一个级联的CNN-LSTM框架,用于从表面电肌图信号中量化呼吸运动
Yihan Huang1, Xiangbin Zhang2, Di Yan2
1Sichuan University, Sichuan University, Chengdu 610041, China, Chengdu, Sichuan, 610041, CHINA.
Physics in medicine and biology
|February 6, 2026
概括
一个新的深度学习框架有效地抑制了隔膜表面电肌图 (sEMG) 信号中的心电图 (ECG) 干扰. 这使得临床应用中可以准确的实时呼吸监测,优于传统方法.
科学领域:
- 生物医学工程 生物医学工程
- 信号处理 信号处理
- 机器学习 机器学习
背景情况:
- 隔膜表面电肌图 (sEMG) 信号对于实时呼吸监测在临床环境中至关重要,如放射治疗和重症监护.
- 电心电图 (ECG) 干扰通常会污染sEMG信号,阻碍精确的呼吸运动估计.
- 现有的心电图器件去除方法经常带来延迟,并依赖于线性假设,限制实时临床适用性.
研究的目的:
- 开发一个强大的深度学习框架,用于从sEMG信号中实时量化呼吸运动.
- 为了实现高准确度的人工物抑制和呼吸运动的准确估计.
- 在临床呼吸监测中克服传统信号处理技术的局限性.
主要方法:
- 提出了一个级联深度学习框架,集成了用于呼吸系统sEMG组件隔离的CNN-LSTM模型和用于非线性特征抽象的多尺度CNN.
- 从45名受试者中收集了sEMG和呼吸系统数据 (20名用于培训,25名用于验证).
- 交叉相关性分析用于评估sEMG衍生的呼吸和参考信号之间的相关性.
主要成果:
- 拟议的深度学习方法实现了较高的相关系数 (皮尔森的r=0.949±0.030) 与腹部压力衍生的呼吸与门 (0.910±0.046) 和模板减法 (0.859±0.081) 相比.
- 该方法即使没有后处理,也与参考信号的相关性明显更高,突出显示了其实时文物抑制能力.
- 这表明在从受污染的sEMG信号中精确量化呼吸运动方面具有强大的性能.
结论:
- 开发的深度学习框架提供了一种高效的解决方案,用于在sEMG信号中进行高准确度的文物抑制.
- 它可以实现准确和实时的呼吸监测,这对于临床应用至关重要.
- 这种方法推进了生理信号处理领域,以改善患者护理和监测.
更多相关视频
06:53Management of Respiratory Motion Artefacts in 18F-fluorodeoxyglucose Positron Emission Tomography using an Amplitude-Based Optimal Respiratory Gating Algorithm
Published on: July 23, 2020
6.1K
09:14Surface Electromyographic Biofeedback as a Rehabilitation Tool for Patients with Global Brachial Plexus Injury Receiving Bionic Reconstruction
Published on: September 28, 2019
12.1K
相关概念视频
Intracellular Signaling Cascades
53.7K
Once a ligand binds to a receptor, the signal is transmitted through the membrane and into the cytoplasm. The continuation of a signal in this manner is called signal transduction. Signal transduction only occurs with cell-surface receptors, which cannot interact with most components of the cell, such as DNA. Only internal receptors can interact directly with DNA in the nucleus to initiate protein synthesis. When a ligand binds to its receptor, conformational changes occur that affect the...
53.7K
Cell-surface Signaling
54.6K
Hormones—or any molecule that binds to a receptor, known as a ligand—that are lipid-insoluble (water-soluble) are not able to diffuse across the cell membrane. In order to be able to affect a cell without entering it, these hormones bind to receptors on the cell membrane. When a first messenger, a hormone, binds to a receptor, a signal cascade is set off, causing second messengers, proteins inside the cell, to become activated, resulting in downstream effects.
54.6K
MAPK Signaling Cascades
8.5K
Mitogen-activated protein kinase, or MAPK pathway, activates three sequential kinases to regulate cellular responses such as proliferation, differentiation, survival, and apoptosis. The canonical MAPK pathway starts with a mitogen or growth factor binding to an RTK. The activated RTKs stimulate Ras, which recruits Raf or MAP3 Kinase (MAPKKK), the first kinase of the MAPK signaling cascade. Raf further phosphorylates and activates MEK or MAP2 Kinases (MAPKK), which in turn phosphorylates MAP...
8.5K
Amplifying Signals via Enzymatic Cascade
18.6K
When a ligand binds to a cell-surface receptor, the receptor's intracellular domain changes shape, which may either activate its enzyme function or allow its binding to other molecules. The initial signal is amplified by most signal transduction pathways. This means that a single ligand molecule can activate multiple molecules of a downstream target. Proteins that relay a signal are most commonly phosphorylated at one or more sites, activating or inactivating the protein. Kinases catalyze...
18.6K
Rab Cascades
3.6K
Rab GTPases act in a regulated cascade during membrane fusion, helping the lipid bilayers mix. The Rab family of proteins are active when bound to GTP, and inactive when bound to GDP. Hence, they act as guanine nucleotide-dependent molecular switches. Rab-GTP recognizes and binds to long or short-range tethering proteins to capture the target vesicle. These tethers coordinate with SNAREs on the vesicle and the target membrane to assemble the trans SNARE complex that locks the mixing bilayers.
3.6K
Yeast Signaling
17.3K
Yeasts are single-celled organisms, but unlike bacteria, they are eukaryotes (cells with a nucleus). Cell signaling in yeast is similar to signaling in other eukaryotic cells. A ligand, such as a protein or a small molecule released from a yeast cell, attaches to a receptor on the cell surface. The binding stimulates second-messenger kinases to activate or inactivate transcription factors that further regulate gene expression. Many of the yeast intracellular signaling cascades have similar...
17.3K
