Scaling to Multimodal and Multichannel Heart Sound Classification with Synthetic and Augmented Biosignals

📄 arXiv: 2509.11606 📥 PDF

作者: Milan Marocchi, Matthew Fynn, Kayapanda Mandana, Yue Rong

分类: cs.SD, cs.LG, eess.SP

发布日期: 2026-07-05

💡 一句话要点

提出基于增强数据集的多模态心音分类方法以提高心血管疾病检测准确性

🎯 匹配领域: 支柱九：具身大模型 (Embodied Foundation Models)

关键词: 心血管疾病 心音分类 多模态学习 数据增强 深度学习 去噪扩散模型 Wav2Vec 2.0 信号处理

📋 核心要点

  1. 现有心音分类方法受限于同步和多通道数据集的稀缺，导致深度学习模型的应用受到限制。
  2. 本研究通过结合传统信号处理与去噪扩散模型，创建增强数据集以训练Transformer架构，提升心音分类性能。
  3. 在多个数据集上，模型分别达到了92.48%和93.14%的准确率，展示了增强数据集在心血管疾病检测中的潜力。

📝 摘要（中文）

心血管疾病是全球主要死亡原因，早期检测至关重要。本文结合传统信号处理与去噪扩散模型，利用增强数据集训练基于Wav2Vec 2.0的分类器，针对多模态和多通道心音数据集进行分类。实验结果显示，模型在多个数据集上均取得了优异的性能，验证了增强数据集对心血管疾病检测的有效性。

🔬 方法详解

问题定义：本文旨在解决心血管疾病检测中，现有方法因缺乏同步和多通道数据集而导致的性能不足问题。

核心思路：通过结合传统信号处理技术与去噪扩散模型（如WaveGrad和DiffWave），生成增强数据集，以此来有效训练基于Wav2Vec 2.0的分类器。

技术框架：整体方法包括数据增强、模型训练和性能评估三个主要阶段。首先，通过去噪扩散模型生成增强数据集，然后使用该数据集对Transformer模型进行微调，最后在多个心音数据集上进行性能评估。

关键创新：本研究的创新在于将去噪扩散模型与传统信号处理相结合，创造性地生成了高质量的增强数据集，从而显著提升了心音分类的准确性。

关键设计：在模型训练中，采用了特定的损失函数和网络结构，确保模型能够有效学习多模态和多通道心音信号的特征。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果表明，模型在CinC 2016数据集上达到了92.48%的准确率和93.05%的无加权平均召回率，在同步PCG和ECG信号上也取得了93.14%的准确率，显示出显著的性能提升，验证了增强数据集的有效性。

🎯 应用场景

该研究具有广泛的应用潜力，尤其在心血管疾病的早期筛查和监测中。通过提高心音分类的准确性，能够为临床医生提供更可靠的辅助诊断工具，进而改善患者的健康管理和预后。

📄 摘要（原文）

Cardiovascular diseases (CVDs) are the leading cause of death worldwide, accounting for approximately 17.9 million deaths each year. Early detection is critical, creating a demand for accurate and inexpensive pre-screening methods. Deep learning has recently been applied to classify abnormal heart sounds indicative of CVDs using synchronised phonocardiogram (PCG) and electrocardiogram (ECG) signals, as well as multichannel PCG (mPCG). However, state-of-the-art architectures remain underutilised due to the limited availability of synchronised and multichannel datasets. Augmented datasets and pre-trained models provide a pathway to overcome these limitations, enabling transformer-based architectures to be trained effectively. This work combines traditional signal processing with denoising diffusion models, WaveGrad and DiffWave, to create an augmented dataset to fine-tune a Wav2Vec 2.0-based classifier on multimodal and multichannel heart sound datasets. The approach achieves state-of-the-art performance. On the Computing in Cardiology (CinC) 2016 dataset of single channel PCG, accuracy, unweighted average recall (UAR), sensitivity, specificity and Matthew's correlation coefficient (MCC) reach 92.48%, 93.05%, 93.63%, 92.48%, 94.93% and 0.8283, respectively. Using the synchronised PCG and ECG signals of the training-a dataset from CinC, 93.14%, 92.21%, 94.35%, 90.10%, 95.12% and 0.8380 are achieved for accuracy, UAR, sensitivity, specificity and MCC, respectively. Using a wearable vest dataset consisting of mPCG data, the model achieves 77.13% accuracy, 74.25% UAR, 86.47% sensitivity, 62.04% specificity, and 0.5082 MCC. These results demonstrate the effectiveness of transformer-based models for CVD detection when supported by augmented datasets, highlighting their potential to advance multimodal and multichannel heart sound classification.