Heart Segment Tracking via 4D Tensor Modeling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for monitoring the right ventricle of the heart are inadequate due to its complex shape and irregular anatomy, leading to inaccurate volume measurements and poor reproducibility, especially in congenital heart disease cases, where existing imaging modalities like echocardiograms and MRI are time-consuming and prone to errors.
Innovation Solution
A system and method that utilize four-dimensional modeling to track segmental movement of the heart by generating three-dimensional models from two-dimensional and three-dimensional echocardiogram images, overlaying a mesh, dividing it into segments, measuring changes in magnitude and direction, and determining tensors to represent volume and function over the heart cycle.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If visual estimation methods are used to evaluate right ventricular volume and function, then the measurement process is simple and quick, but the accuracy and reproducibility are poor
Solution Approach 1:
The right ventricle is divided into multiple segments (e.g., basal, mid, apical regions) that are tracked independently through the cardiac cycle. This segmentation allows complex 3D volume calculations to be broken down into manageable components, improving both accuracy and computational efficiency.
Solution Approach 2:
The patent transitions from 2D echo images to 3D volumetric modeling by acquiring multiple image planes and reconstructing the right ventricle in three dimensions. This dimensional change enables accurate volume measurement despite the complex, non-ellipsoidal shape of the right ventricle.
2Ease of manufacture
If geometric reference figure methods (area-length, multiple-slice) are used to measure right ventricular volume, then the measurement process is standardized, but the accuracy is compromised due to the irregular shape of the right ventricle
Solution Approach 1:
The patent employs dynamic 3D modeling that captures the right ventricle's shape at multiple time points throughout the cardiac cycle. The model adapts to the changing geometry of the ventricle during contraction and relaxation, providing accurate volume measurements without relying on static geometric assumptions.
Solution Approach 2:
The patent creates a digital 3D copy of the right ventricle from echo images, allowing the complex geometry to be represented exactly as it appears in the patient. This virtual replica can be manipulated and measured without the constraints of simplifying geometric assumptions.
3Measurement precision
If 3D echocardiogram volumetric imaging is used to capture the full volume of the heart, then the spatial resolution is improved, but the temporal resolution is compromised due to the time required to acquire and process the data
Solution Approach 1:
The patent performs preliminary segmentation and labeling of the right ventricle in early cardiac phases, allowing the 3D model to be pre-configured before complete data acquisition. This enables faster processing and reduces the time required to generate accurate volumetric measurements.
Solution Approach 2:
The patent continuously tracks the right ventricle through the entire cardiac cycle without interruption, maintaining consistent 3D modeling throughout. This continuous approach eliminates the need to restart measurements and provides both high spatial and temporal resolution efficiently.
4Measurement precision
If manual border tracing in multiple image planes is performed to measure right ventricular volume, then the measurement accuracy is improved, but the time consumption and operator dependency increase
Solution Approach 1:
The patent employs automated algorithms that independently perform the border tracing and 3D reconstruction without requiring manual intervention. The system self-calibrates and processes the echo images automatically, eliminating operator variability and reducing measurement time while maintaining high accuracy.
Solution Approach 2:
The patent replaces manual mechanical border tracing with automated computational algorithms that process images through digital image processing techniques. This substitution eliminates human error and time consumption while providing consistent, reproducible measurements.
Data Source
AI summary
Disclosed is a system, method and/or computer readable medium for use with for imaging the heart and/or segments of the chambers of the heart. Segments from a heart pair (i.e., an ES model and an ED model of the heart) are preferably matched between segments that make up the respective surfaces of the ES and ED models, each segment having a relative angle and displacement. The same segment is present in the two models but at a different position and orientation in three-dimensional space. The displacement of the matching or paired segments indicates the movement of that segment over the heart cycle. In a preferred embodiment, the segments are positioned in the same anatomical structure of the heart, therefore tracking the segments represents the actual anatomic movement. A four-dimensional model may preferably be created from two-dimensional echocardiogram images.