Coronary Vasculature Modeling with Multi-Modal Image Registration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing medical imaging techniques often produce insufficient or inaccurate patient-specific anatomical models, particularly for coronary anatomy, due to limitations in integrating data from multiple imaging modalities, leading to imaging artifacts and reduced accuracy in assessing coronary lesions and blood flow.
Innovation Solution
A method and system that integrates imaging data from multiple sources, such as CT and MR, IVUS, OCT, and angiography, to create a precise, patient-specific anatomical model by averaging and merging image parameters across different imaging techniques, reducing artifacts and enhancing accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If single images are used for anatomical modeling, then the imaging process is simple and quick, but the model accuracy and completeness are insufficient
Solution Approach 1:
The patent combines multiple images from different imaging modalities (CT, MR, IVUS, OCT, angiography) to create a comprehensive anatomical model. By merging data from multiple sources, the system achieves higher model accuracy and completeness while compensating for the limitations of individual imaging techniques.
Solution Approach 2:
The patent creates a composite anatomical model that integrates information from different imaging modalities, similar to how composite materials combine different substances to achieve superior properties. The final model leverages the strengths of each imaging technique (e.g., CT for bone and blood vessels, MR for soft tissue) to produce a more accurate and comprehensive representation of the anatomy.
2Measurement precision
If multiple imaging modalities are integrated, then the model precision is improved, but the data processing complexity increases
Solution Approach 1:
The patent segments the anatomical modeling process into distinct steps: acquiring images from multiple modalities, extracting anatomical parameters from each image type, and integrating these parameters to create the final model. This segmentation allows for systematic processing of complex multi-modal data while maintaining precision.
Solution Approach 2:
The patent introduces an intermediary computational framework that processes and integrates data from different imaging modalities. This intermediary system handles the complexity of multi-modal data integration by providing a structured approach to combining parameters from CT, MR, IVUS, OCT, and angiography images.
3Loss of information
If multiple image acquisitions are performed, then the anatomical model completeness is enhanced, but the imaging time and resource usage increase
Solution Approach 1:
The patent performs preliminary acquisition of multiple imaging modalities before model creation, ensuring all necessary anatomical information is captured upfront. By obtaining CT, MR, IVUS, OCT, and angiography images in advance, the system prevents information loss and ensures comprehensive model completeness.
Solution Approach 2:
The patent employs a multi-functional imaging approach where a single comprehensive modeling system integrates multiple imaging modalities. This universal system can process various image types (CT, MR, ultrasound, optical, angiography) through a unified framework, reducing the need for separate specialized systems and optimizing resource utilization.
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
Systems and methods are disclosed for modeling a patient's coronary vasculature, using a computer system. The method comprises determining one or more lumen diameters from one or more three-dimensional, computed tomography images of the coronary vasculature; determining one or more anatomical parameters of the vasculature from one or more intravascular ultrasound, angiography, or optical coherence tomography images obtained from within a lumen of the patient's coronary vasculature; extracting a geometric model of the vasculature from a reference image chosen from among the images and registering an object model to the geometric model based on the determined lumen diameters or anatomical parameters. The one or more lumen diameters are updated based on at least one of the determined anatomical parameters, using the registration of the object model to the geometric model; and a model of the patient's coronary vasculature is generated based on at least one updated lumen diameter.