3D Anatomical Model Generation Using Anchor Constraints
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for generating three-dimensional models of anatomic structures during medical procedures often result in inaccurate representations due to incomplete or uncertain data sets, particularly in areas with local concavities, leading to challenges in accurately placing medical devices like catheters.
Innovation Solution
The system constrains three-dimensional surface representations relative to anchor portions identified by sensors or physician input, ensuring accurate depiction of anatomic features and allowing for efficient generation based on incomplete data, by modifying the volumetric smoothing process to maintain anatomical accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If three-dimensional models are generated based on incomplete or uncertain data sets of medical device locations, then the models can be built efficiently, but the accuracy of anatomic feature representation deteriorates
Solution Approach 1:
The system performs preliminary actions by identifying and marking anchor portions (reliable data points) before generating the three-dimensional model. These anchor portions serve as pre-established reference points that constrain the model generation process, ensuring accurate representation of anatomic features even when the overall data set is incomplete or uncertain.
2Stability of the object's composition
If volumetric smoothing is applied to three-dimensional surface representations, then the model appears smoother and more continuous, but local anatomic details and accuracy are lost
Solution Approach 1:
The system applies local quality by allowing different regions of the three-dimensional model to have different levels of smoothing. Areas with high confidence data (near anchor portions) maintain sharp local anatomic details, while areas with uncertain data receive smoothing to fill gaps. This creates a spatially varying smoothing effect that preserves local accuracy where needed while maintaining overall surface continuity.
Solution Approach 2:
The volumetric smoothing process is segmented into multiple passes or regions. The system divides the three-dimensional space into zones based on data confidence, applying different smoothing intensities to different segments. This segmentation allows the model to simultaneously achieve surface continuity in low-confidence regions and preserve local anatomic details in high-confidence regions.
3Manufacturing precision
If anchor portions are used to constrain the three-dimensional surface representation, then the accuracy of anatomic features is improved, but the complexity of the modeling process increases
Solution Approach 1:
The system implements self-service by automatically identifying and marking anchor portions from the available sensor data without requiring manual intervention. The algorithm autonomously determines which data points serve as reliable anchors based on confidence metrics, automatically constraining the three-dimensional model generation process. This automation reduces the apparent complexity for the user while maintaining high anatomic feature accuracy.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Devices, systems, and methods of the present disclosure are directed to generating three-dimensional surface representations of an anatomic structure such as a heart cavity. More specifically, a three-dimensional surface representation of the anatomic structure is constrained relative to one or more anchor portions corresponding to received input regarding the location of anatomic features of the anatomic structure. The resulting three-dimensional surface representation includes salient features of the anatomic structure and, therefore, can be useful as visualization tool during any of various different medical procedures, including, for example, cardiac ablation.