Method and system for scale-based vessel enhancement in X-ray angiography
View Patent ↗A method and system for scale-based vessel enhancement in x-ray angiography images is disclosed. An input x-ray image is denoised. A lighting field is estimated in the denoised image. Vessels are extracted from the denoised image by dividing the denoised image by the estimated lighting field. Vessels are enhanced in the input x-ray image by linearly combining the extracted vessels with the input x-ray image, resulting in an enhanced image.
1. A method for vessel enhancement in an input x-ray image, comprising:
denoising the input x-ray image;
estimating a lighting field in the denoised image;
extracting vessels from the denoised image based on the estimated light field; and
generating an enhanced image by enhancing vessels in the input x-ray image based on the extracted vessels.
2. The method of claim 1 , wherein said step of denoising the input x-ray image comprises:
denoising the input x-ray image using an ROF model.
3. The method of claim 1 , wherein said step of estimating a lighting field in the denoised image comprises:
decomposing the denoised image based on scale to estimate a large scale lighting field.
4. The method of claim 1 , wherein said step of estimating a lighting field in the denoised image comprises:
estimating the lighting field using scale-dependent and intensity- independent decomposition of the denoised image.
5. The method of claim 1 , wherein said step of estimating a lighting field in the denoised image comprises:
estimating the lighting field in the denoised image using a TV-L 1 model.
6. The method of claim 5 , wherein said step of estimating the lighting field in the denoised image using a TV-L 1 model comprises generating an estimated light field u from the denoised image f as:
u
=
min
u
∫
Ω
∇
u
+
λ
f
-
u
L
1
,
where
∫
Ω
∇
u
is the total variation or u over its domain Ω, and λis a parameter set to a value corresponding to a scale of the lighting field.
7. The method of claim 1 , wherein said step of extracting vessels from the denoised image based on the estimated light field comprises:
dividing the denoised image by the estimated lighting field.
8. The method of claim 1 , wherein said step of generating an enhanced image by enhancing vessels in the input x-ray image based on the extracted vessels comprises:
linearly combining the extracted vessels and the input x-ray image to generate the enhanced image.
9. The method of claim 1 , further comprising:
automatically adjusting a contrast of the enhanced image.
10. The method of claim 9 , wherein said step of automatically adjusting a contrast of the enhanced image comprises:
adjusting a contrast of the enhanced image using one of histogram redistribution and histogram equalization.
11. An apparatus for vessel enhancement in an input x-ray image, comprising:
means for denoising the input x-ray image;
means for estimating a lighting field in the denoised image;
means for extracting vessels from the denoised image based on the estimated light field; and
means for generating an enhanced image by enhancing vessels in the input x-ray image based on the extracted vessels.
12. The apparatus of claim 11 , wherein said means for denoising the input x-ray image comprises:
means for denoising the input x-ray image using an ROF model.
13. The apparatus of claim 11 , wherein said means for estimating a lighting field in the denoised image comprises:
means for estimating the lighting field using scale-dependent and intensity-independent decomposition of the denoised image.
14. The apparatus of claim 11 , wherein said means for estimating a lighting field in the denoised image comprises:
means for estimating the lighting field in the denoised image using a TV-L 1 model.
15. The apparatus of claim 11 , wherein said step of extracting vessels from the denoised image based on the estimated light field comprises:
dividing the denoised image by the estimated lighting field.
16. The apparatus of claim 11 , wherein said means for generating an enhanced image by enhancing vessels in the input x-ray image based on the extracted vessels comprises:
means for linearly combining the extracted vessels and the input x-ray image to generate the enhanced image.
17. The apparatus of claim 11 , further comprising:
means for automatically adjusting a contrast of the enhanced image.
18. A non-transitory computer readable medium encoded with computer executable instructions for vessel enhancement in an input x-ray image, the computer executable instructions defining steps comprising:
denoising the input x-ray image;
estimating a lighting field in the denoised image;
extracting vessels from the denoised image based on the estimated light field; and
generating an enhanced image by enhancing vessels in the input x-ray image based on the extracted vessels.
19. The non-transitory computer readable medium of claim 18 , wherein the computer executable instructions defining the step of denoising the input x-ray image comprise computer executable instructions defining the step of:
denoising the input x-ray image using an ROF model.
20. The non-transitory computer readable medium of claim 18 , wherein the computer executable instructions defining the step of estimating a lighting field in the denoised image comprise computer executable instructions defining the step of:
estimating the lighting field using scale-dependent and intensity- independent decomposition of the denoised image.
21. The non-transitory computer readable medium of claim 18 , wherein the computer executable instructions defining the step of estimating a lighting field in the denoised image comprise computer executable instructions defining the step of:
estimating the lighting field in the denoised image using a TV-L 1 model.
22. The non-transitory computer readable medium of claim 18 , wherein the computer executable instructions defining the step of extracting vessels from the denoised image based on the estimated light field comprise computer executable instructions defining the step of:
dividing the denoised image by the estimated lighting field.
23. The non-transitory computer readable medium of claim 18 , wherein the computer executable instructions defining the step of generating an enhanced image by enhancing vessels in the input x-ray image based on the extracted vessels comprise computer executable instructions defining the step of:
linearly combining the extracted vessels and the input x-ray image to generate the enhanced image.
24. The non-transitory computer readable medium of claim 18 , further comprising computer executable instructions defining the step of:
automatically adjusting a contrast of the enhanced image.