New AI framework translates fetal ECG to Doppler waveforms

Researchers have developed a novel cross-modal generative framework that translates fetal electrocardiogram (fECG) signals into fetal Doppler waveforms. This model utilizes dilated convolutions and cross-modal attention to incorporate maternal ECG data and capture temporal dependencies. When trained on data from 39 pregnancies, the framework synthesized Doppler envelopes with significantly reduced power spectral density mean squared error compared to baseline methods, and also improved heart-rate error. AI

IMPACT This research could lead to more comprehensive fetal assessments by enabling better understanding of cardiovascular system dynamics.

RANK_REASON The cluster contains a research paper detailing a new AI framework for signal translation in a medical context. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• Doppler
• Doppler Ultrasound Detection of Tissue Motion and Flow Generated By External Energy
• electrocardiography
• FECG signal extraction based on multichannel v-SVR combined with TFBSS
• Fetal Electrocardiogram Extraction-Pilot Study

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →