Cross-Modal Generative Framework for Signal Translation from Fetal-Maternal Electrocardiograms to Fetal Doppler Waveforms

2026-07-08

AI Summary

This study addresses the challenge of reconstructing fetal Doppler waveforms from synchronized maternal and fetal electrocardiographic signals to disentangle mechanically driven blood flow components into those explainable and unexplainable by electrical activity. To this end, the authors propose a cross-modal generative framework that integrates dual-channel ECG inputs, leveraging dilated convolutions and self-attention mechanisms to model long-range temporal dependencies, while introducing a cross-modal attention module to quantify maternal-fetal cardiac coupling. By analyzing residual components in the synthesized Doppler signals, the method effectively isolates purely mechanical contributions, thereby enhancing the comprehensiveness of fetal circulatory assessment. Evaluated on 39 pregnancy cases, the approach reduces power spectral density mean squared error (PSD MSE) to 49.9 ± 15.8 dB²—a 51% improvement over baseline—and achieves a heart rate estimation error of 4.71 ± 0.77 bpm, with the cross-modal attention mechanism alone contributing an additional 39% reduction in PSD MSE.

Abstract

Fetal electrocardiogram (fECG) and Doppler ultrasound provide complementary views of fetal cardiovascular function: fECG captures electrical activity while Doppler reflects mechanical hemodynamics shaped by factors such as placental resistance and vascular compliance. Understanding the recoverable and unrecoverable Doppler components through reconstruction from fECG offers insight into the relative contributions of electrical versus mechanical factors in fetal circulation, thereby informing clinical decisions. In addition, clinical evidence of maternal-fetal cardiac coupling suggests that maternal cardiovascular dynamics may also inform fetal hemodynamics. To computationally model these relationships, we propose a cross-modal generative framework combining dilated convolutions with cross-modal attention to selectively incorporate maternal ECG and self-attention to capture long-range temporal dependencies. Trained on 885 synchronized fetal/maternal ECG and Doppler envelope segments from 39 pregnancies, our model synthesizes Doppler envelopes with power spectral density mean squared error (PSD MSE) of 49.9 +/- 15.8 dB^2 (51% lower than two-channel baseline) and heart-rate error of 4.71 +/- 0.77 bpm (1.5% better than baseline; negligible relative to the 110-160 bpm physiological range). Cross-modal attention yields a 39% PSD MSE reduction over naive dual-channel concatenation, quantifying the contribution of maternal-fetal coupling. Our proposed framework advances computational modeling of the maternal-fetal cardiovascular system by enabling the synthesis of Doppler envelopes from dual-lead ECG. By analysis of both recoverable and residual Doppler components, this approach enables quantification of the purely mechanical contributions to Doppler waveforms -- those not recoverable from electrical recordings -- ultimately facilitating a more comprehensive fetal assessment.

Problem

• fetal electrocardiogram
• Doppler ultrasound
• cross-modal generation
• maternal-fetal coupling
• signal translation

Innovation

• cross-modal generative framework
• dilated convolutions
• cross-modal attention
• fetal Doppler synthesis
• maternal-fetal cardiac coupling