Personalized Topology-Informed Localization of Standard 12-Lead ECG Electrode Placement from Incomplete Cardiac MRIs for Efficient Cardiac Digital Twins

2024-08-25

AI Summary

This study addresses the challenge of automatically localizing personalized 12-lead ECG electrode positions for efficient cardiac digital twin (CDT) construction when full-torso anatomical structures are unavailable in clinical cardiac MRI. We propose a novel topology-guided, sparse-contour-driven electrode localization paradigm: leveraging only standard 2D cardiac MRI sequences, our deep learning framework extracts sparse torso contours and jointly performs keypoint regression with 3D topological constraints to achieve fully automatic, precise electrode placement on subject-specific torso surfaces. The method requires no additional torso imaging or manual intervention. Validation shows a mean localization error of 1.24 ± 0.293 cm—superior to conventional approaches—and inference time of only 2 seconds per case (≈1000× faster than manual placement). Furthermore, the predicted electrode positions enable high-fidelity body-surface ECG simulation, significantly enhancing CDT reconstruction efficiency and clinical practicality.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Machine Learning: Learning with Manifolds
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Cardiac digital twins (CDTs) offer personalized in-silico cardiac representations for the inference of multi-scale properties tied to cardiac mechanisms. The creation of CDTs requires precise information about the electrode position on the torso, especially for the personalized electrocardiogram (ECG) calibration. However, current studies commonly rely on additional acquisition of torso imaging and manual/semi-automatic methods for ECG electrode localization. In this study, we propose a novel and efficient topology-informed model to fully automatically extract personalized ECG standard electrode locations from 2D clinically standard cardiac MRIs. Specifically, we obtain the sparse torso contours from the cardiac MRIs and then localize the standard electrodes of 12-lead ECG from the contours. Cardiac MRIs aim at imaging of the heart instead of the torso, leading to incomplete torso geometry within the imaging. To tackle the missing topology, we incorporate the electrodes as a subset of the keypoints, which can be explicitly aligned with the 3D torso topology. The experimental results demonstrate that the proposed model outperforms the time-consuming conventional model projection-based method in terms of accuracy (Euclidean distance: $1.24 pm 0.293$ cm vs. $1.48 pm 0.362$ cm) and efficiency ($2$~s vs. $30$-$35$~min). We further demonstrate the effectiveness of using the detected electrodes for in-silico ECG simulation, highlighting their potential for creating accurate and efficient CDT models. The code is available at https://github.com/lileitech/12lead_ECG_electrode_localizer.

Problem

• Automates ECG electrode localization from cardiac MRIs.
• Enhances accuracy and efficiency in cardiac digital twins.
• Integrates topology to solve incomplete torso imaging issues.

Innovation

• Automated ECG electrode localization
• Topology-informed model from MRIs
• Efficient 3D torso alignment