Atlas-Based Electromechanical Activation Mapping From Clinical VCGs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for generating patient-specific cardiac electrical and mechanical activation maps are either invasive or computationally expensive, lacking precision in non-invasive approaches.
Innovation Solution
Utilizing dimensionality reduction techniques such as PCA, t-SNE, and UMAP to generate atlases from cardiac electrophysiology and biomechanical simulations, allowing for efficient reconstruction of patient-specific activation patterns from non-invasive clinical measurements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If invasive procedures are used to generate patient-specific cardiac activation maps, then measurement precision is improved, but ease of operation deteriorates and loss of time increases
Solution Approach 1:
The patent introduces an atlas as an intermediary between non-invasive clinical measurements and patient-specific activation maps. The atlas, pre-computed from a population of simulations, serves as a reference framework that enables accurate reconstruction of individual activation patterns without direct invasive measurement, thus maintaining precision while eliminating procedural invasiveness
Solution Approach 2:
The patent creates a computational copy of cardiac activation patterns through the atlas, which captures the essential variability of activation maps across the population. This copying approach allows non-invasive reconstruction of patient-specific maps by matching clinical measurements to the atlas, avoiding the need for invasive procedures while preserving measurement accuracy
2Measurement precision
If individual patient simulations are performed to generate activation maps, then measurement precision is improved, but productivity deteriorates due to computational expense
Solution Approach 1:
The patent performs preliminary computations by pre-generating an atlas from a population of simulations before actual patient application. This preliminary action captures the essential variability of activation patterns, allowing rapid reconstruction of patient-specific maps through simple matching operations rather than computationally expensive individual simulations, thus achieving both precision and speed
Solution Approach 2:
The patent creates a universal atlas that serves multiple patients simultaneously. The single atlas captures population-level variability and can be applied to reconstruct activation maps for any individual patient through matching their specific clinical measurements, eliminating the need for separate simulations for each patient while maintaining patient-specific accuracy
3Ease of operation
If non-invasive clinical measurements are used, then ease of operation is improved, but measurement precision deteriorates due to lack of detailed cardiac data
Solution Approach 1:
The atlas acts as an intermediary that bridges non-invasive clinical measurements and detailed activation patterns. By matching accessible clinical data against the pre-computed atlas, the system recovers fine-grained activation details that would otherwise require invasive measurement, thus maintaining precision while preserving ease of operation
Solution Approach 2:
The patent replaces the mechanical/invasive measurement system with a computational matching system. Instead of physically inserting sensors to obtain detailed activation data, the system uses computational matching between non-invasive measurements and the atlas to reconstruct detailed activation patterns, substituting physical intrusion with information processing
Data Source
AI summary
A method may include generating, based on a plurality of electrophysiology simulations such as electrical and/or electromechanical activation maps, one or more atlases including an activation time (AT) atlas and a vectorcardiogram (VCG) atlas. The atlases may be generated by applying a dimensionality reduction technique to include one or more modes of variation present in the electrophysiology simulations. The atlases may be applied to match a clinical vectorcardiogram of a patient to a simulated vectorcardiogram associated with an activation map included in the electrophysiology simulations. At least one of a diagnosis or treatment for the patient may be determined based on the activation map. Related systems and computer program products are also provided.