Method and system for three-dimensional reconstruction of medical images based on monte carlo path tracing
By combining Monte Carlo path tracing with Woodcock random tracking and a hybrid scattering model, the problems of high computational cost and noise control in traditional methods are solved, achieving efficient and accurate 3D reconstruction of medical images, improving image quality and interactive response speed, and making it suitable for medical image diagnosis and visualization.
CN122199801APending Publication Date: 2026-06-12NORTHEASTERN UNIV CHINA
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- NORTHEASTERN UNIV CHINA
- Filing Date
- 2026-03-11
- Publication Date
- 2026-06-12
Smart Images
Figure CN122199801A_ABST
Abstract
This invention provides a method and system for 3D reconstruction of medical images based on Monte Carlo path tracing, belonging to the field of medical image processing technology. The method includes: acquiring medical image sequence data of the object to be reconstructed; obtaining 3D volume data through preprocessing; constructing a regular voxel mesh model; constructing a virtual camera model and setting an imaging plane; generating an initial ray for each pixel defined on the imaging plane, originating from the camera and entering the 3D voxel space defined by the regular voxel mesh model; sampling the path of each initial ray using the Woodcock tracing method to obtain the path sampling result for each initial ray; generating the illumination rendering result of the 3D volume data based on a hybrid scattering and illumination modeling framework and performing bilateral filtering denoising processing to obtain the denoised illumination rendering result as the 3D medical image reconstruction result. This invention provides a new solution for medical image visualization that balances accuracy and efficiency.
Need to check novelty before this filing date? Find Prior Art