Near Real-Time Implementation of An Adaptive Seismocardiography - ECG Multimodal Framework for Cardiac Gating

Area of Science:

• Medical Imaging
• Biomedical Engineering
• Cardiovascular Diagnostics

Background:

• Accurate cardiac gating is essential for high-quality computed tomography (CT) imaging in cardiovascular disease diagnosis.
• Conventional gating methods, often relying solely on electrocardiography (ECG), may have limitations in precision.
• Optimizing cardiac gating can lead to improved diagnostic accuracy and patient outcomes.

Purpose of the Study:

• To present a near real-time cardiac gating strategy by fusing seismocardiography (SCG) and ECG.
• To evaluate the feasibility and accuracy of this multimodal gating approach.
• To demonstrate improvements in quiescence prediction for CT data acquisition.

Main Methods:

• Integration of commercial hardware and software platforms for a multimodal sensing system.
• Fusion of seismocardiography (SCG) and electrocardiography (ECG) signals for cardiac gating.
• Testing on healthy subjects and cardiac patients, with comparisons to echocardiography-derived quiescence.

Main Results:

• The implemented system achieved an average processing latency of 5.1 ms, well within acceptable limits.
• The SCG-ECG-based method reduced average prediction error from 59.58 ms (ECG-only) to 27.24 ms.
• The multimodal framework demonstrated significantly improved quiescence prediction accuracy.

Conclusions:

• The developed SCG-ECG fusion method offers a feasible and accurate near real-time cardiac gating solution.
• This optimized strategy enhances diagnostic capabilities in CT imaging for cardiovascular diseases.
• The multimodal approach provides superior performance compared to ECG-only gating methods.