Multi-device medical image rigid registration method based on same overaly region frame
A medical image and rigid registration technology, which is applied in image enhancement, image data processing, special data processing applications, etc., can solve the problems of poor robustness, improve robustness, eliminate local extreme values, and reduce misalignment Effect
Inactive Publication Date: 2004-04-14
广州宜诚数字医疗系统有限公司
View PDF0 Cites 9 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0006] The purpose of the present invention is to address the disadvantages of poor robustness of the current traditional registration method, and from the perspective of image overlapping areas, a multi-device medical image rigid registration method based on the same overlapping area framework is proposed to improve the robustness of the method It can reduce the mis-matching rate of image registration, so as to meet the registration requirements of most medical images in the clinical application environment
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0024] The present invention will be further described below in conjunction with specific examples.
[0025] 1. Select the position transformation of a floating image to the reference image as the initial coordinate transformation, such as image 3 shown;
[0026] 2. Obtain the overlapping area of the two sets of images to be registered under the initial coordinate transformation, as shown in 4;
[0027] 3. In an area near the above-mentioned initial coordinate transformation, translate the position of the floating image by 2 mm and rotate it by 2° as a comparison coordinate transformation; obtain the overlapping area of the two sets of images to be registered under the comparison coordinate transformation, such as Figure 5 , 6 shown; the process is as follows: take the coordinates of the reference image as a reference, and for each voxel point on the reference image, obtain the corresponding coordinate points on the floating image under coordinate transformation, if th...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The method includes following steps. (1) A float image is selected from transformed position of a reference image by using an original coordinate transformation. Comparison coordinate transformation is carried out for the said float image in area near to the original coordinate transformation. (2) Same overlap area is obtained from two float images relevant to two coordinate transformations and the reference image. (3) Similarity measures are calculated for the same overlap area under two coordinate transformations. (4) Based on comparing values of similarity measures, the coordinate transformation with large similarity measure is selected to update the original coordinate transformation. Going back to step (1), cyclic search is carried out until similarity measure is largest under the original coordinate transformation. The method eliminates local extrema caused by different overlap areas so as to reduce mismatching and raise robustness of the method.
Description
Technical field [0001] The invention relates to a method for rigid registration of multi-device medical images based on the framework of the same overlapping area. The multi-device images include anatomical images such as CT, MR, and B-ultrasound, and functional images such as SPECT and PET. Background technique [0002] With the development of medical imaging equipment research and development, more and more medical imaging equipment is used clinically, and plays an important role in clinical diagnosis and treatment. There are many types of these equipment images, including equipment images such as CT, MR, and B-ultrasound that reflect the anatomical structure of the human body, and equipment images such as SPECT, PET, and fMR that reflect the metabolic function of the human body. The reason why various images are used clinically at the same time is that these images have different advantages and disadvantages. How to better combine the images of these different devices, le...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06T5/50
Inventor 陈明陈武凡
Owner 广州宜诚数字医疗系统有限公司