Improved registration method for image with obvious local deformation
A local deformation and obvious technology, applied in image analysis, image data processing, instruments, etc., can solve problems such as over-constraint, registration accuracy drop, and over-smoothing
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
example 1
[0029] In this embodiment, two simulated human brain MR images in BrainWeb are taken as an example to describe the registration method of the present invention.
[0030] see figure 1 , the specific implementation steps of the registration method of the improved local deformation obvious image of the present invention are as follows:
[0031] Step 1, read in respectively image 3 (a) and image 3 (b), and will image 3 (a) As a reference image I, image 3 (b) as a floating image J. In order to improve the accuracy of calculation and speed up the convergence of the program, the read-in image 3 (a) and image 3(b) Convert from unsigned integer type to double-precision floating-point type, and then linearly transform their gray values into 0~1.
[0032] Step 2, to Indicates the position of the control point, n x ×n y ×n z Indicates the grid size, using the B-spline multi-resolution grid free deformation model shown in the following formula (II) to the floating imag...
example 2
[0050] In this example, liver images obtained by CT scanning in the arterial phase and venous phase after contrast agent injection Figure 5 (a) and Figure 5 (b) Take the registration method as an example, the specific steps are as follows.
[0051] first read in Figure 5 (a) and Figure 5 (b), and will Figure 5 (a) as a reference image, Figure 5 (b) as a floating image, and then follow the steps described in Example 1 for registration. In this example, the sizes of the three-layer deformed grids are 32×32×32, 16×16×16, and 8×8×8 in sequence; λ in formula (I) is 0.05, and γ is 0.001. Registration results such as Figure 6 (a) Column shown above.
[0052] In order to verify the effect of the method of the present invention, this example still refers to the prior art described in example 1 to Figure 5 (a) The reference image shown and Figure 5 The floating images shown in (b) are registered, and the registration results are as follows Figure 6 (b) Column shown a...
example 3
[0054] Example 3 (Research on the influence of λ value on registration effect)
[0055] In order to verify that the method proposed by the inventor has higher registration accuracy than the traditional free deformation registration method, and is more robust to the weight parameter λ, in this example, λ is set to 0.001, 0.005, 0.01, 0.05 respectively , 0.1 these 5 different values, carry out 5 groups of experimental comparisons.
[0056] In this example, use image 3 (a) as a reference image, image 3 (b) As a floating image, use the improved registration method for images with obvious local deformation and the existing method described in Example 1 for registration respectively. The comparison results are shown in Figure 7 . in Figure 7 (a) is listed as the residual map obtained by using the improved registration method of locally deformed images, Figure 7 (b) is listed as the residual map obtained by registration using the existing method described in Example 1. Fro...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More