Key result
A two-step multi-modal ECG and PCG segmentation algorithm achieved an F1 score of 96.43 on the PhysioNet 2016 dataset, and its segment-wise contrastive learning outperformed SimCLR with limited data.
Why the study?
Accurate heart sound segmentation algorithms remain understudied despite advances in wearable sensors, and existing deep learning models struggle to segment noisy signals using only PCG data.
A novel multi-modal deep learning framework combining ECG and PCG signals improves heart sound segmentation and reduces the need for large labeled datasets.
May support label-efficient multi-modal segmentation; extends contrastive learning but leaves open prospective clinical validation.
The COVID-19 pandemic has intensified the need for home-based cardiac health monitoring systems. Despite advancements in electrocardiograph (ECG) and phonocardiogram (PCG) wearable sensors, accurate heart sound segmentation algorithms remain understudied. Existing deep learning models, such as convolutional neural networks (CNN) and recurrent neural networks (RNN), struggle to segment noisy signals using only PCG data. We propose a two-step heart sound segmentation algorithm that analyzes synchronized ECG and PCG signals. The first step involves heartbeat detection using a CNN-LSTM-based model on ECG data, and the second step focuses on beat-wise heart sound segmentation with a 1D U-Net that incorporates multi-modal inputs. Our method leverages temporal correlation between ECG and PCG signals to enhance segmentation performance. To tackle the label-hungry issue in AI-supported biomedical studies, we introduce a segment-wise contrastive learning technique for signal segmentation, overcoming the limitations of traditional contrastive learning methods designed for classification tasks. We evaluated our two-step algorithm using the PhysioNet 2016 dataset and a private dataset from Bayland Scientific, obtaining a 96.43 F1 score on the former. Notably, our segment-wise contrastive learning technique demonstrated effective performance with limited labeled data. When trained on just 1% of labeled PhysioNet data, the model pre-trained on the full unlabeled dataset only dropped 2.88 in the F1 score, outperforming the SimCLR method. Overall, our proposed algorithm and learning technique present promise for improving heart sound segmentation and reducing the need for labeled data.
No takes yet. Share an insight, caveat, or question.
Huang et al. (2024) studied Heart sound segmentation. Two-step multi-modal ECG and PCG segmentation algorithm with segment-wise contrastive learning vs. SimCLR method was evaluated on F1 score for heart sound segmentation. A two-step multi-modal ECG and PCG segmentation algorithm achieved an F1 score of 96.43 on the PhysioNet 2016 dataset, and its segment-wise contrastive learning outperformed SimCLR with limited data.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: