CUDA-based medical image three-dimensional reconstruction method
A technology of three-dimensional reconstruction and medical image, applied in the field of three-dimensional reconstruction of medical image, can solve the problem of giving up flexibility and so on
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0071] The key to the implementation of the ray casting algorithm on CUDA is to be able to use the GPU to complete the traversal, sampling and calculation of the volume data, and to mix the obtained sampling values to produce the final reconstruction result.
[0072] To implement the ray casting algorithm with CUDA, it is necessary to declare a kernel function kernel to traverse volume data, equidistant sampling in the light direction, and cumulative calculation of color values. In the implementation process, each ray is equivalent to a thread, and multiple threads can be executed in parallel, so that multiple rays can be calculated in parallel. Use the loadRawFile function to read volume data on the CPU host side and store it in the system memory; then copy the volume data from the system memory to the global memory on the GPU device side through the system bus, and allocate thread blocks and threads according to the size of the volume data , in the kernel function, each ra...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


