Sub-voxel Anatomical Model Refinement via Tissue Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current medical imaging technologies struggle to accurately correlate three-dimensional anatomical models with medical images at resolutions finer than the resolution of the images themselves, limiting the precision in diagnosing anatomical changes such as tumor growth or deformation.
Innovation Solution
The method employs sophisticated digital anatomical atlases that refine anatomical models to sub-voxel resolution by using computed percentages of different tissues within a voxel volume, adjusting the three-dimensional model to more accurately represent the contents of the voxel volume, allowing for precise modeling of anatomical changes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If sophisticated composite anatomical atlases are used to provide detailed three-dimensional models, then model resolution is improved, but the ability to accurately correlate with individual patient medical images at finer resolutions deteriorates due to voxel size limitations
Solution Approach 1:
The patent segments each voxel into multiple sub-voxel regions, allowing the anatomical model to be divided and positioned at sub-voxel precision. This segmentation enables the model to achieve higher resolution correlation with patient images by distributing model features across sub-voxel portions rather than being constrained to whole-voxel boundaries
Solution Approach 2:
The patent introduces a sub-voxel dimension by computing partial voxel intensities and distributing model features across sub-voxel portions. This adds a finer resolution dimension below the original voxel grid, enabling more precise alignment between anatomical models and individual patient images without requiring higher-resolution imaging data
2Device complexity
If the voxel volume is used as the smallest unit for intensity assignment, then the imaging process is simplified, but the resolution is limited and cannot capture anatomical changes at finer scales
Solution Approach 1:
The patent segments each voxel into multiple sub-voxel portions and computes intensity contributions from each portion separately. This segmentation allows the system to achieve higher anatomical model resolution by distributing model features across sub-voxel regions, capturing anatomical changes at scales finer than the original voxel dimensions while maintaining compatibility with standard medical imaging data
Solution Approach 2:
The patent changes the resolution parameter by computing partial voxel intensities and positioning model features at sub-voxel precision. This parameter change enables the system to work with standard medical imaging data while producing anatomical models at higher resolution through computational refinement of voxel-level information
Data Source
AI summary
The current document is directed to methods and systems that refine anatomical models to sub-voxel resolution. In certain implementations, sophisticated, composite, digital anatomical atlases provide detailed three-dimensional models of the contents of three-dimensional medical images. However, three-dimensional medical images have limited resolutions characterized by a smallest volume, referred to as a voxel, to which an intensity is assigned by the imaging process. The currently disclosed methods employ computed percentages of different types of tissue within voxel volumes to adjust a three-dimensional model of the contents of the voxel volumes to more accurately model the contents of the voxel volumes.