CT image-based spine three-dimensional modeling method and device
A CT image, 3D modeling technology, applied in image analysis, image enhancement, 3D modeling, etc., can solve problems such as inconvenience in case interpretation
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0106] figure 1 A schematic flow chart of a method for three-dimensional modeling of the spine based on CT images provided by an embodiment of the present invention; figure 2 A schematic diagram of the principles of the CT image-based spine three-dimensional modeling method provided by the embodiment of the present invention; figure 1 and figure 2 As shown, the method includes:
[0107] S101: Acquire a CT image of the spine to be segmented, wherein the spine to be segmented includes several vertebrae, and each vertebra corresponds to several CT images in the CT image.
[0108] Specifically, step S101 may include the following steps:
[0109] A: The original CT image of the spine to be segmented can be obtained, and the image parameters of the original CT image can be obtained, wherein the image parameters include: slope, intercept, image center coordinates, and image width.
[0110] The source image data used in the embodiment of the present invention is a high-definitio...
Embodiment 2
[0155] It is found through experiments that for a slightly deformed spine, when passing through the junction of two deformed vertebral bodies, adjacent images are usually very similar, making it difficult to distinguish the vertebral body structures. Using a single threshold α is not enough.
[0156]Therefore, in a specific implementation manner of the embodiment of the present invention, the difference between Embodiment 2 of the present invention and Embodiment 1 of the present invention lies in:
[0157] The acquisition process of the preset threshold includes: using the formula, α=0.1802*e -0.7713x +0.7752, calculate the first preset threshold, where α is the first preset threshold; e is the natural base; x is the interval between two adjacent images in the sequence of CT images of the current vertebra;
[0158] Using the formula, β=0.1802*e -0.7713x +0.6635, calculate the second preset threshold, where β is the second preset threshold; e is the natural base;
[0159] T...
Embodiment 3
[0165] In a specific implementation manner of the embodiment of the present invention, on the basis of Embodiment 1 of the present invention, the following steps are added before step S103:
[0166] Figure 8 A schematic diagram of the spinous process recognition process in the CT image-based spine three-dimensional modeling method provided by the embodiment of the present invention, as shown in Figure 8 As shown, H: When the current image is the last CT image of the current vertebra, the next image of the current image is taken as the current image.
[0167] In the region similarity detection step, if the similarity rate is not greater than α or β, the two images no longer belong to the same pyramid. However, the spinous part of the spine usually extends into the first few images of the next vertebra, and this part of the vertebral structure usually appears at the bottom of the image until it disappears. Therefore, we start corner detection from the first image where the r...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More