通过PCG信号检测心脏门疾病的强大和高效的工作流程:集成WCNN,MFCC优化和信号质量评估
Shin-Chi Lai1,2, Yen-Ching Chang3, Ying-Hsiu Hung4
1Department of Automation Engineering, National Formosa University, Yunlin 632301, Taiwan.
Sensors (Basel, Switzerland)
|November 13, 2025
概括
这项研究引入了一种高效的系统,用于从心脏声音 (PCG) 信号中识别心脏膜疾病 (HVD),使用轻量级的神经网络. 该系统以低计算成本实现高精度,可实现实时HVD检测.
科学领域:
- 生物医学工程 生物医学工程
- 人工智能在医学中的应用
- 信号处理 信号处理
背景情况:
- 心脏膜疾病 (HVDs) 构成了严重的健康负担.
- 准确有效的HVD诊断工具对于及时干预至关重要.
- 声心图 (PCG) 信号提供了一种非侵入性方法来评估HVD.
研究的目的:
- 从PCG信号中开发一个计算效率高,准确的HVD识别系统.
- 实施适合现实世界临床部署的端到端工作流.
- 在PCG信号分析中增强噪声强度和特征提取.
主要方法:
- 使用轻量加权卷积神经网络 (WCNN) 与关键加权计算 (KWC) 层进行噪声强度.
- 采用GradCAM指导的Mel频 cepstral系数 (MFCC),以优化特征提取.
- 纳入带能比 (BER) 度量来评估PCG信号质量并识别与噪声相关的错误分类.
主要成果:
- 在GitHub PCG数据库上实现了高分类准确率99.6%,在PhysioNet/CinC Challenge 2016数据库上达到90.74%.
- 与之前的研究相比,在显著减少的参数 (312,357) 和较低的计算成本 (4.5M FLOP) 的情况下,证明了卓越的性能.
- 在Raspberry Pi上成功实现实时HVD检测,实现1.4秒信号的检测时间为1.87ms.
结论:
- 拟议的WCNN系统为PCG信号的HVD识别提供了一个计算效率高和高度准确的解决方案.
- 该系统的轻量级设计和实时处理能力使其适合于实际,广泛部署.
- 将KWC层和MFCC与GradCAM集成,有效地解决了PCG分析中的噪声挑战.
相关概念视频
01:30Pulse rhythm
1.3K
Pulse rhythm refers to the pattern of pulsations within specific intervals, offering valuable insights into the regularity or irregularity of the heart's beats as observed through the pattern of pulsation within specific intervals. A regular pulse exhibits a consistent heart rate with uniform waveforms and pulsation force, variations of which can be classified as normal, weak, or bounding.
Conversely, an irregular pulse pattern is termed dysrhythmia, stemming from disruptions in cardiac...
Conversely, an irregular pulse pattern is termed dysrhythmia, stemming from disruptions in cardiac...
1.3K
01:30Classification of Signals
1.3K
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
1.3K