NMCSE: Noise-Robust Multi-Modal Coupling Signal Estimation Method via Optimal Transport for Cardiovascular Disease Detection

2025-05-14

AI Summary

Traditional deconvolution methods for joint ECG–PCG analysis often amplify noise, limiting clinical performance in cardiovascular disease (CVD) detection. To address this, we formulate electro-mechanical coupling signal estimation as a distribution alignment problem jointly optimizing both amplitude and temporal dimensions, grounded in optimal transport theory—enabling robust, preprocessing-free coupling signal reconstruction. We propose an end-to-end framework integrating multimodal temporal alignment with spatiotemporal feature extraction, thereby circumventing the noise sensitivity inherent in inverse convolution. Evaluated on the noisy PhysioNet 2016 dataset, our method reduces mean squared error (MSE) by approximately 30% and significantly improves Pearson correlation. For CVD classification, it achieves 97.38% accuracy and an AUC of 0.98—outperforming state-of-the-art approaches. This work establishes a novel, theoretically principled paradigm for noise-robust multimodal physiological signal coupling.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Security and Privacy: Large-scale security measurements
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Electrocardiogram (ECG) and Phonocardiogram (PCG) signals are linked by a latent coupling signal representing the electrical-to-mechanical cardiac transformation. While valuable for cardiovascular disease (CVD) detection, this coupling signal is traditionally estimated using deconvolution methods that amplify noise, limiting clinical utility. In this paper, we propose Noise-Robust Multi-Modal Coupling Signal Estimation (NMCSE), which reformulates the problem as distribution matching via optimal transport theory. By jointly optimizing amplitude and temporal alignment, NMCSE mitigates noise amplification without additional preprocessing. Integrated with our Temporal-Spatial Feature Extraction network, NMCSE enables robust multi-modal CVD detection. Experiments on the PhysioNet 2016 dataset with realistic hospital noise demonstrate that NMCSE reduces estimation errors by approximately 30% in Mean Squared Error while maintaining higher Pearson Correlation Coefficients across all tested signal-to-noise ratios. Our approach achieves 97.38% accuracy and 0.98 AUC in CVD detection, outperforming state-of-the-art methods and demonstrating robust performance for real-world clinical applications.

Problem

• Estimating noise-robust coupling signals from ECG and PCG
• Improving cardiovascular disease detection accuracy
• Reducing noise amplification in multi-modal signal processing

Innovation

• Optimal transport for noise-robust signal estimation
• Joint optimization of amplitude and temporal alignment
• Temporal-Spatial Feature Extraction network integration