3D Cardiac Anatomy Model via Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for reconstructing cardiac anatomy, such as atrial fibrillation ablation, are prone to long procedural times and excessive radiation exposure, and lack precision in visualizing key structures like the left atrium, pulmonary veins, and left atrial appendage.
Innovation Solution
An apparatus and method using machine-learning to generate a three-dimensional (3D) model of cardiac anatomy, which involves receiving images of cardiac anatomy, generating training data using a 3D heart model, training a cardiac anatomy modeling model, and refining an initial 3D model based on the generated data structure.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If current LA reconstruction methods (FAM, cardiac CT merging, Ultrasound assisted anatomy reconstruction) are used, then cardiac anatomy can be reconstructed, but procedural time becomes excessively long and radiation exposure increases
Solution Approach 1:
The patent uses pre-acquired cardiac CT images to create a 3D anatomical model that serves as a copy of the actual cardiac structures. This pre-built model eliminates the need for time-consuming procedural reconstruction methods like FAM or ultrasound-assisted reconstruction, providing immediate access to precise anatomical information without extending procedural time
Solution Approach 2:
The 3D cardiac anatomical model is constructed and prepared in advance (preliminarily) using cardiac CT images before the ablation procedure begins. This preliminary action allows the model to be ready for integration with the ablation system, eliminating the need for time-consuming intra-procedural reconstruction and reducing overall procedural time while maintaining anatomical precision
2Measurement precision
If current LA reconstruction methods are used, then cardiac anatomy can be reconstructed, but radiation exposure becomes excessive
Solution Approach 1:
The patent creates a digital 3D copy of cardiac anatomy from pre-acquired CT images, eliminating the need for additional radiation exposure during the procedure. This copy can be repeatedly viewed and manipulated without exposing the patient to more radiation, unlike methods that require continuous imaging during reconstruction
Solution Approach 2:
The pre-acquired cardiac CT images serve multiple purposes: they provide the diagnostic information needed for ablation planning and simultaneously generate the 3D anatomical model. This multi-functionality eliminates the need for separate imaging procedures during reconstruction, reducing cumulative radiation exposure while maintaining comprehensive anatomical visualization
3Ease of operation
If ultrasound-assisted anatomy reconstruction is used, then real-time guidance is possible, but system complexity and manual segmentation requirements increase
Solution Approach 1:
The patent replaces complex mechanical and manual segmentation systems with an automated computational approach. The 3D model is generated automatically from cardiac CT images using image processing algorithms, eliminating the need for manual segmentation and complex ultrasound-assisted reconstruction systems while maintaining real-time guidance capabilities through digital integration
Data Source
AI summary
An apparatus for generating a three-dimensional (3D) model of cardiac anatomy via machine-learning, wherein the apparatus includes a process and a memory containing instructions configuring the processor to receive a set of images of a cardiac anatomy pertaining to a subject, generate an 3D data structure representing the cardiac anatomy as a function of the set of images using a cardiac anatomy modeling model, generate an initial 3D model of the cardiac anatomy, refine the generated initial 3D model of the cardiac anatomy as a function of the 3D data structure representing the cardiac anatomy, and generate a subsequent 3D model of the cardiac anatomy as a function of the refinement.