convolving said reference image R with a window function Hw to generate Rw,
convolving said floating image F with the same window function Hw to generate Fw,
generating a subtraction image by performing subtraction Rw−Fw (g(r)), wherein r represents a voxel (x, y, z) in the reference image R,
applying a pattern detector to said subtraction image to detect corresponding nodules in reference image R and floating image F, and
displaying corresponding nodules.
2. A workflow method according to claim 1 wherein said window function is an averaging function.
3. A workflow method according to claim 2 wherein the size of said window function is related to the dimensions of said nodules.
4. A workflow method according to claim 1 wherein the size of said window function is related to the dimensions of said nodules.
5. A computer software product for nodule detection review, the product comprising a non-transitory computer-readable medium in which program instructions are stored, which instructions, when read by a computer, cause the computer to:
register a reference image R with a floating image F,
convolve said reference image R with a window function Hw to generate Rw,
convolve said floating image F with the same window function Hw to generate Fw,
generate a subtraction image by performing subtraction Rw−Fw (g(r)), wherein r represents a voxel (x, y, z) in reference image R,
apply a pattern detector to said subtraction image to detect corresponding nodules in reference image R and floating image F, and
display corresponding nodules.
6. A computer executing a software product for nodule detection review, the computer:
registering a reference image R with a floating image F,
convolving said reference image R with a window function Hw to generate Rw,
convolving said floating image F with the same window function Hw to generate Fw,
generating a subtraction image by performing subtraction Rw−Fw (g(r)), wherein r represents a voxel (x, y, z) in reference image R,
applying a pattern detector of the computer to said subtraction image to detect corresponding nodules in reference image R and floating image F, and
displaying corresponding nodules on a display of the computer.
7. A computer according to claim 6 wherein said window function is an averaging function.
8. A computer according to claim 7 wherein the size of said window function is related to the dimensions of said nodules.
9. A computer according to claim 6 wherein the size of said window function is related to the dimensions of said nodules.
10. A product according to claim 5 wherein said window function is an averaging function.
11. A product according to claim 10 wherein the size of said window function is related to the dimensions of said nodules.
12. A product according to claim 5 wherein the size of said window function is related to the dimensions of said nodules.