Vascular Image Co-Registration for Hemodynamic Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing medical imaging systems for vascular assessment lack effective methods for co-registering intravascular and extravascular imaging data, limiting the integration of hemodynamic data without additional pullback runs.
Innovation Solution
A neural network is trained using co-registered intravascular and extravascular imaging data sets, including intravascular ultrasound, optical coherence tomography, and angiographic data, to predict hemodynamic values during intravascular imaging events, enabling simultaneous display of both types of data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional vascular imaging methods are used separately, then each imaging modality can be optimized independently, but the integration of intravascular and extravascular imaging data is limited and requires additional pullback runs
Solution Approach 1:
The patent combines intravascular imaging data (from intravascular imaging elements) with extravascular imaging data (from extravascular imaging elements) by co-registering them to a common reference frame. This merging allows the system to integrate multiple imaging modalities and simultaneously display both intravascular and extravascular images, eliminating the need for additional pullback runs while improving overall vascular assessment capability.
Solution Approach 2:
The patent introduces a co-registration system that acts as an intermediary between intravascular and extravascular imaging data. This intermediary component aligns the different imaging modalities by transforming coordinates and overlaying images on a common reference, enabling accurate integration without requiring the imaging elements to physically interact or perform additional measurements.
2Reliability
If additional pullback runs are performed to obtain hemodynamic data, then more comprehensive vascular assessment is achieved, but procedure time and complexity increase
Solution Approach 1:
The patent performs preliminary co-registration of intravascular and extravascular imaging data during the initial imaging process. By pre-aligning the imaging datasets and establishing a common reference frame before hemodynamic measurement, the system enables simultaneous display and integration of imaging data with hemodynamic values without requiring additional pullback runs, thus reducing procedure time while maintaining data accuracy.
Solution Approach 2:
The system uses feedback from the co-registered imaging data to automatically align and overlay intravascular and extravascular images. The feedback mechanism continuously adjusts the registration parameters to ensure accurate superposition of imaging modalities, enabling reliable hemodynamic assessment without repeated manual adjustments or additional imaging runs.
3Measurement precision
If intravascular and extravascular imaging data are displayed separately, then each image type can be optimized for its specific purpose, but the correlation between different imaging modalities is difficult to achieve
Solution Approach 1:
The patent transitions from displaying intravascular and extravascular imaging data in separate two-dimensional spaces to integrating them in a unified three-dimensional co-registered space. By adding the dimension of spatial registration and overlay, the system maintains the optimization benefits of separate imaging modalities while enabling direct visual correlation through multi-planar reconstruction and 3D rendering capabilities.
Data Source
AI summary
A neural network is trained for estimating patient hemodynamic data using a plurality of extravascular imaging data sets and a plurality of intravascular imaging data sets that are each co-registered to a corresponding extravascular imaging data set. A plurality of hemodynamic data sets are provided, each hemodynamic data set co-registered with the corresponding extravascular imaging data set. The neural network learns what hemodynamic data to expect for a given intravascular imaging data set. An intravascular imaging event is subsequently performed in which an intravascular imaging element is translated within a blood vessel of the patient to produce one or more intravascular images. The neural network uses its training to predict hemodynamic values corresponding to the one or more intravascular images from the intravascular imaging event, and the one or more intravascular images are outputted in combination with the predicted hemodynamic values.