Volume Rendering via Boundary Mesh Extraction and Smoothing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In medical imaging, volume rendering techniques struggle to distinguish between tissues of interest and adjacent tissues due to similar voxel values, leading to indistinguishable rendered images, and existing methods face efficiency and smoothness issues in rendering three-dimensional structures.
Innovation Solution
The method involves obtaining boundary meshes of tissues from volume data, determining intersections of rendering rays with these meshes, and using these intersections to calculate a volume rendering result, which includes processing the meshes with a mesh smoothing algorithm to enhance smoothness and continuity of tissue boundaries.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional volume rendering is used to render tissues with similar voxel values, then the rendering operation can be performed, but the tissues of interest become indistinguishable from adjacent tissues in the rendered image
Solution Approach 1:
The patent segments the volume data into different tissue regions by extracting boundary meshes for each tissue type. This segmentation allows the rendering system to treat different tissues differently, applying unique rendering parameters to each tissue region based on its boundary mesh, thereby making tissues with similar voxel values distinguishable through their boundary characteristics
Solution Approach 2:
The patent applies local quality by assigning different rendering parameters to different tissue regions. Each tissue is rendered with parameters (such as color, opacity, and boundary sharpness) that are specific to that tissue type, derived from its boundary mesh. This allows tissues with similar voxel values to be differentiated through their locally optimized rendering properties
2Shape
If boundary meshes are extracted and mesh smoothing is applied to improve boundary smoothness, then the visual quality improves, but the computational complexity increases
Solution Approach 1:
The patent applies preliminary action by extracting boundary meshes and performing mesh smoothing before the actual rendering process. This preliminary processing of the mesh data allows the rendering system to work with pre-smoothed boundaries, reducing the computational burden during rendering while maintaining smooth boundary appearance
Solution Approach 2:
The patent creates a simplified representation (boundary mesh) of the complex volume data. Instead of processing the entire volumetric dataset for smoothing, the system works with the extracted mesh surfaces, which are computationally lighter while preserving the essential boundary geometry and smoothness characteristics
3Productivity
If traditional volume rendering processes are used, then the rendering can be performed, but the efficiency is reduced due to processing all volume data uniformly
Solution Approach 1:
The patent extracts only the boundary mesh information from the complete volume data. By taking out and focusing on just the boundary surfaces rather than processing the entire volumetric dataset uniformly, the system significantly reduces processing time while maintaining rendering quality, as boundaries are the critical features for tissue differentiation
Solution Approach 2:
The patent applies local quality by concentrating computational resources on boundary regions rather than uniformly processing the entire volume. The mesh extraction and smoothing operations focus specifically on tissue boundaries, where the most important visual differentiation occurs, thereby optimizing processing efficiency by working only on critical regions
Data Source
AI summary
The present disclosure relates to a method for image processing. The method may be implemented on a computing device having at least one storage device storing a set of instructions, and at least one processor in communication with the at least one storage device. The method may include for each stage of at least one stage of a target disease, determining a type of one or more regions of interest (ROIs) corresponding to the stage; generating a first distribution image indicating the distribution of the one or more ROIs corresponding to the stage in a subject by processing a structural image of the subject based on the type of the one or more ROIs; and generating a lesion detection result of the subject by processing a functional image of the subject based on the first distribution image corresponding to the stage.