Aneurysm Segmentation in Volumetric Image Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current aneurysm segmentation techniques in 3D image data often result in incomplete detection and inaccurate measurements due to aneurysm overflow or leak outside the region of interest, especially in complex cases, leading to high risks of rupture and hemorrhage.
Innovation Solution
A framework that generates a refined mask by performing region growing starting at an aneurysm dome point to eliminate indirectly connected vessels, and further removes 'kissing vessels' to accurately segment the aneurysm and its parent vessel in volumetric image data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional segmentation technique is used, then aneurysm detection can be performed, but aneurysm overflow or leak outside region of interest occurs leading to incomplete detection and inaccurate measurements
Solution Approach 1:
The patent applies segmentation by dividing the aneurysm detection task into multiple processing stages: initial segmentation to identify candidate regions, refinement processing to eliminate false positives and overflow, and final classification. This multi-stage segmentation approach resolves the contradiction by improving both detection accuracy and segmentation completeness through systematic refinement.
Solution Approach 2:
The patent employs preliminary action by performing pre-processing steps including noise reduction, contrast enhancement, and initial thresholding before the main segmentation process. These preliminary actions prepare the image data to reduce overflow and leak phenomena, thereby improving both measurement precision and segmentation reliability.
2Productivity
If traditional segmentation technique is used, then processing speed can be maintained, but detection accuracy decreases due to aneurysm overflow and leak
Solution Approach 1:
The patent performs preliminary image enhancement and noise reduction before segmentation, which simplifies subsequent processing steps and maintains overall processing speed while improving detection accuracy by reducing overflow and leak artifacts in advance.
Solution Approach 2:
The patent applies partial action by focusing computational resources on critical regions identified in preliminary processing, rather than uniformly processing the entire volume. This selective approach maintains productivity while improving measurement precision in the aneurysm region of interest.
Data Source
AI summary
A framework for isolating an aneurysm and parent vessel in volumetric image data is provided herein. In accordance with one aspect, the framework generates a refined mask by performing region growing starting at an aneurysm dome point to eliminate vessels that are indirectly connected to an aneurysm or parent vessel in volumetric image data. A final mask may be generated based at least in part on the refined mask by eliminating any kissing vessel connected with the aneurysm from the refined mask. The final mask may then be used for segmentation of the aneurysm and the parent vessel in the volumetric image data.