Cardiac 3D Model Generation from ICE Ultrasound Contours
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The construction of three-dimensional cardiac chamber models using an Intracardiac Echocardiography (ICE) catheter is time-consuming and prone to inaccuracies, requiring manual intervention and specialized knowledge for image selection, leading to incomplete and coarse models.
Innovation Solution
A method involving the acquisition of ultrasound images and probing position information, extraction of contour feature points, obtaining spatial positions, and calibrating a standard three-dimensional model using genetic algorithms to create a patient-specific cardiac model.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If manual processes are used to construct three-dimensional cardiac chamber models using an ICE catheter, then the surgeon can establish three-dimensional spatial information and determine relative position of surgical instruments, but the construction process is time-consuming and the generated models lack accuracy and detail
Solution Approach 1:
The system pre-processes and stores ultrasound images with their corresponding probing position information in a database before the actual model construction is needed. This preliminary organization of data allows for rapid retrieval and automatic processing during surgery, eliminating the time-consuming manual image selection and model construction steps while maintaining high accuracy through systematic data management
Solution Approach 2:
The system creates a digital copy of the cardiac chamber by automatically generating a three-dimensional model from stored ultrasound images and probing position data. This digital copying process replaces manual tracing and outlining, significantly reducing construction time while improving accuracy through automated image processing and three-dimensional reconstruction algorithms
2Measurement precision
If manual image selection is performed to construct three-dimensional models, then the surgeon can select images from specific cardiac cycle phases, but the process requires high level specialized knowledge and is time-consuming
Solution Approach 1:
The system performs automatic image selection by itself, retrieving ultrasound images based on stored probing position information and automatically identifying appropriate cardiac cycle phases. This self-service capability eliminates the need for the surgeon to manually select images, reducing both the time required and the specialized knowledge needed, while maintaining high selection accuracy through automated processing algorithms
3Quantity of substance
If manual tracing and outlining is used to build cardiac chamber models, then the surgeon can construct three-dimensional models, but the models are coarse and incomplete
Solution Approach 1:
The system automatically generates a complete and detailed three-dimensional model by digitally copying and reconstructing the cardiac chamber geometry from multiple ultrasound images. This automated copying process captures all anatomical details without the coarseness of manual tracing, while significantly reducing construction time through computer-based three-dimensional reconstruction algorithms that process multiple images simultaneously
Data Source
AI summary
A method of generating a model includes the steps of: acquiring a plurality of ultrasound images of a target object and corresponding probing position information; extracting a contour feature point set of the target object in each of the ultrasound images, where the contour feature point set includes a plurality of contour feature points; obtaining spatial position information of each of the contour feature points based on the contour feature point set corresponding to each of the ultrasound images and the probing position information; obtaining a target projection point of each of the contour feature points on a standard three-dimensional model corresponding to the target object according to the spatial position information of each of the contour feature points.