Vascular Image Analysis Using Contrast Timing for Access Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining arterial and venous access positions in complex vascular structures, such as those found in the brain, are inefficient and lack accuracy due to varying geometric conditions and branching vessels, which complicates the embolization process.
Innovation Solution
A method utilizing contrast agent flow dynamics through vascular structures, captured in image data with time information, to differentiate between arteries and veins by determining access positions based on time limits and geometric criteria, supported by artificial intelligence for enhanced accuracy and efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If segmentation of image data is used to trace blood vessels, then the course of blood vessels can be identified more effectively, but the method lacks accuracy in determining arterial and venous access positions due to varying geometric conditions and branching vessels
Solution Approach 1:
The patent applies preliminary action by performing segmentation of the vascular structure before determining access positions. The segmentation process creates a simplified representation of the vascular tree, which is then used as a basis for identifying arterial and venous access positions. This preliminary structuring enables more accurate differentiation between artery and vein based on topological relationships and flow direction analysis.
Solution Approach 2:
The patent transitions from two-dimensional image data to a three-dimensional vascular model by reconstructing the vascular structure in space. This dimensional transformation allows for more precise determination of access positions by considering spatial relationships, branching patterns, and flow dynamics in three dimensions, thereby improving measurement precision beyond what is achievable with planar images alone.
2Reliability
If complex vascular structures with branching vessels are analyzed, then complete vascular mapping is achieved, but the determination of access positions becomes inefficient and computationally intensive
Solution Approach 1:
The patent divides the complex vascular structure into segmented components representing different vascular segments and branches. By segmenting the vascular tree into manageable units with defined topological relationships, the system can efficiently analyze each segment independently while maintaining the overall vascular map. This segmentation reduces computational complexity compared to analyzing the entire vascular structure as a single complex entity.
Solution Approach 2:
The patent applies local quality by focusing computational resources on determining access positions at specific critical locations within the vascular structure rather than uniformly processing all vessels. The method identifies and prioritizes regions where access positions are most likely to be located, such as branch points and terminal vessels, thereby improving efficiency while maintaining reliability of the overall vascular mapping.
3Device complexity
If traditional image analysis methods are used without time information, then processing is simpler, but differentiation between arteries and veins is not possible
Solution Approach 1:
The patent introduces time as an additional parameter to the image analysis process by capturing images at multiple time points during contrast agent injection and flow. This parameter change from static to temporal analysis enables differentiation between arteries and veins based on the timing and pattern of contrast agent arrival and flow direction, while the processing remains relatively simple by utilizing temporal correlation of image sequences.
Data Source
AI summary
A computer-implemented method for evaluating image data depicting a vascular structure for the purpose of automatically determining at least one arterial and/or venous access position of the vascular structure. An embolization may be carried out at at least one peripheral position of a pathological change in the region of the vascular structure by introducing a catheter via an access path which runs through the vascular structure and leads from the access position or one of the access positions to the respective peripheral position. The method includes obtaining the image data comprising a plurality of image points, wherein those image points through whose respectively associated position in the vascular structure a contrast agent flowed during the recording of the image data, or of raw images from which the image data is derived, are each assigned at least one captured item of time information relating to a time point at which the contrast agent reached the respective position, the contrast agent being administered during or before this recording and determining the at least one arterial and/or venous access position on the basis of the at least one item of time information.